Eprint first made available on ORBi (E-prints, working papers and research blog)
Assessing and predicting review helpfulness: Critical review, open challenges and research agenda
Hoffait, Anne-Sophie; Ittoo, Ashwin; Schyns, Michael
2018
The issues of determining what makes a customer review helpful and how to predict review helpfulness have received significant attention in recent years. However, the current literature is highly heterogeneous with contradictory findings.
We critically synthesize extant literature and identify factors responsible for these contradictions which we classify into four dimensions, viz. datasets, features, approach and review helpfulness operationalization, and clarify the prevailing confusion.
We highlight research gaps, and propose novel research directions to bridge them and to advance the state-of-the-art. We provide resources such as synthetic tables, which summarize past research and develop a (future) research roadmap. These resources not only provide a concise overview of current research, but also illustrate its heterogeneity and serve as a valuable basis to ground future research.
Eprint first made available on ORBi (E-prints, working papers and research blog)
Predictive Maintenance of Technical Faults Using Machine Learning : A Case Study in Air Transport
Peters, Florian; Aerts, Stéphanie; Schyns, Michael
2020
Eprint first made available on ORBi (E-prints, working papers and research blog)
Les réseaux de neurones: principes et applicatioàn à la détection financière des faillites
Schyns, Michael
1997
Eprint first made available on ORBi (E-prints, working papers and research blog)
A Comparison of Departure Time of Day Formulations
Airline passengers’ itinerary choices are influenced by many factors including carriers, prices, the number of connections, and departure times. This paper compares three different methods that have been used to model departure time of day preferences. The first is a discrete formulation that uses indicator variables to represent the hour of departure. The next two methods are based on a continuous formulation that uses a series of sine and cosine functions. One assumes departure time preferences over a 24-hour cycle and the other uses shorter cycle lengths that account for fewer departures during certain hours of the day. We compare models using itineraries in the Continental U.S. that are separated by two time zones. Although the discrete formulation fits the data better, the two continuous time of day formulations are preferred as they provide more intuitive predictions and require fewer parameters. Results between the two continuous time of day formulations are similar but differ in how strongly they weight itineraries that depart very early or very late in the day. Based on empirical results, we recommend testing both 24-hour and less than 24-hour cycle lengths for a particular dataset.
Eprint already available on another site (E-prints, working papers and research blog)
Continuous Departure Time of Day Preferences for Continental U.S. Airline Markets Segmented by Distance, Direction of Travel, Number of Time Zones, Day of Week and Itinerary Type
Airlines use itinerary choice models to allocate the total number of passengers in a city pair to specific itineraries. In a related paper, we estimated a multinomial logit (MNL) itinerary choice model using database of more than 3 million tickets for Continental U.S. markets provided by the Airlines Reporting Corporation that accounted for price endogeneity. The size and comprehensiveness of our database allowed us to estimate highly refined continuous departure time of day preference curves that account for distance, direction of travel, the number of time zones traversed, departure day of week and itinerary type (outbound, inbound or one-way). This paper and accompanying Excel spreadsheet located at http://garrowlab.ce.gatech.edu contain the results of all model coefficients (including the 1260 time of day parameters) and summarize results in a series of ten figures. These highly-refined time of day preference curves can be used by airlines, researchers, and government organizations in the evaluation of demand-management and other policies.
Eprint first made available on ORBi (E-prints, working papers and research blog)
Early Detection of University Students in Potential Difficulty
Hoffait, Anne-Sophie; Schyns, Michael
2016
Using data mining methods, this paper presents a new means of identifying freshmen's profiles likely to face major difficulties to complete their first academic year. Academic failure is a relevant issue at a time when post-secondary education is ever more critical to economic success. We aim at early detection of potential failure using student data available at registration, i.e. school records and environmental factors, with a view to timely and efficient remediation and/or study reorientation. For the sake of accuracy, we adapt three data mining methods, namely random forest, logistic regression and artificial neural network algorithms. Real data pertaining to undergraduates at the University of Liège (Belgium), illustrates our methodology.
Working paper (E-prints, working papers and research blog)
Combined analysis of single cell RNA-Seq and ATAC-Seq data reveals putative regulatory toggles operating in native and iPS-derived retina.
We report the generation and analysis of single-cell RNA-Seq data (> 38,000 cells) from native and iPSC-derived murine retina at four matched developmental stages spanning the emergence of the major retinal cell types. We combine information from temporal sampling, visualization of 3D UMAP manifolds, pseudo-time and RNA velocity analyses, to show that iPSC-derived 3D retinal aggregates broadly recapitulate the native developmental trajectories. However, we show relaxation of spatial and temporal transcriptome control, premature emergence and dominance of photoreceptor precursor cells, and susceptibility of dynamically regulated pathways and transcription factors to culture conditions in iPSC-derived retina. We generate bulk ATAC-Seq data for native and iPSC-derived murine retina identifying ~125,000 peaks. We combine single-cell RNA-Seq with ATAC-Seq information and obtain evidence that approximately half the transcription factors that are dynamically regulated during retinal development may act as repressors rather than activators. We propose that sets of activators and repressors with cell-type specific expression constitute regulatory toggles that lock cells in distinct transcriptome states underlying differentiation. We provide evidence supporting our hypothesis from the analysis of publicly available single-cell ATAC-Seq data for adult mouse retina. We identify subtle but noteworthy differences in the operation of such toggles between native and iPSC-derived retina particularly for the Etv1, Etv5, Hes1 and Zbtb7a group of transcription factors.
Dataset
Working paper (E-prints, working papers and research blog)
A Recursive Algorithm for Synchronized Rich Vehicle Routing in Air Cargo Ground Handling
Tonka, Jenny; Paquay, Célia; Schyns, Michael
2024
We study a rich vehicle coordination problem that arises in air cargo ground handling: a set of services should be provided by different vehicle types to different clients at different locations within defined time intervals, and various vehicle interdependencies exist. We first formalize the problem as a set of rich Vehicle Routing Problems that are bound together by multiple synchronization constraints. In particular, we consider compulsory vehicle pairings, precedence constraints between services, as well as goods transfers between vehicles of different types. The latter can involve more than two vehicles, implying cascading dependencies that greatly complicate the problem. We then develop a client-centered heuristic approach using a recursive procedure that is able to solve the problem as a whole without having to handle constraints separately, as is often the case in vehicle routing problems with such complex structures. We seek to minimize total service time to produce safety time buffers that would help absorb the impact of disruptions and subsequently reduce the number and duration of delays. The algorithm is designed to be easily adaptable to other application domains, and tests on real instances from a major cargo airport in Europe show that it performs well.
Eprint first made available on ORBi (E-prints, working papers and research blog)
Grafting Information in Scenario Trees: Application to Option Prices
Schyns, Michael; Crama, Yves; Hübner, Georges
2005
The high level of sophistication in portfolio management modeling techniques often goes along with very large output sensitivity to parameter choices. As a potential solution to this problem, this paper proposes a consistent and flexible methodology to represent the distribution of future values of a portfolio through scenario trees. This
methodology relies on the information contained in current option prices in order to generate the probability density function of future returns. This density function can be used, in turn, to generate scenario trees . As an illustration, a tree of scenarios based on S&P500 options is built and then used to compute arbitrage-free option prices. The approach preserves information embedded in options prices and is able to provide very accurate values for out-of-sample options. The high level of numerical accuracy of the framework is reproduced on different samples. The scenario tree approach also provides stable pricing results when confronted with the passage of time. The results derived from our model are comparable to those obtained from Rubinstein’s
[1994] methodology, although both models fulfill different objectives.
Eprint already available on another site (E-prints, working papers and research blog)
How to optimally load a set of containers into an aircraft
Eprint first made available on ORBi (E-prints, working papers and research blog)
The digital twin concept: a definition attempt
Tonka, Jenny; Schyns, Michael
2021
Nowadays more than ever, the digital transition is an essential evolution for the survival of industrial activity. Digital twins (DT) are a good way for enterprises to face this new challenge. Although the concept is not new, there is still no general agreement on its definition. Therefore, this paper seeks to identify what are the key elements of DTs and attempts to formulate a definition that group them all together.
Doctoral thesis (Dissertations and theses)
Modelling Financial Data and Portfolio Optimization Problems
Schyns, Michael
2001
This doctoral dissertation in management science, entitled “Modelling Financial Data and
Portfolio Optimization Problems”, consists of two independent parts, whose unifying theme
is the construction and solution of mathematical programming models motivated by portfolio
selection problems. As such, this work is located at the interface of operations research and of
finance. It draws heavily on techniques and theoretical results originating in both disciplines.
The first part of the dissertation (Chapter 2) deals with an extension of Markowitz
model and takes into account some of the side-constraints faced by a decision-maker when
composing an investment portfolio, viz. lower and upper bounds on the quantities traded,
and upper bounds on the number of assets included in the portfolio. We focus on the
algorithmic difficulties raised by this model and we describe an original simulated annealing
heuristic for its solution.
The second (and largest) part of the thesis deals with a new multiperiod model for the
optimization of a portfolio of options linked to a single index (Chapters 4-10). The objective
of the model is to maximize the expected return of the portfolio under constraints limiting its
value-at-risk. The model contains several interesting features, like the possibility to rebalance
the portfolio with options introduced at the start of each period, explicit consideration of
transaction costs, realistic pricing of options, consideration of advanced probability models
to represent the future, etc. Some deep theoretical results from the financial literature
are exploited in order to enrich the model and to extend its applicability. In particular,
several available schemes for the generation of scenarios and for option pricing have been
critically examined, and the most appropriate ones have been implemented. Furthermore,
several optimization approaches (heuristic or exact procedures) have also been developed,
implemented and tested.
The models investigated in the dissertation bear on very different portfolio problems, draw
on separate streams of scientific literature, and are handled by distinct algorithmic techniques.
Therefore, the corresponding parts of the dissertation are fully independent, and each part
contains its own specific introduction and literature review.
Master’s dissertation (Dissertations and theses)
Prétraitement de données en reconnaissance de formes par RNA
Schyns, Michael
1993
Les réseaux de neurones n'ont malheureusement pas que des avantages. Leur taille croît avec la quantité et la complexité des données à traiter. Or le principal inconvénient du RNA est lié à sa complexité. Plus elle est grande, plus le RNA sera difficile et coûteux à implémenter physiquement et plus son temps d'apprentissage sera grand. Pour résoudre ce problème, une solution est de prétraiter les données pour diminuer leur taille.
Il nous a dès lors été demandé d'analyser trois méthodes de compression applicables au traitement par RNA : la méthode de Karhunen-Loève, la méthode LPC (Linear Predictive Coding) et la méthode NLPCA (Non Linear Principal Composant Analysis). Nous en avons ajouté une : la méthode LSP (Line Spectral Pair). Les chapitres qui y sont consacrés tenteront de convaincre le lecteur de l'efficacité de ces procédés. Nous déterminerons également comment choisir la méthode à utiliser pour un problème de classification posé à un RNA.
Article (Scientific journals)
"Circuler" dans la jeunesse liégeoise de Simenon. Enjeux de création et de réception d'un dispositif de médiation, muséalisation et patrimonialisation du littéraire par le biais de la réalité augmentée
Cet article présente les enjeux de création et de réception du projet de rénovation du parcours touristique dédié à Georges Simenon à Liège (Belgique), ville qu'il a arpentée durant sa jeunesse (1903-1922). Ce projet se matérialise par la révision des contenus textuels du parcours, par l'ajout significatif de documents textuels, sonores et interactifs, ainsi que par la création d’une application pour smartphone contenant une expérience en réalité augmentée, prenant place en fin de parcours dans le célèbre local de la "Caque" (véritable motif littéraire chez Simenon). L’ambition de cet article est de présenter les enjeux qu’impliquent la production d’une forme de médiation expérientielle, se construisant sur l'expérience de Simenon à Liège et celle du visiteur, qui soit à la fois documentaire, patrimoniale et scientifique.
Editorial reviewed
Article (Scientific journals)
Comparing the transcriptome of developing native and iPSC-derived mouse retinae by single cell RNA sequencing.
We report the generation and analysis of single-cell RNA-Seq data (> 38,000 cells) from mouse native retinae and induced pluripotent stem cell (iPSC)-derived retinal organoids at four matched stages of development spanning the emergence of the major retinal cell types. We combine information from temporal sampling, visualization of 3D UMAP manifolds, pseudo-time and RNA velocity analyses, to show that iPSC-derived 3D retinal organoids broadly recapitulate the native developmental trajectories. However, we observe relaxation of spatial and temporal transcriptome control, premature emergence and dominance of photoreceptor precursor cells, and susceptibility of dynamically regulated pathways and transcription factors to culture conditions in retinal organoids. We demonstrate that genes causing human retinopathies are enriched in cell-type specifying genes and identify a subset of disease-causing genes with expression profiles that are highly conserved between human retinae and murine retinal organoids. This study provides a resource to the community that will be useful to assess and further improve protocols for ex vivo recapitulation and study of retinal development.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Perception of avatars nonverbal behaviors in virtual reality
2023 • In Psychology and Marketing, 40 (11), p. 2464-2481
Virtual reality has shown great potential in many fields, especially in business and psychology. By immersing someone in a new computer-generated reality, it is possible to create realistic, safe, and controllable simulations for research and training, as well as new three-dimensional-enriched consumer experiences and services. Most of these environments, especially in the metaverse, rely on virtual representations of people called avatars. The design and non-verbal behaviors of these avatars must be carefully crafted to provide a realistic and truly immersive experience. This paper aims to understand how avatar nonverbal behaviors (i.e., body posture, facial expression, and head movement) are perceived by users immersed in a virtual reality context, a very common situation encountered in many simulations and especially during training. Therefore, the first objective of this study is to validate, through an experiment with 125 participants, how the audience's levels of emotional valence and arousal are perceived in virtual reality. Based on these results, a library of audience non-verbal behaviors corresponding to different arousal and valence levels is now available for future applications. The experiment also examines the benefits of using low-end versus high-end virtual reality headsets, and photo-realistic versus cartoon avatars. The results have implications for the design of realistic, challenging, and interactive virtual audiences.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Developing a video game as an awareness and research tool based on SARS-CoV-2 epidemiological dynamics and motivational perspectives
In mid-2020, the University of Liège (ULiège, Belgium) commissioned the ULiège Video Game Research Laboratory (Liège Game Lab) and the AR/VR Lab of the HEC-Management School of ULiège, to create a serious game to raise awareness of preventive measures for its university community. This project has its origins in two objectives of the institutional policy of ULiège in response to the crisis caused by SARS-CoV-2: to raise awareness among community members of various preventive actions that can reduce the spread of the virus and to inform about the emergence and progression of a pandemic. After almost two years of design, the project resulted in the creation of SARS WARS, a decision-making management game for browsers and smartphones. This article presents the creative process of the game, specifically the integration of an adapted SEIR (susceptible-exposed-infectious-recovered) model, as well as the modeling of inter-compartmental circulation dynamics in the game’s algorithm, but also the various limitations observed regarding its original missions and possibilities for future work. The SARS-CoV-2 video game project may be considered as an innovative way to translate epidemiology into a language that can be used in the scope of citizen sciences. On the one hand, it provides an engaging tool and encourages active participation of the audience. On the other hand, it allows us to have a better understanding of the dynamic changes of a pandemic or an epidemic (crisis preparedness, monitoring and control) and to anticipate potential consequences given found parameters at set time (emerging risk identification), while offering insights for impact on some parameters on motivation (social science aspect).
Peer Reviewed verified by ORBi
Article (Scientific journals)
Covid-19: contribution of clinical characteristics and laboratory features for early detection of patients with high risk of severe evolution
2022 • In Acta Clinica Belgica, 77 (2), p. 261-267
The aim of this study was to identify early clinical and laboratory predictive factors of a severe coronavirus disease 2019 (COVID-19). The study revealed clinical and laboratory features able to predict high risk of ICU requirement, or even death, at admission time. These results provide a potential tool for patient’s triage in a context of pandemic.
Peer Reviewed verified by ORBi
Complete issue (Scientific journals)
Special issue: Twelfth Workshop on Models and Algorithms for Planning and Scheduling Problems (MAPSP 2015)
Crama, Yves; Goossens, Dries; Leus, Roelet al.
2017 • In Journal of Scheduling, 20 (6), p. 543-711
This special issue of the Journal of Scheduling contains ten papers presented at the Twelfth Workshop on Models and Algorithms for Planning and Scheduling Problems (MAPSP 2015), held from June 8 to June 12, 2015, in La Roche-en-Ardenne, Belgium.
2024 • In Annals of Tourism Research: A Social Sciences Journal, 109
In three studies (a lab experiment, a field experiment, and a qualitative study), this
research investigates memories formed by tourism brand experiences in VR.
Specifically, this work establishes to what extent tourism brand experiences in VR are
remembered by consumers as direct brand interactions, why and how VR experiences
affect memories, and to what extent the episodic and semantic memories of the
tourism brand are formed in VR. Moreover, using a bespoke VR environment and
adopting a longitudinal approach, this study evidences how accuracy and confidence in
episodic and semantic memories of a tourism brand formed in VR evolve over time.
Theoretical and managerial implications are considered.
Peer Reviewed verified by ORBi
Article (Scientific journals)
RelaxMCD: smooth optimisation for the Minimum Covariance Determinant estimator
Schyns, Michael; Haesbroeck, Gentiane; Critchley, Frank
2010 • In Computational Statistics and Data Analysis, 54 (4), p. 843-857
The Minimum Covariance Determinant (MCD) estimator is a highly robust procedure for estimating the
center and shape of a high dimensional data set. It consists of determining a subsample of h points out
of n which minimizes the generalized variance. By definition, the computation of this estimator gives rise
to a combinatorial optimization problem, for which several approximative algorithms have been developed.
Some of these approximations are quite powerful, but they do not take advantage of any smoothness in the
objective function. In this paper, focus is on the approach outlined in a general framework in Critchley et
al. (2009) and which transforms any discrete and high dimensional combinatorial problem of this type into a
continuous and low-dimensional one. The idea is to build on the general algorithm proposed by Critchley et
al. (2009) in order to take into account the particular features of the MCD methodology. More specifically,
both the adaptation of the algorithm to the specific MCD target function as well as the comparison of this
“specialized” algorithm with the usual competitors for computing MCD are the main goals of this paper. The
adaptation focuses on the design of “clever” starting points in order to systematically investigate the search
domain. Accordingly, a new and surprisingly efficient procedure based on the well known k-means algorithm
is constructed. The adapted algorithm, called RelaxMCD, is then compared by means of simulations and
examples with FASTMCD and the Feasible Subset Algorithm, both benchmark algorithms for computing
MCD. As a by-product, it is shown that RelaxMCD is a general technique encompassing the two others,
yielding insight about their overall good performance.
Peer Reviewed verified by ORBi
Article (Scientific journals)
A relaxed approach to combinatorial problems in robustness and diagnostics
2010 • In Statistics and Computing, 20 (1), p. 99-115
A range of procedures in both robustness and diagnostics require optimisation of a target functional over all subsamples of given size. Whereas such combinatorial problems are extremely difficult to solve exactly, something less than the global optimum can be ‘good enough’ for many practical purposes, as shown by example. Again, a relaxation strategy embeds these discrete, high-dimensional problems in continuous, low-dimensional ones. Overall, nonlinear optimisation methods can be exploited to provide a single, reasonably fast algorithm to handle a wide variety of problems of this kind, thereby providing a certain unity. Four running examples illustrate the approach. On the robustness side, algorithmic approximations to minimum covariance determinant (MCD) and least trimmed squares (LTS) estimation. And, on the diagnostic side, detection of multiple multivariate outliers and global diagnostic use of the likelihood displacement function. This last is developed here as a global complement to Cook’s (in J. R. Stat. Soc. 48:133–169, 1986) local analysis. Appropriate convergence of each branch of the algorithm is guaranteed for any target functional whose relaxed form is—in a natural generalisation of concavity, introduced here—‘gravitational’. Again, its descent strategy can downweight to zero contaminating cases in the starting position. A simulation study shows that, although not optimised for the LTS problem, our general algorithm holds its own with algorithms that are so optimised. An adapted algorithm relaxes the gravitational condition itself.
Peer Reviewed verified by ORBi
Article (Scientific journals)
An Ant Colony System for Responsive Dynamic Vehicle Routing
Schyns, Michael
2015 • In European Journal of Operational Research, 245 (3), p. 704-718
We present an algorithm based on an Ant Colony System to deal with a broad
range of Dynamic Capacitated Vehicle Routing Problems with Time Windows, (partial)
Split Delivery and Heterogeneous fleets (DVRPTWSD). Besides the traditional distance
criterion, we address the important case of responsiveness. Responsiveness is defined here
as completing a delivery as soon as possible, within the time window, such that the client or
the truck may restart its activities. This is crucial for many production or service activities
in different fields: express parcel deliveries, taxi services, Just in Time production, express
repair services, medical care, petrol station replenishment, etc. We develop an interactive
web-based solution to allow dispatchers to take new information into account in real-time.
The algorithm and its parametrization were tested on real and artificial instances. We
first illustrate our approach with a problem submitted by Liege Airport, the 8th biggest
cargo airport in Europe. The goal is to develop a decision system to optimize the journey
of the refueling trucks. We then consider some classical VRP benchmarks with extensions
for more complex problems.
Peer Reviewed verified by ORBi
Article (Scientific journals)
The Airline Container Loading Problem with Pickup and Delivery
Lurkin, Virginie; Schyns, Michael
2015 • In European Journal of Operational Research, 244 (3), p. 955-965
This paper considers the loading optimization problem for a set of containers and pallets
transported into a cargo aircraft that serves multiple airports. Because of pickup and
delivery operations that occur at intermediate airports, this problem is simultaneously a
Weight & Balance Problem and a Sequencing Problem. Our objective is to minimize fuel
and handling operation costs. This problem is shown to be NP-hard. We resort to a
mixed integer linear program. Based on real-world data from a professional partner (TNT
Airways), we perform numerical experiments using a standard B&C library. This approach
yields better solutions than traditional manual planning, which results in substantial cost
savings.
Peer Reviewed verified by ORBi
Article (Scientific journals)
MIP-based constructive heuristics for the three-dimensional Bin Packing Problem with transportation constraints
2018 • In International Journal of Production Research, 56 (4), p. 1581-1592
This article is about seeking a good feasible solution in a reasonable amount of computation time to the three-dimensional Multiple Bin Size Bin Packing Problem (MBSBPP). The MBSBPP studied considers additional constraints encountered in real world air transportation situations, such as cargo stability and the particular shape of containers. This MBSBPP has already been formulated as a Mixed Integer linear Programming problem, but as yet only poor results have been achieved for even fairly small problem sizes. The goal of the work this paper describes is to develop heuristics that are able to quickly provide good initial feasible solutions for the MBSBPP. Three methodologies are considered, which are based on the decomposition of the original problem into easier subproblems: the matheuristics Relax-and-Fix, Insert-and-Fix and Fractional Relax-and-Fix.
They have been parametrised on real data sets and then compared to each other. In particular, two of these techniques show promising results in reasonable computational times.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Optimal selection of a portfolio of options under Value-at-Risk constraints: a scenario approach
Schyns, Michael; Crama, Yves; Hübner, Georges
2010 • In Annals of Operations Research, 181, p. 683-708
This paper introduces a multiperiod model for the optimal selection of a financial portfolio of options linked to a single index. The objective of the model is to maximize the expected return of the portfolio under constraints limiting its Value-at-Risk. We rely on scenarios to represent future security prices. The model contains several interesting features, like the consideration of transaction costs, bid-ask spreads, arbitrage-free option pricing, and the possibility to rebalance the portfolio with options introduced at the start of each period. The resulting mixed integer programming model is applied to realistic test instances involving options on the S&P500 index. In spite of the large size and of the numerical difficulty of this model, near-optimal solutions can be computed by a standard branch-and-cut solver or by a specialized heuristic. The structure and the financial features of the selected portfolios are also investigated.
Peer Reviewed verified by ORBi
Article (Scientific journals)
A Mixed Integer Programming formulation for the three dimensional bin packing problem deriving from an air cargo application
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2016 • In International Transactions in Operational Research, 23 (1-2), p. 187-213
The present paper looks into the problem of optimising the loading of boxes
into containers. The goal is to minimise the unused volume. This type of problem belongs
to the family of Multiple Bin Size Bin Packing Problems. The approach includes an extensive
set of constraints encountered in real-world applications in the three-dimensional case:
the stability, the fragility of the items, the weight distribution and the possibility to rotate
the boxes. It also includes the specific situation in which containers are truncated parallelepipeds.
This is typical in the field of air transportation. While most papers on cutting
and packing problems describe ad-hoc procedures, this paper proposes a mixed integer linear
program. The validity of this model is tested on small instances.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Simulated annealing for complex portfolio selection problems
Crama, Yves; Schyns, Michael
2003 • In European Journal of Operational Research, 150 (3), p. 546-571
This paper describes the application of a simulated annealing approach to the solution of a complex portfolio selection model. The model is a mixed integer quadratic programming problem which arises when Markowitz' classical mean-variance model is enriched with additional realistic constraints. Exact optimization algorithms run into difficulties in this framework and this motivates the investigation of heuristic techniques. Computational experiments indicate that the approach is promising for this class of problems. (C) 2003 Elsevier B.V. All rights reserved.
Peer Reviewed verified by ORBi
Article (Scientific journals)
A robust heuristic for the optimal selection of a portfolio of stocks
Schyns, Michael
2010 • In International Journal of Operational Research, 9 (3), p. 258-271
This paper introduces a new optimization heuristic for the robustification of critical inputs under consideration in many problems. It is shown that it allows to improve significantly the quality and the stability of the results for two classical financial problems, i.e. the Markowitz' portfolio selection problem and the computation of the financial beta.
Focus here is on the robust Minimum Covariance Determinant (MCD) estimator which can easily be substituted to the classical estimators of location and scatter. By definition, the computation of this estimator gives rise to a combinatorial optimization problem. We present a new heuristic, called 'RelaxMCD', which is based on a relaxation of the problem to the continuous space. The utility of this approach and the performance of our heuristic, with respect to other competitors, are illustrated through extensive simulations.
2012 • In Journal of the Operational Research Society, 63, p. 1271–1283
The goal of this paper is the development of a new mixed integer linear program designed for optimally loading
a set of containers and pallets into a compartmentalised cargo aircraft. It is based on real-world problems submitted by a professional partner.
This model takes into account strict technical and safety constraints. In addition to the standard goal of optimally positioning the centre of gravity, we also propose a new approach based on the moment of inertia.
This double goal implies an increase in aircraft efficiency and a decrease in fuel consumption.
Cargo loading generally remains a manual, or at best a computer assisted, and time consuming task.
A fully automatic software was developed to quickly compute optimal solutions.
Experimental results show that our approach achieves better solutions than manual planning, within only a few seconds.
Peer Reviewed verified by ORBi
Article (Scientific journals)
The Impact of Virtual Reality Exposure on Stress Level and Sense of Competence in Ambulance Workers
Virtual reality (VR) exposure is one of the tools used in clinical psychology to treat anxiety dis-orders. It is also used to enhance the resilience of soldiers by confronting them with virtual combat environments. Increasing their resilience could strengthen them against the negative consequences of trauma exposure or the suffering experienced by people they rescued. Most studies focused on military and emergency medical staff but none has so far investigated ambu-lance workers’ experience (AW) while they are daily confronted with traumatic situations. The current study aims to assess the impact of a single VR exposure session on AW’ competence and stress. Forty participants were randomly assigned to either a VR immersion (experimental group, N = 20) or an audio immersion (control group, N = 20) of a shooting attack situation. The main hypotheses were that VR would lead to a decrease of anxiety, as measured by visual analogue scales, as well as an increase in the sense of competence compared to the control situa-tion. Results showed a significant reduction in the fear in both groups. Besides, results revealed an increase of the sense of competence after the VR immersion, and a reduction of the tension in the control group, even if these differences did not reach statistical significance’s level (p = 0.06). Although our hypotheses were only partially confirmed, since beneficial effects of either VR and the audio description on stress were observed, findings suggested that VR exposure could be a useful way to increase the resilience of the AW.
Peer Reviewed verified by ORBi
Article (Scientific journals)
A tailored two-phase constructive heuristic for the three-dimensional Multiple Bin Size Bin Packing Problem with transportation constraints
Paquay, Célia; Limbourg, Sabine; Schyns, Michael
2018 • In European Journal of Operational Research, 267 (1), p. 52-64
This paper considers the three-dimensional Multiple Bin Size Bin Packing Problem which
consists in packing a set of cuboid boxes into containers of various shapes with minimising
unused space. The problem is extended to air cargo where bins are Unit Load Devices,
especially designed for fitting in aircraft. We developed a fast constructive heuristic able to
manage the different constraints met in transportation. The heuristic is split into two distinct
phases. The first phase deals with the packing of boxes into identical bins using an extension
of the Extreme Points. During this phase, the fragility, stability and orientations of the boxes
are taken into account as well as the special shape of the bins and their weight capacity.
The second phase takes into account the multiple types of available bins. If necessary, the
best found loading pattern is finally enhanced with respect to weight distribution in a post
processing. After parametrisation, computational experiments have been performed on data
sets especially designed for this application. The heuristic requires really short computational
times to achieve promising results.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Modeling competition among airline itineraries
Lurkin, Virginie; Garrow, Laurie A.; Higgins, Matthew J.et al.
2018 • In Transportation Research. Part A, Policy and Practice, 113, p. 157-172
Discrete choice models are commonly used to forecast the probability an airline passenger chooses a specific itinerary. In a prior study, we estimated an itinerary choice model based on a multinomial logit specification that corrected for price endogeneity. In this paper, we extend the analysis to include inter-itinerary competition along three dimensions: nonstop versus connecting level of service, carrier, and time of day using nested logit (NL) and ordered generalized extreme value (OGEV) models. To the best of our knowledge, these are the first NL and OGEV itinerary choice models to correct for price endogeneity. Despite the many structural changes that have occurred in the airline industry, our results are strikingly similar to models estimated more than a decade ago. These results are important because it suggests that customer preferences, on average, have been stable over time and are similar across distribution channels. The stability in inter-itinerary competition patterns provides an important practical implication for airlines, namely it reduces the need to frequently update the parameter estimates for these models.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Accounting for Price Endogeneity in Airline Itinerary Choice Models: An Application to Continental U.S. Markets
2017 • In Transportation Research. Part A, Policy and Practice, 100, p. 228–246
Network planning models, which forecast the profitability of airline schedules, support many critical decisions, including equipment purchase decisions. Network planning models include an itinerary choice model which is used to allocate air total demand in a city pair to different itineraries. Multinomial logit (MNL) models are commonly used in practice and capture how individuals make trade-offs among different itinerary attributes; however, none that we are aware of account for price endogeneity. This study formulates an itinerary choice model that is consistent with those used by industry and corrects for price endogeneity using a control function that uses several types of instrumental variables. We estimate our models using database of more than 3 million tickets provided by the Airlines Reporting Corporation. Results based on Continental U.S. markets for May 2013 departures show that models that fail to account for price endogeneity overestimate customers’ value of time and result in biased price estimates and incorrect pricing recommendations. The size and comprehensiveness of our database allows us to estimate highly refined departure time of day preference curves that account for distance, direction of travel, the number of time zones traversed, departure day of week and itinerary type (outbound, inbound or one-way). These time of day preference curves can be used by airlines, researchers, and government organizations in the evaluation of different policies such as congestion pricing.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Early Detection of University Students with Potential Difficulties
Hoffait, Anne-Sophie; Schyns, Michael
2017 • In Decision Support Systems, 101, p. 1-11
Using data mining methods, this paper presents a new means of identifying freshmen's profiles likely to face major difficulties to complete their first academic year. Academic failure is a relevant issue at a time when post-secondary education is ever more critical to economic success. We aim at early detection of potential failure using student data available at registration, i.e. school records and environmental factors, with a view to timely and efficient remediation and/or study reorientation. We adapt three data mining methods, namely random forest, logistic regression and artificial neural network algorithms. We design algorithms to increase the accuracy of the prediction when some classes are of major interest. These algorithms are context independent and can be used in different fields. Real data pertaining to undergraduates at the University of Liège (Belgium), illustrates our methodology.
Peer Reviewed verified by ORBi
Article (Scientific journals)
Une audience virtuelle pour l’entrainement de la fluence de parole lors d’une prise de parole en public : Etude pilote
Contexte : Prendre la parole face à une audience est un défi pour beaucoup. Elle est considérée comme l’une des activités les plus craintes. L’anxiété liée à la prise de parole en public a un impact sur les performances de communication, notamment sur la fluence de parole. La littérature met en évidence les bénéfices d’un entrainement ciblant les compétences communicationnelles liées à cette activité. Néanmoins, son implémentation dans des situations proches du monde réel reste complexe. Par conséquent, la réalité virtuelle pourrait être un outil novateur et pertinent pour ce type d’entrainement.
Objectifs : Cette étude vise à valider l’utilisation d’une audience virtuelle pour l’entrainement de la prise de parole en public en évaluant sa capacité à susciter des réactions émotionnelles (en termes d’anxiété) et comportementales (en termes de disfluences).
Méthodologie : Huit participants ont réalisé une présentation orale dans trois conditions : 1) face à un public réel (Vivo_Public), 2) devant un public virtuel (Virtuo_Public) et 3) dans une salle de conférence virtuelle sans public (Virtuo_Vide). Les disfluences et le niveau d’anxiété des participants ont été analysés. Le vécu de l’immersion dans l’environnement virtuel a quant à lui été évalué au moyen d’un questionnaire portant sur le sentiment de présence et les cybermalaises.
Résultats : Les réactions comportementales, le sentiment de présence satisfaisant et l’absence de cybermalaises suggèrent que cet environnement virtuel est un outil prometteur pour l’entrainement à la prise de parole en public.
Conclusion : Cette étude est la première étape d’un projet à long terme. Elle a permis de mettre en évidence les éléments positifs de cette audience virtuelle ainsi que ceux nécessitant une amélioration. D’autres études sont toutefois nécessaires pour améliorer cet environnement et confirmer statistiquement sa validité écologique.
This volume contains abstracts of talks presented at the 12th Workshop on Models and Algorithms for Planning and Scheduling Problems (MAPSP 2015), held from June 8 to June 12, 2015, in La Roche-en-Ardenne, Belgium. MAPSP is a biennial workshop dedicated to all theoretical and practical aspects of scheduling, planning, and timetabling. The abstracts in this volume include 5 invited talks by Onno Boxma, Michel Goemans, Willem-Jan van Hoeve, Rolf Niedermeier, and Stephan Westphal, plus 88 contributed talks.
Book published as author, translator, etc. (Books)
Théorie stochastique de la décision d'investissement
Justens, Daniel; Schyns, Michael
1997 • De Boeck & Larcier, Bruxelles, Belgium
La complexité, l'imprévisibilité croissantes de l'environnement et de la structure interne des entreprises contraignent le gestionnaire à tendre vers une description probabiliste de l'univers. Le passage de la théorie classique, paramétrique, incluant la variabilité des données dans un contexte déterministe et discret, à la théorie stochastique continue, se fait progressivement. Chaque étape est illustrée au moyen d'exemples concrets. Un logiciel (sur CD-ROM) permet la résolution immédiate des problèmes propres à l'utilisateur.
Book published as author, translator, etc. (Books)
Visualizing Statistical Models and Concepts
Farebrother, Robert W.; Schyns, Michael
2002 • Marcel Dekker, Inc, New York, United States
This text/reference examines classic algorithms, geometric diagrams, and mechanical principles for enhanced visualization of statistical estimation procedurs and mathematical concepts in physics, engineering, and computer programming - stressing the role of geometric and mechanical representations in the design and generation of numericl models for applications in physical science. Visualizing Statistical Models and Concepts provides methods to determine the position of a multivariate location parameter ... offers techniques to fit a plane or curved surface to multivariate data ... considers geomechanical dynamics for linear and non linear programming ... discusses mathematical approaches to estimate and predict potential energy, force, and strain of system components...and analyzes data sets generated by transitive and nontransitive pairwise preference orderings.
Contribution to collective works (Parts of books)
Automatic Cargo Load Planning: Special shipments
Limbourg, Sabine; Schyns, Michael
2011 • In Cornelis, Eric (Ed.) Proceedings of the BIVEC-GIBET Transport Research Day 2011
The aircraft loading problem is a real-world combinatorial optimisation problem highly constrained. Indeed, loading the aircraft so the gross weight is less than the maximum allowable is not enough. This weight must be distributed to keep the centre of gravity (CG) within specified limits. Moreover, an aircraft has usually several cargo compartments with specific contours and structural limitations such as floor loading, combined load limits and cumulative load limitations. Finally, some shipments are particularly restrictive to transport, like dangerous goods, live animals and perishable goods. This paper is concerned with the incorporation of these latter constraints in a mixed integer linear program for the problem of loading a set of Unit Loading Devices (ULDs) and bulk into an aircraft. Experimental results for real data sets show that the model achieves better balanced solutions in only a few seconds compared to the solution obtained by load masters.
Contribution to collective works (Parts of books)
Alternative to the Mean-Variance Asset Allocation Analysis: A Scenario Methodology for Portfolio Selection
Schyns, Michael; Hübner, Georges; Crama, Yves
2009 • In Gregoriou, Greg N. (Ed.) Stock Market Volatility
This paper introduces a new methodology to optimize the allocation of financial assets. The
objective of the model is to maximize the expected return of the portfolio under constraints
limiting its Value-at-Risk. The assets could consist in stocks as well as options. We rely on a
flexible scenario tree approach to represent the future prices. In order to reduce the number of
leaves and maintain the model tractable, stocks prices are obtained through the Fama & French
empirical asset pricing model. Experiments on historical data are performed to illustrate the
method and show the performance of the approach. Different strategies are compared:
considering various market distributions, several factor models and a few portfolio hypothesis.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Le Pouvoir du Machine Learning, du NLP, et de la Réalité Virtuelle pour la Prise de Parole en Public
Etienne, Elodie; Schyns, Michael
2023
Cette recherche se concentre sur la création d'un environnement de réalité virtuelle visant à améliorer les compétences en prise de parole en public. L'objectif initial est la conception d'une audience virtuelle réaliste à l'aide de techniques de réalité virtuelle et de photoréalisme. Ensuite, l'attention s'est portée sur l'analyse de la voix et du discours, en particulier la détection des émotions dans la voix des orateurs. Une base de données émotionnelle de haute qualité a été en cours de développement, ainsi que des recherches sur des algorithmes d'apprentissage automatique et profond pour cette analyse. Enfin, des avatars animés par l'intelligence artificielle sont en cours de création pour offrir une expérience d'apprentissage immersive aux orateurs. Cette recherche vise à améliorer la formation à la prise de parole en public en explorant les synergies entre la réalité virtuelle, l'analyse émotionnelle vocale et l'intelligence artificielle.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Validation of a virtual audience in VR environments
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Integrating EmoVox Dataset and Virtual Reality for Public Speaking Training
Etienne, Elodie; Schyns, Michael
2023
This research focuses on enhancing public speaking training through the integration of an emotional speech dataset and Virtual Reality (VR) technology. The study recognizes the significance of emotions in effective communication and highlights the potential of AI techniques for emotion detection. To address the limitations of existing datasets, a high-quality emotional speech dataset is developed in French and English, incorporating professional actor recordings and Text-to-Speech software-generated samples. The dataset is then validated through subjective evaluation experiments. By leveraging VR technology, the research aims to create an immersive and interactive training environment where participants can practice speaking in front of virtual avatars that react authentically based on their emotional states. This research contributes to the advancement of public speaking training and establishes a valuable resource for emotional speech analysis in various applications, including VR, robots, and virtual assistants.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Développer des environnements virtuels pour l'enseignement. Teaching with VR
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Automatic Cargo Load Planning: Special shipments
Limbourg, Sabine; Schyns, Michael
2011
The aircraft loading problem is a real-world combinatorial optimisation problem highly constrained. Indeed, loading the aircraft so the gross weight is less than the maximum allowable is not enough. This weight must be distributed to keep the centre of gravity (CG) within specified limits. Moreover, an aircraft has usually several cargo compartments with specific contours and structural limitations such as floor loading, combined load limits and cumulative load limitations. Finally, some shipments are particularly restrictive to transport, like dangerous goods, live animals and perishable goods. This paper is concerned with the incorporation of these latter constraints in a mixed integer linear program for the problem of loading a set of Unit Loading Devices (ULDs) and bulk into an aircraft. Experimental results for real data sets show that the model achieves better balanced solutions in only a few seconds compared to the solution obtained by load masters.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Planification automatique de chargements d'avions cargo
Limbourg, Sabine; Schyns, Michael
2011
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Identification du profil du consommateur par datamining
Schyns, Michael
2011
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Systèmes d'information de gestion modernes
Schyns, Michael
2008
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
What is the impact of ticket-level fare information on classic itinerary choice models ?
Lurkin, Virginie; Garrow, Laurie; Schyns, Michael
2015
I have been invited by Prof. Dr. Catherine Cleophas as an external guest to the "Revenue Management Colloquium" in Aix-la-Chapelle from March 25 to March 26. The aim is to present my own doctoral project and discuss the presentations of other PhD students
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Three Dimensional Bin Packing Problem applied to air cargo
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2011
Deciding whether a set of three dimensional boxes can be packed into a container is a NP-hard problem. Mathematical models have been developed, however, only few studies take into account constraints encountered in real-world applications such as the stability or the fragility of the cargo. Moreover, despite the importance of this issue in air transport, the literature is almost silent on constraints related to the distribution of the weight inside a container. This paper is concerned with the formulation of the three dimensional palletization which includes the main constraints met in the air cargo industry.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
What the heck is Revenue Management
Lurkin, Virginie; Schyns, Michael; Garrow, Laurie
2015
The airline industry changed dramatically in 1978 when it became deregulated. Operations research analysts played a critical role after deregulation by developing algorithms and decision-support systems designed to help airlines to maximize their revenue. More than thirty-five years after deregulation, the airline industry is faced with new challenges. The increased use of the Internet as the major distribution channel and the increased market penetration of low cost carriers have led to an increasing interest in using discrete choice models to model air travel demand as the collection of individual's decisions.
Scientific conference in universities or research centers (Scientific conferences in universities or research centers)
Nowadays public speaking is one of the most important skills a person should develop. Such a skill is vital in many circumstances and in very different fields: the sales representative who presents a product to customers, the tourist guide visiting a city with a group, the manager who defends his project in front of stakeholders, the candidate during a job interview, the professor in front of students… Unfortunately, many firms complain about the too low level of this skill within their staff. The global theme of our work is to look for innovative solutions leading to an improvement of public speaking performances. The global project aims to help people to speak in public by training them in a realistic and interactive VR environment providing some feedbacks. Unity 3D engine was used to create a first basic version of the tool. 3D avatars have been designed and animated to represent some common audience postures, corresponding to different degrees of arousal and valence, and some classical situations as people typing on laptops or playing with smartphones. 3D photogrammetric versions of these avatars will soon be completed for testing increased realism. The objective of this presentation is to validate the virtual audience.
Poster (Scientific congresses and symposiums)
How can digital twins optimize the air cargo industry? A combination of operational research and machine learning techniques
Tonka, Jenny; Schyns, Michael
2024 • HEC Liège - Research day
Poster (Scientific congresses and symposiums)
A Deep Reinforcement Learning approach for the 3D Multiple-Bin Packing Problem
Evers, Justine; Schyns, Michael
2024 • HEC Research Day
Paper published on a website (Scientific congresses and symposiums)
Development and evaluation of Virtual Reality environments for public speaking training
Saufnay, Sarah; Etienne, Elodie; Schyns, Michael
2024 • AIRSI2024 The Metaverse Conference goes offline
Peer reviewed
Paper published on a website (Scientific congresses and symposiums)
EmoVox: Creation of a speech database for emotion analysis
Nous présentons un projet visant à créer une base de données émotionnelle (audio & vidéo, en français & en anglais) de haute qualité, équilibrée phonétiquement, contenant les six émotions de base d'Ekman et d'autres émotions communes lors de la prise de parole en public. Le but de cette base de données sera de détecter automatiquement les émotions chez un individu grâce à l'intelligence artificielle. Pour chaque langue, nous avons conçu deux études. La première consiste à enregistrer des phrases phonétiquement équilibrées avec les 10 émotions (et 2 niveaux d'intensité différents) produites par 12 acteurs. La deuxième implique la validation de chaque enregistrement par 25 juges différents. Nous pensons que notre projet sera notamment utile pour la formation à la prise de parole en public et pour la création d'environnements de formation en réalité virtuelle. En outre, notre base de données sera publique et ouverte à la communauté scientifique et pourra être utilisée à des fins de formation.
Editorial reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Air cargo ground service vehicle coordination: A responsive algorithm and some numerical evidence
Tonka, Jenny; Schyns, Michael
2024 • AGIFORS Airline Operations Conference
Unpublished conference/Abstract (Scientific congresses and symposiums)
Le pouvoir du Metavers dans l'aérien. Cas d'utilisation : prise de parole en public
Etienne, Elodie; Schyns, Michael
2023 • Séminaire Data Science
Unpublished conference/Abstract (Scientific congresses and symposiums)
Charitable Branding Using Virtual Reality Narratives
Charitable brands like zoos or aquariums seek to educate the public and obtain donations to support their conservation agendas. Importantly, this also aligns with the public interest for these brands to be more conscientious, as keeping some animals in captivity might harm their welfare. To address this concern, these brands have begun to embrace virtual reality (VR) to create life-like animal exhibits, replacing the need for physical captivity. VR allows these brands to supplement exhibition content with additional information, including animal welfare and wildlife conservation ideas. These VR exhibits transport individuals to digital, immersive environments to enhance learning.
Many charitable brands (e.g., Oxfam, UNICEF) have increased appeals through VR and these require substantial resource investments; on average, VR development costs often exceed $100,000. Immersive technology like VR has potential to promote charitable giving and conservation. While there has been no research to investigate how VR animal exhibits affect charitable giving, VR (vs. other media) has shown ability to increase donations. Thus, we turn to VR and charitable giving research to answer this question and explain why and how VR may impact donations.
Paper published in a book (Scientific congresses and symposiums)
A best fit heuristic for the three-dimensional Bin Packing Problem with practical constraints from an air transportation application
Paquay, Célia; Limbourg, Sabine; Schyns, Michael
2017 • In Proceedings of the BIVEC-GIBET Transport Research Days 2017
This work considers the three-dimensional Multiple Bin Size Bin Packing Problem which consists in packing a set of cuboid boxes into containers of various shapes, while minimising unused space. The aim of the present work is to find good initial solutions in short computational times. In this purpose, a fast best fit heuristic able to manage the different constraints to be met in transportation is developed. The heuristic is split into two distinct phases. The first phase deals with the packing of boxes into identical bins using an extension of the Extreme Points rule. During this phase, the fragility, stability and orientation of the boxes are taken into account, as well as the special shape of the bins and their weight capacity. The second phase considers the multiple types of available bins. If necessary, the best loading pattern identified is enhanced with respect to weight distribution in post processing. After parametrisation, computational experiments are performed on data sets specially designed for this application. The heuristic requires very short computational times to achieve promising results.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Early detection of university students with potential difficulties
Hoffait, Anne-Sophie; Schyns, Michael
2017 • IFORS 2017
Using data mining methods, this paper presents a new means of identifying freshmen's profiles likely to face major difficulties to complete their first academic year. We aim at early detection of potential failure using student data available at registration, i.e. school records and environmental factors, with a view to timely and efficient remediation and/or study reorientation. We adapt three data mining methods, namely random forest, logistic regression and artificial neural network algorithms. We design algorithms to increase the accuracy of the prediction when some classes are of major interest. These algorithms are context independent and can be used in different fields. They rely on a dynamic split of the observations into subclasses during the training process, so as to maximize an accuracy criterion. Four classes are so built: high risk of failure, risk of failure, expected success or high probability of success. Real data pertaining to undergraduates at the University of Liège (Belgium), illustrates our methodology. With our approach, we are now able to identify with a high rate of confidence (90%) a subset of 12.2% of students facing a very high risk of failure, almost the quadruple of those identified with a non-dynamic approach. By testing some confidence levels, our approach makes it possible to rank the students by levels of risk and a sensitivity analysis allows us to find out why some students are likely to encounter difficulties.
Unpublished conference/Abstract (Scientific congresses and symposiums)
The contribution of augmented reality in architectural education
Despite its importance, the specific issue of performance and reading of sketches in augmented reality does not seem to have been analyzed recently. Indeed, even if many articles have been published in connection with VR or RA in architecture, the questions studied are very varied and often related to specific applications. Recent literature, based on new technologies available since 2016, is also very limited. The research presented here was carried out within the pedagogical framework offered by the construction course taught to first-year students in the Faculty of Architecture of ULiège. The general objective of this course is to introduce students to a graphic approach framework that links construction technologies to the development of an architectural project. Students explore different construction techniques through the drawing of technical details. A first exploratory approach was carried out last year during the development of a prototype. It shows us the feasibility of the project and some pitfalls to avoid. The main objective of the project is to study the impact of augmented reality on the performance and skills acquisition of architecture students. It focuses on reading plans and sketches of technical construction drawings in order to identify the contributions of 3D spatialization.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Early detection of university students in potential difficulty
Hoffait, Anne-Sophie; Schyns, Michael
2015 • 16e conférence de la Roadef (Société Française de Recherche Opérationelle et Aide à la Décision)
Rate of success in the first year at University in Belgium is very low regarding other foreign universities. The University of Liege, as other Universities, has already taken different initiatives.
But by early identifying students who have a high probability to face difficulties if nothing is done, the Universities might develop adapted methods to attack the problem with more emphasis where it is more needed and when it is still possible.
Thus we want to develop a decision tool able to identify these students to help them. For that, we consider three standard datamining methods: logistic regression, artificial neural networks and decision trees and focus on early detection, i.e. before starting at the University.
Then, we suggest to adapt these three methods as well as the classification framework in order to increase the probability of correct identification of the students. In our approach, we do not restrict the classification to two extreme classes, e.g. failure or success, but we create subcategories for different levels of confidence: high risk of failure, risk of failure, expected success or high probability of success. The algorithms are modified accordingly and to give more weight to the class that really matters.
Note that this approach remains valid for any other classification problems for which the focus is on some extreme classes; e.g. fraud detection, credit default...
Finally, simulations are conducted to measure the performances of the three methods, with and without the suggested adaptation. We check if the factors of success/failure we can identify are similar to those reported in the literature.
We also make a ``what-if sensitivity analysis''. The goal is to measure in more depth the impact of some factors and the impact of some solutions, e.g., a complementary training or a reorientation.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Exercice de relaxation en réalité virtuelle: faisabilité et application dans une population d’enfants tout venants
2024 • 1er Congrès de la Research Unit for a life-Course perspective on Health and Education: Santé et éducation à tous les âges de la vie Regards transdisciplinaires au service de la qualité de vie
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Teaching with VR. Développer des environnements virtuels pour l'enseignement en sciences humaines
2017 • Semaine de l'enseignement. Atelier 2 - Les outils numériques « made in ULiège »
Présentation du projet Teaching with VR, qui associe des enseignants-chercheurs de 4 facultés pour développer des environnements en réalité virtuelle au service de l'enseignement en sciences humaines. Trois environnements sont montrés, qui peuvent être déclinés pour différentes disciplines (psychologie, architecture, marketing, etc.), en fonction de dispositifs ajoutés aux environnements.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Chargement d’un avion cargo : le cas des marchandises nécessitant des précautions particulières
Kleyntssens, Thomas; Limbourg, Sabine; Schyns, Michael
2011 • 3è Colloque International "Systèmes Industriels et Logistiques" 2011
Le problème du chargement de marchandises dans un avion cargo est soumis à des contraintes strictes de sécurité. C’est un problème d’optimisation combinatoire d’une importance cruciale pour les compagnies aériennes. En effet, un mauvais chargement diminue l’efficacité d’un avion et impose des tensions importantes sur sa structure qui peuvent entraîner
la destruction d’équipements de haute valeur, voire la perte de vies. De plus, certains colis spéciaux ont des contraintes très restrictives. C’est le cas notamment des produits dangereux, des animaux, des marchandises alimentaires et périssables. En plus des incompatibilités entre certains produits, il faut tenir compte des interactions possibles sur des équipements de l’avion.
Par exemple, des produits émettant des émissions magnétiques doivent être placés de manière à ne pas avoir des effets néfastes avec les instruments de navigation. Dans cet article, nous proposons d’incorporer ces contraintes liées aux colis nécessitant des précautions particulières dans un programme d’optimisation linéaire mixte du problème de chargement d’un ensemble de Unit Loading Devices et de vrac dans un avion. Les résultats obtenus à partir de données réelles montrent que notre méthode permet d’obtenir des solutions optimales en seulement quelques secondes.
Unpublished conference/Abstract (Scientific congresses and symposiums)
The Airline Container Loading Problem with Pickup and Delivery
Lurkin, Virginie; Schyns, Michael
2013 • 26th European Conference on Operational Research
We address the problem of allocating containers into predefined positions of a carrier, in this case aircraft, under several realistic structural and safety constraints. The originality of our approach is to allow multi-trips with pickup and delivery at some intermediate locations. The objective is to minimize the economic and environmental costs including the impact of the intermediate operations. We resort to an integer linear model. Numerical experiments have been performed using a standard B\&C library. Heuristics are developed to speed up the process.
Unpublished conference/Abstract (Scientific congresses and symposiums)
A branch and price approach for an airport vehicle routing problem
Schyns, Michael
2013 • 26th European Conference on Operational Research (Euro 2013)
This project has been initiated by a main European freight airport. The goal is to optimize the aircraft refueling process which relies on a given set of trucks. The underlying process can be defined as a vehicle routing problem with capacity and time windows. We resort to a branch and price approach for which we first analyze the impact of different parameters on the performance of the algorithm. Due to the stochastic nature of the demand and time windows in this context, we are also working on a priori (split delivery) and a posteriori (efficient re-optimization) measures.
Unpublished conference/Abstract (Scientific congresses and symposiums)
A 'price balance statistic' for optimizing pricing strategies: a better estimation of elasticities and cross-elasticities
Demand forecasting, price optimization and capacity controls form three major tools of revenue management. Over the past few decades, each discipline has generated a great deal of research but has typically been studied separately from the others. Yet, better understanding their relationship gives an airline the opportunity to increase its profitability. In prior work, Tim Jacobs and colleagues introduced a macro-level metric known as the ‘Price Balance Statistic (PBS)’ for evaluating the quality of a given pricing strategy and guiding a search algorithm to identify an optimal alignment between pricing structure, scheduled capacity and RM controls using marginal revenue principles. The aim of our work is to incorporate additional modeling improvements to the PBS. The current model formulation uses price elasticity as input parameters and assumes perfect independency between the different fare classes. However, in reality, a passenger demand fluctuates between classes based on differences in prices. We propose to use instrumented variable linear regression methods to obtain parameter estimates for price elasticities and cross-elasticities. This modification incorporates accurate price elasticities but also the impact of a change in one fare class on another through the cross-elasticities.
Unpublished conference/Abstract (Scientific congresses and symposiums)
A constructive heuristic for the three dimensional Bin Packing Problem with transportation constraints
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2014 • 20th Conference of the International Federation of Operational Research Societies (IFORS)
The aim of this work is to propose a Relax-And-Fix heuristic to build a good initial solution to the 3D BPP. First, a mathematical formulation has been developed taking into account several types of constraints such as the stability and fragility of the boxes to pack, their possibility to rotate, the weight distribution inside the bins and their special shapes. Since this model contains a lot of integer variables, we have decided to apply the Relax-and-Fix method. We have selected several sets of variables to be the branching variables and carried out some tests.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Accounting for price endogeneity in airline itinerary choice models
This study formulates an itinerary choice model that is consistent with those used by industry and corrects for price endogeneity using a control function that uses several types of instrumental variables. We estimate our models using database of more than 3 million tickets provided by the Airlines Reporting Corporation. Results based on Continental U.S. markets for May 2013 departures show that models that fail to account for price endogeneity overestimate customers’ value of time and result in biased price estimates and incorrect pricing recommendations. Extensions to advanced discrete choice models show the importance of accounting for inter-alternative substitution for products that share similar departure times.
Paper published in a book (Scientific congresses and symposiums)
Solving the m-TSP Problem with Stochastic or Time Dependent Demands
Louveaux, François; Schyns, Michael
2004 • In Opasanon, S.; Miller-Hooks, E. (Eds.) Proceedings of TRISTAN V (Triennial Symposium on Transportation Analysis)
There are many examples of problems in transportation where some elements are uncertain. In the distribution of goods as well as systems responding to calls for emergency, demands typically occur in a random fashion. Transportation systems have thus to be created in face of uncertainty about future levels of demands, making strategic decisions difficult to take. Similarly, traffic conditions vary randomly over time and travel routes are usually designed in face of uncertainty about traffic conditions, hence about effective travel times. Stochastic models, i.e. models that take uncertainty explicitly into account, have thus a central role to play in transportation.
Peer reviewed
Poster (Scientific congresses and symposiums)
Experimental investigation of decision-making processes in daily physically active behaviors using a virtual reality set-up
2018 • 32nd annual conference of the European Health Psychology Society
Background: Energy expenditure provided by physical activity (PA) can be significantly increased by daily behaviors (stair use, walking). However, factors from the environment, and motivational and volitional processes, tend to impact the decisions when an active solution (stairs) is available at the same time as an inactive solution (elevator). The aim of this study is to identify the decision-making processes implicated in daily PA when time and effort to reach an objective (e.g., a meeting) vary.
Methods: 150 healthy adults will be randomized to one of three experiments after filling out questionnaires measuring habits regarding PA, motivational, and volitional factors of PA adoption. Experiment 1 is a first-person 3D interactive movie where 3 actors are waiting at the point-of-decision, where peers’ behaviors and availability of the inactive solution vary. Experiment 2 is a virtual replication of a business school, where previous knowledge of the building and disposition of the stairs (hidden/visible) vary. Experiment 3 is a virtual modified version of the business school where a stairwell and an escalator provide access to the first floor, using implicit (steps on the floor) and explicit (motivational messages) as point-of-decision prompts.
Expected results: Results will be analyzed in line with the integrated behavior change model (Hagger & Chatzisarantis, 2014) and the naturalistic decision-making theory (Klein, 2015).
Current stage of work: Participants will be contacted for experimentations from February to June 2018.
Discussion: Real time decision-making processes will be linked to processes of change regarding PA, allowing for recommendations for future interventional designs.
Paper published in a book (Scientific congresses and symposiums)
Estimation of Airline Itinerary Choice Models Using Disaggregate Ticket Data
Lurkin, Virginie; Garrow, Laurie A.; Higgins, Matthew J.et al.
2015 • In 55th AGIFORS Annual Proceedings 2015
Airline itinerary choice models support many multi-million dollar decisions, i.e., they are used to evaluate potential route schedules. Classic models suffer from major limitations, most notably they use average fare information but to not correct for price endogeneity. We use a novel database of airline tickets to estimate itinerary choice models using detailed fare data and compare these to classic itinerary choice models that use aggregate fare information but correct for price endogeneity.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Improving e-commerce logistics with Augmented Reality and Machine Learning: The case of the 3D bin packing problem
Peters, Florian; Schyns, Michael
2020 • 6th International AR VR Conference
Unpublished conference/Abstract (Scientific congresses and symposiums)
Optimization of business processes thanks to machine learning and virtual reality. Use-case : SpeakInVR
2021 • Annual Meeting of the Belgian Association of Psychological Sciences
Background. Public speaking is one of the most feared activities (Furmark, 2002). Speaker’s anxiety influences their communication performance. While the literature highlights the benefits of public speaking training, is complex to implement in real -life (Goberman et al., 2011). Hence, virtual reality (VR) could be a viable alternative tool (Owens & Beidel, 2015).
The aim of this study was to validate a virtual audience for public speaking by assessing its qualities (i.e., feeling of presence and cybersickness) and its ability to elicit emotional (i.e., anxiety) and behavioral (i.e., dysfluencies) reactions.
Methodology. Forty participants without social anxiety (attested to by the PRCS, Heeren et al., 2013 ; LSAS-SR, Heeren et al., 2012 ; and BFNE-S, Rodebaugh et al., 2004) or fluency disorders (confirmed by the SSI-4, Riley, 2009) were recruited. They had to give an oral presentation under three counterbalanced conditions (in an empty virtual conference room and in front of virtual and real audiences). We aimed to analyze their speech and anxiety and the quality of VR. Due to the health crisis, this methodology was only pre-tested on 8 participants.
However, positive results, including a sufficient feeling of presence and the lack of cybersickness, suggest that this virtual audience can be a relevant tool.
Conclusions. The methodology will be discussed in light of these first positive results, on the one hand, and of the characteristics that can be improved (realism of the virtual audience and methodological limits), on the other hand, for the benefit of future studies.
References
Furmark, T. (2002). Social phobia: Overview of community surveys. Acta Psychiatrica Scandinavica, 105(2), 84–93. https://doi.org/10.1034/j.1600-0447.2002.1r103.x
Goberman, A. M., Hughes, S., & Haydock, T. (2011). Acoustic characteristics of public speaking: Anxiety and practice effects. Speech Communication, 53(6), 867–876. https://doi.org/10.1016/j.specom.2011.02.005
Heeren, A., Ceschi, G., Valentiner, D. P., Dethier, V., & Philippot, P. (2013). Assessing public speaking fear with the short form of the personal report of confidence as a speaker scale: Confirmatory factor analyses among a French-speaking community sample. Neuropsychiatric Disease and Treatment, 9, 609–618. https://doi.org/10.2147/NDT.S43097
Heeren, A., Maurage, P., Rossignol, M., Vanhaelen, M., Peschard, V., Eeckhout, C., & Philippot, P. (2012). Self-report version of the Liebowitz Social Anxiety Scale: Psychometric properties of the French version. Canadian Journal of Behavioural Science, 44(2), 99–107. https://doi.org/10.1037/a0026249
Owens, M. E., & Beidel, D. C. (2015). Can virtual reality effectively elicit distress associated with social anxiety disorder? Journal of Psychopathology and Behavioral Assessment, 37(2), 296–305. https://doi.org/10.1007/s10862-014-9454-x
Rodebaugh, T. L., Woods, C. M., Thissen, D. M., Heimberg, R. G., Chambless, D. L., & Rapee, R. M. (2004). More information from fewer questions: The factor structure and item properties of the original and brief Fear of Negative Evaluation Scale. Psychological Assessment, 16(2), 169–181. https://doi.org/10.1037/1040-3590.16.2.169
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Applicabilité et efficacité d'un exercice de respiration profonde en réalité virtuelle sur l’anxiété d’enfants hospitalisés dans un service de pédiatrie
2023 • 12ème congrès de l'Association Francophone de Psychologie de la Santé (AFPSA)
En pédiatrie, la réalité virtuelle (RV) a été principalement étudiée comme tâche distractive durant des soins médicaux en désengageant l’attention du stimulus anxiogène et douloureux1. Au-delà de son potentiel distracteur, certains suggèrent l’utilité de la RV dans l’apprentissage de techniques d’autorégulation, telle que la relaxation par respiration profonde2. Cependant, les études examinant un dispositif RV engageant le jeune patient dans une autorégulation active sont rares. Dans le cadre d’une hospitalisation, la peur et le sentiment d’impuissance sont fréquemment rapportés dans les services de pédiatrie3. Ces réponses émotionnelles sont connues pour avoir des impacts négatifs durant le séjour, et après celui-ci4. L’apprentissage de techniques de respiration par la RV leur permettrait de combiner l’aspect attrayant de l’outil et l’utilisation d’une technique de régulation active dans la gestion de leurs propres soins.
L’objectif de cette étude est d’examiner l’applicabilité et l’efficacité d'un exercice de respiration profonde en RV sur l’anxiété d’enfants âgés de 7 à 15 ans (N=44), hospitalisés dans un service de pédiatrie. Les enfants ont été immergés dans un environnement relaxant dans lesquels un exercice de respiration guidée est proposé (voix et image virtuelle). Nous faisons l’hypothèse d’un effet de cette immersion mesuré à l’aide d’une évaluation pré- et post sur des variables d’anxiété état. Une attention est également portée aux effets modérateurs du genre, de l’âge afin d’acquérir des connaissances sur les dispositifs RV les plus adaptés.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Impact d’une Intervention en Réalité Virtuelle sur la dissonance cognitive, chez des personnes en surcharge pondérale
Etienne, Anne-Marie; Farra Pauline; Schyns, Michael
2023 • Promouvoir des comportements de santé favorables pour la santé : enjeux théoriques et méthodologiques
L’obésité et la surcharge pondérale engendrent un sérieux problème de santé publique. L’activité
physique et l’obésité sont étroitement liées. C’est pourquoi conseiller de diminuer le temps passé à des activités sédentaires (privées et professionnelles) et promouvoir l’activité physique quotidienne serait des facteurs bénéfiques dans la prévention de la surcharge pondérale. L’hypothèse principale de cette étude est que l’intervention en réalité virtuelle sur la dissonance cognitive favorise l’engagement vers une solution active chez des participants en surcharge pondérale. Le contexte expérimental (Randomisation) implique que chaque sujet est confronté aux trois scénarios de dissonance cognitive (paresse, maîtrise et transpiration), et a une des conditions de la variable intraparticipant (accessibilité ; effort ; urgence et charge). Le bâtiment de HEC de l’ULiège a été modélisé en un environnement interactif 3D virtuel et a servi d'environnement virtuel pour cette étude. Avant et après l’expérimentation, les 50 participants ont complété une batterie de questionnaires ;
propension à l’immersion, cybermalaises, sentiment d’auto-efficacité, motivation pour l‘activité et pratique d’activités physiques. L’analyse statistique des résultats obtenus indique que l’intervention sur la dissonance cognitive en réalité virtuelle induite dans le deuxième et troisième scénario (paresse et maîtrise) encourage un changement d’attitude en faveur de l’utilisation des escaliers au travail chez les sujets en surcharge pondérale. En revanche, il s’avère que le premier scénario (qui encourage les participants à prendre l’ascenseur afin d’éviter la transpiration) ne permet pas de changement d’attitude chez les participants. En conclusion la dissonance cognitive semble mobiliser les participants à s’engager dans une activité physique.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Exploring interactions, immersion, and presence in a Virtual Reality experience for mooting
Speaking out in public is one of the most important skills a person should develop. It is especially true regarding business, law, and education. To efficiently teach students practical skills in their learning journey, we need to prepare and train them. In this paper, we focus on mooting, also known as a mock trial, which is often used in universities to achieve this goal. Like every training module, it can be logistically challenging to implement. In the past years, Virtual Reality (VR) has shown to be particularly useful when it comes to learning by doing. In VR, participants are immersed in a controlled virtual environment. This paper aims to validate the implementation of a comprehensive, automated, artificial intelligence-based VR application for mooting to improve participant performance. Semi-structured interviews will be conducted at UK, and Belgian universities and an experiment with 125 participants will be conducted within the same institutions to determine the characteristics of such an environment. We will also know if there are significant differences between Belgium and the United Kingdom that must be considered when designing it. Of course, the results will not be limited to mooting and can be easily adapted to other areas where speaking in public is a competency important to learn. For example, in business processes: the sales representative who presents a product to customers, the tourist guide visiting a city with a group, and the manager who defends his project in front of stakeholders... In future work, we will use our environment during the training of the students to confront them in various situations in response to their speech.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Jumeau numérique et Réalité Virtuelle : aide à la décision, monitoring et formation
The goal of this paper is the development of a new mixed integer linear pro-
gram designed for optimally loading a set of containers and pallets into a compartmentalised
cargo aircraft. It is based on real-world problems submitted by a professional partner. This
model takes into account strict technical and safety constraints. In addition to the standard
goal of optimally positioning the centre of gravity, we also propose a new approach based
on the moment of inertia. This double goal implies an increase in aircraft efficiency and
a decrease in fuel consumption. Cargo loading generally remains a manual, or at best a
computer assisted, and time consuming task. A fully automatic software was developed to
quickly compute optimal solutions. Experimental results show that our approach achieves
better solutions than manual planning, within only a few seconds.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Utilisation d’un MOOC et d’une animation 3D interactive en RA pour faciliter la compréhension des mécanismes du climat et de son réchauffement
De Lemos Esteves, Frédéric; Schyns, Michael; Jacquemin, Alexiset al.
2022 • 9e colloque international en éducation
Les MOOCs (Massive Open Online Course) sont des cours en ligne scénarisés et composés de capsules vidéo-pédagogiques, d’activités pédagogiques variées, de ressources complémentaires ou encore de forums de discussions (Downes, 2008). Ces cours sont proposés gratuitement et massivement sur la plateforme FUN MOOC (https://www.fun-mooc.fr/) mais ils sont aussi ancrés aux cursus des étudiants de l’Université de Liège (Belgique) où ils sont utilisés dans un contexte pédagogique hybride. Le MOOC « Tout comprendre sur le climat et son réchauffement » constitue une aide à la compréhension du fonctionnement du climat, du réchauffement climatique et de ses conséquences. Dans le cadre de ce cours en ligne, une animation 3D interactive en réalité augmentée permettant de visualiser plus clairement la circulation atmosphérique générale et les interconnexions existantes entre les différents constituants impliqués dans le fonctionnement du climat est une véritable innovation techno-pédagogique. Certains phénomènes climatiques plus précis, comme l’effet de Foehn ou les vents catabatiques, profitent même d’une animation 3D interactive spécifique. Cette animation a nécessité une réflexion de fond sur les connaissances et la matière enseignée et son utilisation est d’autant plus facile qu’elle est proposée pour travailler sur n’importe quel terminal que ce soit sur smartphone, tablette ou ordinateur. Les apprenants sont sondés en début et en fin de cours afin de pouvoir évaluer différents indicateurs et réguler le MOOC pour la session suivante.
Peer reviewed
Paper published in a book (Scientific congresses and symposiums)
Improvement of Public Speaking Skills using Virtual Reality: Development of a Training System
Saufnay, Sarah; Etienne, Elodie; Schyns, Michael
2024 • In 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)
The Public Speaking project is a Virtual Reality
(VR) training system dedicated to the improvement of public
speaking skills. It provides users with the opportunity to rehearse
their speech in a realistic virtual environment which displays
an interactive audience. The experience is customized based on
the chosen training scenario, which is determined by the room,
participant’s role, audience behaviors, and timer. A companion
website provides comprehensive feedback reports on speakers’
performance, based on their verbal and nonverbal behavior,
as well as replay functionalities. In addition to its educational
objective, this system is used as a tool to advance research into the
development of effective public speaking training environments.
Peer reviewed
Paper published in a book (Scientific congresses and symposiums)
Optimisation 3D du chargement de conteneurs pour le transport aérien
Paquay, Célia; Limbourg, Sabine; Schyns, Michael
2012 • In LigéRO (Ed.) Proceedings ROADEF 2013
De nos jours, décider comment remplir des conteneurs avec des colis est une activité courante
aussi bien dans le domaine du transport routier qu’aérien. Ce type de question est apparentée
aux problèmes de Bin-Packing(BPP) en recherche opérationnelle. En termes économiques,
ces opérations doivent mener à une solution qui satisfait de nombreuses contraintes physiques,
être réalisées rapidement et de sorte à maximiser certains critères. Typiquement, on tentera de
charger un maximum de colis dans un minimum de conteneurs pour réduire les coûts.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Three dimensional Bin Packing Problem applied to air transport
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2012 • 26th Annual Conference of the Belgian Operations Research Society
Packing boxes into containers is a daily process in many di erent elds and
especially in transport. However, the particular case of air transport brings some
new constraints such as the stability or the fragility of the cargo. The distribution
of the weight has also to be considered. Moreover, this special case also brings some
data such as the dimensions of the possible containers, called Unit Load Devices.
This paper is concerned with the formulation of the three dimensional palletization
which includes the main constraints met in the air cargo industry. It proposes a
integer linear program for this combinatorial optimization problem.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Automatic Aircraft Cargo Load Planning with Pick-up and Delivery
Lurkin, Virginie; Schyns, Michael
2013 • 27th Annual Conference of the Belgian Operational Research Society
This research aims to develop a new mixed integer linear program to solve the containers
assignment problem when pickup and deliveries are considered. Given a pool of ULDs and an
aircraft with multiple destinations, we want to obtain a loading plan determining at which
positions the ULDs must be assigned in order to minimize simultaneous the quantity of fuel
consumed and the number of re-handles. The loading plan should also ensure a number of
structural, safety and manoeuvrability constraints. The model has been tested on real instances
and provides encouraging results.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Air cargo ground operations optimization: A service vehicles coordination problem - Algorithmic approach
Tonka, Jenny; Schyns, Michael
2023 • AGIFORS 63rd Symposium
Unpublished conference/Abstract (Scientific congresses and symposiums)
Aircraft Cargo AutoLoad
Schyns, Michael; Limbourg, Sabine
2011 • UGR-GreatRoad (Interreg IV)
Paper published in a book (Scientific congresses and symposiums)
A relax-and- fix heuristic for the three-dimensional bin-packing model with transportation constraints
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2014 • In 11th ESICUP Meeting proceedings
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
A 'price balance statistic' for optimizing pricing strategies: a better estimation of elasticities and cross-elasticities
Demand forecasting, price optimization and capacity controls form three major tools of revenue management. Over the past few decades, each discipline has generated a great deal of research but has typically been studied separately from the others. Yet, better understanding their relationship gives an airline the opportunity to increase its profitability. In prior work, Tim Jacobs and colleagues introduced a macro-level metric known as the ‘Price Balance Statistic (PBS)’ for evaluating the quality of a given pricing strategy and guiding a search algorithm to identify an optimal alignment between pricing structure, scheduled capacity and RM controls using marginal revenue principles. The aim of our work is to incorporate additional modeling improvements to the PBS. The current model formulation uses price elasticity as input parameters and assumes perfect independency between the different fare classes. However, in reality, a passenger demand fluctuates between classes based on differences in prices. We propose to use instrumented variable linear regression methods to obtain parameter estimates for price elasticities and cross-elasticities. This modification incorporates accurate price elasticities but also the impact of a change in one fare class on another through the cross-elasticities.
Unpublished conference/Abstract (Scientific congresses and symposiums)
A relax-and- fix heuristic for the three-dimensional bin-packing model with transportation constraints
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2014 • 28th annual conference of the Belgian Operational Research Society
Paper published in a book (Scientific congresses and symposiums)
The Airline Container Loading Problem with Pickup and Delivery
Lurkin, Virginie; Schyns, Michael
2014 • In Airline Group of the Intl Federation of Operational Research Soc ( AGIFORS ) (Ed.) 54th AGIFORS Annual Proceedings 2014
The present paper looks into the problem of optimizing the loading of a set of containers and pallets into cargo aircraft serving multiple airports. Due to the pickup and delivery operations occurring at intermediate airports, this problem is simultaneously a weight and balance problem and a sequencing problem. Our objective is to minimize fuel and handling operations costs. This problem is shown to be NP-hard. We resort to a mixed integer linear program. On the basis of a professional partner's real-world data, TNT Airways, we perform numerical experiments using a standard B&C library. This approach yields better solutions than traditional manual planning, which results in substantial cost savings.
Peer reviewed
Paper published in a book (Scientific congresses and symposiums)
Robust Portfolio Selection
Schyns, Michael
2008 • In JSM Proceedings, Statistical Computing Section
In many financial problems, small variations in some inputs may result in big changes in the outputs. In this talk, we consider the problem of portfolio selection as suggested by Markowitz. This model relies on a covariance matrix usually estimated using historical returns of the assets under consideration. Gross error in these returns or atypical events occurring in the past could lead to different portfolios with quite different expected returns. Defining methods that do not depend too much on these atypical data is the aim of robust statistics. We will show that some techniques developed in that field are worth applying in our context. More precisely, the covariance matrix of historical data will be estimated with the Minimum Covariance Determinant estimator, computed with a 'smooth' algorithm. This robust Markowitz methodology will be illustrated on real financial data.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
The Use of Virtual Reality in Public Speaking Training: Design of a dedicated tool
Saufnay, Sarah; Etienne, Elodie; Schyns, Michael
2025 • Laval Virtual Doctoral Consortium
Given their significance in many management contexts, public speaking skills are increasingly valued by organizations. Not always innate, these skills can fortunately be acquired through practice. However, due to their intrinsic social aspect, opportunities to refine these skills in real-life settings are scarce. Faced with such limitations, Virtual Reality emerges as a suitable and innovative solution. By simulating public speaking scenarios, it allows users to practice in front of an audience, albeit a virtual one. The added value of Virtual Reality public speaking tools is therefore clear, but the optimal training approach and environment design are not of a basic nature. In order to identify best practices, a dedicated Virtual Reality training system has been developed and will be presented in light of the scientific literature. The objective of the present research project is to leverage the system to investigate unanswered questions pertaining to the perception of virtual audiences, the evaluation of public speaking performance, and the effectiveness of such tools.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Deep Reinforcement Learning for Combinatorial Problems: A new approach for the 3DBPP container loading problem in logistics
Evers, Justine; Schyns, Michael
2023 • 19th ESICUP Meeting
Unpublished conference/Abstract (Scientific congresses and symposiums)
Several constructive heuristics for the three dimensional Multiple Bin Size Bin Packing Problem with air transportation constraints
Paquay, Célia; Limbourg, Sabine; Oliveira, José Fernandoet al.
2015 • 12th ESICUP Meeting
Unpublished conference/Abstract (Scientific congresses and symposiums)
Early detection of university students in potential difficulty : a case study
Hoffait, Anne-Sophie; Schyns, Michael
2014 • 22nd meeting of the Belgian Statistical Society
Rate of success in the first year at University in Belgium is very low regarding other foreign universities. The University of Liege, as other Universities, has already taken different initiatives.
But by early identifying students who have a high probability to face difficulties if nothing is done, the Universities might develop adapted methods to attack the problem with more emphasis where it is more needed and when it is still possible.
Thus we want to develop a decision tool able to identify these students to help them. For that, we consider three standard datamining methods: logistic regression, artificial neural networks and decision trees and focus on early detection, i.e. before starting at the University.
Then, we suggest to adapt these three methods as well as the classification framework in order to increase the probability of correct identification of the students. In our approach, we do not restrict the classification to two extreme classes, e.g. failure or success, but we create subcategories for different levels of confidence: high risk of failure, risk of failure, expected success or high probability of success. The algorithms are modified accordingly and to give more weight to the class that really matters.
Note that this approach remains valid for any other classification problems for which the focus is on some extreme classes; e.g. fraud detection, credit default...
Finally, simulations are conducted to measure the performances of the three methods, with and without the suggested adaptation. We check if the factors of success/failure we can identify are similar to those reported in the literature.
We also make a ``what-if sensitivity analysis''. The goal is to measure in more depth the impact of some factors and the impact of some solutions, e.g., a complementary training or a reorientation.
Unpublished conference/Abstract (Scientific congresses and symposiums)
An exact formulation for the three-dimensional bin-packing with transportation constraints
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2013 • 26th European Conference on Operational Research
Poster (Scientific congresses and symposiums)
Prise de parole en public : Analyse du sentiment de présence et d’immersion face à une audience virtuelle et mise en relation avec l’anxiété
2024 • 1er Congrès Interdisciplinaire de RUCHE - Santé et éducation à tous les âges de la vie
Introduction: La prise de parole en public est une activité de communication essentielle. Pourtant, celle-ci génère fréquemment de l’anxiété (Bodie, 2010). Si des entrainements à la prise de parole existent, leur mise en place demeure toutefois complexe car ils nécessitent le recrutement d’un public (Menjot et al., 2023). La réalité virtuelle s’avère être un outil intéressant permettant de contourner ces difficultés pratiques. Objectifs : Évaluer la capacité d’une audience virtuelle à immerger les participants et analyser les paramètres influençant ce sentiment (anxiété). Méthodologie : 60 étudiants ont réalisé une présentation orale face à une audience virtuelle. Le sentiment de présence et d’immersion des participants a ensuite été mesuré (à l’aide de l’ITC-SOPI) et mis en relation avec la propension à l’immersion des participants mais également avec leur tendance à ressentir de l’anxiété. Résultats : L'environnement virtuel semble générer un sentiment de présence suffisant et une absence de cybermalaises suite à l'immersion. Aucune corrélation n'a été mise en évidence entre la propension à l’immersion des participants et le sentiment de présence et d’immersion ressenti dans cet environnement virtuel spécifique. En outre, plus l’anxiété trait des participants était importante et plus le sentiment de présence dans l'environnement virtuel était important (Felnhofer et al., 2019 ; Ling et al., 2014). Conclusions : L'audience virtuelle semble validée en termes de sentiment de présence et d'absence de cybermalaises. Cette étude constitue une première étape dans la validation de cet environnement virtuel pour l'entrainement à la prise de parole en public.
Unpublished conference/Abstract (Scientific congresses and symposiums)
The Airline Container Loading Problem with Pickup and Delivery
Lurkin, Virginie; Schyns, Michael
2014 • 2014 INFORMS Annual Meeting
We address the problem of allocating containers into predefined positions of a carrier, in this case aircraft, under several realistic structural and safety constraints. The originality of our approach is to allow multi-trips with pickup and delivery at some intermediate locations. The objective is to minimize the economic and environmental costs including the impact of the intermediate operations. We resort to an integer linear model. Numerical experiments have been performed using a standard B\&C library. Heuristics are developed to speed up the process.
Paper published in a book (Scientific congresses and symposiums)
The Airline Container Loading Problem with Pickup & Delivery and Multi Doors
Schyns, Michael; Lurkin, Virginie
2013 • In 53rd AGIFORS Annual Proceedings 2013: Annual Symposium and Study Group Meeting
We address the problem of allocating containers into predefined positions of a carrier, in
this case aircraft, under several realistic structural and safety constraints, including the management of several doors. The originality of
our approach is to allow multi-trips with pickup and delivery at some intermediate locations.
The objective is to minimize the economic and environmental costs including the impact of
the intermediate operations. We resort to an integer linear model. Numerical experiments have
been performed using a standard B&C library. The cost impact is measured. The Airline Group of the International Federation of Operational Research Societies, composed of professionals and academics, has awarded us the price of the "Best technical presentation" for this work.
Peer reviewed
Paper published in a book (Scientific congresses and symposiums)
Automatic Cargo Load Planning: Special shipments
Kleyntssens, Thomas; Limbourg, Sabine; Schyns, Michael
2012 • In ILS 2012 Proceedings
The aircraft loading problem is a real-world combinatorial optimisation problem highly constrained. Indeed, loading the aircraft so the gross weight is less than the maximum allowable is not enough. This weight must be distributed to keep the centre of gravity within specified limits. Moreover, an aircraft has usually several cargo compartments with specific contours and structural limitations such as floor loading, combined load limits and cumulative load limitations. Finally, some shipments are particularly restrictive to transport, like dangerous goods, live animals and perishable goods. This paper is concerned with the incorporation of these latter constraints in a mixed integer linear program for the problem of loading a set of Unit Loading Devices and bulk into an aircraft. Experimental results show that our method achieves optimal solutions within only few seconds.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Automatic Aircraft Cargo Load Planning with Pick-up and Delivery
Lurkin, Virginie; Schyns, Michael
2013 • 14ème conférence ROADEF de la Société Française de Recherche Opérationnelle et Aide à la Décision
This research aims to develop a new mixed integer linear program to solve the containers
assignment problem when pickup and deliveries are considered. Given a pool of ULDs and an
aircraft with multiple destinations, we want to obtain a loading plan determining at which
positions the ULDs must be assigned in order to minimize simultaneous the quantity of fuel
consumed and the number of re-handles. The loading plan should also ensure a number of
structural, safety and manoeuvrability constraints. The model has been tested on real instances
and provides encouraging results.
Unpublished conference/Abstract (Scientific congresses and symposiums)
The main goal of this paper is to validate a virtual reality environment for public speaking training. Following Slater’s terminology (2003), there are two important concepts in VR: “immersion which stands for what the technology delivers from an objective point of view” and presence which is “the human reaction to immersion”, i.e., the participant’s subjective sense of being in the virtual place.
The reactions of the audience can have a significant impact on the speaker’s emotions and performance. At a first level, our hypothesis is that interactivity has a positive impact on the presence feeling. At a higher level, as already shown by Chollet et al. (2015), interactivity in VR is also a major ingredient in the training process. It is therefore essential to know if the users perceive the interactions in the virtual environment as representative of the reality and how each one is interpreted. There are two main dimensions in the context of emotion and affect: arousal and valence. As defined by Chollet and Scherer (2017), “arousal can be understood as an audience member’s level of alertness, and valence corresponds to how positively or negatively the person feels toward the speaker or the presentation”. In their paper, they tried to understand how users perceive virtual audience based on the nonverbal behavior of audience members. Our first question is to investigate which attitudes the characters must display and how people perceive the individual members of the audience in terms of their states of arousal and valence.
A second related question is linked to the level of reality used to represent the public. The characters in virtual environments, i.e. avatars, are most often synthetic images. In some cases, photorealistic representations are used but the level of animation is then generally extremely limited. In this context, our second research question investigates whether the use of fully rigged 3D photogrammetric models, i.e. with a skeleton we can animate, can significantly improve the user’s presence.
Peer reviewed
Paper published on a website (Scientific congresses and symposiums)
EVE : Emotional Voice Expressions, an acted audiovisual corpus
It is imperative that law students in higher education are provided with a holistic education
curriculum that covers all three areas of being a lawyer: 1) legal knowledge, 2) practical skills, and 3)
ethical awareness (Sullivan et al., 2007). Simulation is an effective way of teaching practical skills that
cannot be taught in a traditional classroom setting (Newbery-Jones, 2015). Virtual reality (VR) is a
technology that is increasingly being used in education to facilitate simulated learning exercises
(Kavanagh et al., 2017). In this study, a novel virtual reality (VR) legal simulation application is
developed and will be tested amongst students to identify its potential impact in this context. It aims
to propose a theoretical framework to guide the implementation of virtual reality technology in legal
education contexts.
Peer reviewed
Paper published in a book (Scientific congresses and symposiums)
A Systematic Review on the Socio-affective Perception of IVAs' Multi-modal behaviour
2024 • In IVA '24: Proceedings of the 24th ACM International Conference on Intelligent Virtual Agents
The multimodal behaviour of IVAs may convey different socio-affective dimensions, such as emotions, personality, or social capabilities. Several research works show that factors may impact the perception of the IVA's behaviour. This paper proposes a systematic review, based on the PRISMA method, to investigate how the multimodal behaviour of IVAs is perceived with respect to socio-affective dimensions. To compare the results of different research works, a socio-emotional framework is proposed, considering the dimensions commonly employed in the studies. The conducted analysis of a wide array of studies ensures a comprehensive and transparent review, providing guidelines on the design of socio-affective IVAs.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
A Deep Reinforcement Learning Approach for the 3D Multiple-Bin Packing Problem
Evers, Justine; Schyns, Michael
2024 • 20th ESICUP Meeting
Poster (Scientific congresses and symposiums)
Validation of a virtual reality environment with a relaxing breathing exercise in a population of children hospitalized in a pediatric unit
2024 • Pan European VOice Conference 15 (PEVOC 15)
Introduction : Public speaking (PS) is a widespread vocal activity required in many personal and professional situations. Its quality can impact one’s career success, reputation, and credibility (1). However, little is known about which voice characteristics are representative of PS (2). Objective : This presentation aims to determine the acoustic characteristics of the PS voice by analyzing frequency parameters as well as long-term spectral features. Methods : We conducted acoustic analyses on the speech productions of 65 university students in two conditions: (1) reading aloud a phonetically balanced text (control), and (2) giving a one-minute oral presentation in front of an 8-people audience (PS). Preliminary results: Paired t-tests indicated a significantly enhanced vocal quality in the PS condition compared to the control condition, as evidenced by increased CPPS, spectral slope and center of gravity values. We found a significant effect of condition on intonation as evidenced by an increased f0 SD in the PS task. No significant difference was found for median f0. Conclusion: These findings suggest the existence of acoustic characteristics specific to PS that could be associated with Lombard speech (3) and clear speech (4). The two speaking styles are used in challenging communication situations to optimize intelligibility.
1. Ferreira Marinho, A. C., Mesquita de Medeiros, A., Côrtes Gama, A. C., & Caldas Teixeira, L.
(2017). Fear of public speaking: Perception of college students and correlates. Journal of Voice, 31(1), 7-11.
2. Niebuhr, O., Skarnitzl, R., & Tylečková, L. (2018). The acoustic fingerprint of a charismatic voice : Initial evidence from correlations between long-term spectral features and listener ratings. 9th International Conference on Speech Prosody,359-363.
3. Garnier, M., & Henrich, N. (2014). Speaking in noise: How does the Lombard effect improve
acoustic contrasts between speech and ambient noise?. Computer Speech & Language, 28(2), 580-597.
4. Krause, J. C., & Braida, L. D. (2004). Acoustic properties of naturally produced clear speech at normal speaking rates. The Journal of the Acoustical Society of America, 115(1), 362-378.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Le Deep Reinforcement Learning à la rescousse des problèmes combinatoires: Une nouvelle approche pour le 3DBPP en logistique
Evers, Justine; Schyns, Michael
2023 • Séminaire Data Science
Paper published in a book (Scientific congresses and symposiums)
The case sensitivity function approach to diagnostic and robust computation: a relaxation strategy
Cho, Justin; Jung, Timothy; tom Dieck, Mandyet al.
2023 • MMU Business and Law Doctoral Symposium
Editorial reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Deep Reinforcement Learning for Combinatorial Problems: A new approach for the 3DBPP container loading problem in logistics
Evers, Justine; Schyns, Michael
2023 • ORBEL 37
Unpublished conference/Abstract (Scientific congresses and symposiums)
ARanatomy, une application de réalité augmentée dédiée à l’enseignement de l’anatomie et de l’histologie : une innovation pédagogique à haut potentiel dans différentes scénarisation
L'anatomie et l’histologie sont des pierres angulaires de l’enseignement préclinique au sein des institutions universitaires formant des professionnels de la santé. Cependant, les étudiants peuvent ne pas percevoir pleinement l’importance de ces disciplines en tant que composantes essentielles de leur formation et ne pas développer un niveau de compétence suffisant. Les séances de laboratoire sont souvent limitées et l’intégration des notions reste compliquée pour la majorité des étudiants. Pour faciliter leur apprentissage et gagner en efficacité, des environnements 3D utilisant la réalité augmentée apparaissent dans les stratégies éducatives émergentes. Dès lors, nous avons développé, ARanatomy, une application de réalité augmentée répondant aux exigences suivantes : intégré des notions d’anatomie et d’histologie, basé sur la réalité anatomique, capable d’évoluer et utilisable dans un enseignement hybride. ARanatomy associe des notions anatomiques du rétropéritoine et histologiques du système néphro-urinaire, de même que le squelette reconstitué en photogrammétrie et les données d’imagerie médicale correspondantes. Le potentiel de l’intégration de cette application a été évalué dans différentes scénarisations pédagogiques.
Peer reviewed
Poster (Scientific congresses and symposiums)
ARanatomy, an Augmented Reality Application Dedicated to Anatomy and Histology Teaching. an Educational Innovation with High Potential in Different Educational Strategies
Anatomy and histology are cornerstones of preclinical education for health professionals. However, students may not fully perceive the importance of these disciplines and therefore may not develop a sufficient level of competence. To facilitate learning and increase efficiency, 3D environments using augmented reality (AR) recently emerge as educational strategies. They seem to improve knowledge and create an environment conducive to learning. Therefore, we have developed an AR application that integrate anatomy and histology, based on anatomical reality, able to scalable and usable in hybrid teaching.
Reference patient DICOM data were transformed into .obj formats using the 3D slicer software and imported into the blender, while zbrush, autodesk maya and substance software were used to optimize the skeleton, urinary cavities, and vascular structures. Bone images obtained by photogrammetry were superimposed on this reconstruction. To this basic structure, relevant anatomical and histological structures with a high degree of scientific fidelity have been integrated.
A feasibility study was carried out to assess the technical aspects, the ways to introduce the app to the students and the potential for its implementation in educational strategies.
First, a technical test was performed with 500 first-year medical students. From 202 respondents, 31% of them encountered technical difficulties mostly related to functionalities. We are nevertheless optimistic about the tool potential because almost half of the students (47% of respondents) have found it very useful to better visualize the 3D aspects and the relationships between organs.
A second feasibility study investigated the tool handling. 41 second-year medical students were randomly assigned to three protocols: one totally autonomous, one autonomous after watching an explanatory video and another supervised by a teacher. The handling was evaluated by questions requiring the use of all the app functionalities. The most successful group is the one that used the explanatory video, followed by the accompanied group and then the working independently group. The survey showed that the students experienced technical difficulties to display the model (20%) and the observation levels (11%), to perform rotations (40%) and zooms (17%). The tool potential was underlined as 91% find the app useful. Aspects relating to anatomy and histology integration (34%), 3D visualization (28%) and topography (17%) are mentioned in the free answers. Several anatomical visualizations in the same tool, displaying areas of interest and superimposing histological images are estimated useful by all of the involved students (100%). Finally, 97% of students have a general positive opinion qualifying the app as promising, useful, fun, integrative, congruent with morphology courses. This view is tempered by difficulties related to technical stability.
In conclusion, the difficulties encountered are explained by the fact that the tool is still in the optimization phase. The app potential was undeniably highlighted. The integration of anatomy and histology in the same learning tool is a real opportunity. Indeed, while most students approach anatomy as a compartmentalized memorization task, those who combine it with understanding, integration with other disciplines and visualization at different levels seems to have a better acquisition of knowledge. This aspect will be investigated in the future.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Chargement de marchandises dans un avion cargo: le cas des marchandises nécessitant des précautions particulières
Schyns, Michael; Limbourg, Sabine; Kleyntssens, Thomas
2012 • 13ème Congrès de la Société française de Recherche Opérationnelle et d'Aide à la Décision (ROADEF)
D'une part, les entreprises de transport aérien ont acheminé en 2010 plus d’un tiers de la valeur des exportations mondiales. D'autre part, le chargement des avions est une opération complexe soumise à de nombreuses contraintes et peu d'outils sont disponibles pour aider les loadmasters à trouver la meilleure disposition des conteneurs dans les avions. Limbourg, Schyns et Laporte (2011) ont proposé un modèle à variables entières pour traiter les problèmes élémentaires. Notre travail est une extension de ces travaux. Nous considérons des chargements spéciaux qui impliquent des précautions particulières (produits dangereux, animaux, produits réfrigérés, aliments périssables, ...) ainsi que le transport de marchandises de plus grande taille. L’ajout de ces deux types de contraintes se justifie par la grande fréquence de ces situations dans des problèmes réels rencontrés par nos partenaires industriels. Le problème résultant est très complexe et nous proposons un outil pour le résoudre.
Unpublished conference/Abstract (Scientific congresses and symposiums)
An Integer Programming model for air transport of hazardous and special shipments
Kleyntssens, Thomas; Limbourg, Sabine; Schyns, Michael
2012 • 26th annual conference of the Belgian Operations Research Society
The aircraft loading problem is a real-world combinatorial optimisation problem
highly constrained. This weight must be distributed to keep the centre of gravity
within speci ed limits. Moreover, an aircraft has usually several cargo compart-
ments with speci c contours and structural limitations such as
oor loading, com-
bined load limits and cumulative load limitations. Finally, some shipments are par-
ticularly restrictive to transport, like dangerous goods, live animals and perishable
goods. This paper is concerned with the incorporation of these latter constraints
in a mixed integer linear program for the problem of loading a set of Unit Load-
ing Devices and bulk into an aircraft. Experimental results show that our method
achieves optimal solutions within only few seconds.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Optimisation des opérations au sol : Un problème de coordination des véhicules de service
Tonka, Jenny; Schyns, Michael
2023 • Séminaire Data Science
Paper published in a book (Scientific congresses and symposiums)
Three dimensional Bin Packing Problem applied to air cargo
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2012 • In ILS 2012 Proceedings
Deciding whether a set of three dimensional boxes can be packed into a container is a NP-hard problem.
Mathematical models have been developed, however, only few studies take into account constraints encountered in real-world applications such as the stability or the fragility of the cargo. Moreover, despite the importance of this issue in air transport, the literature is almost silent on constraints related to the distribution of the weight inside a container. This paper is concerned with the formulation of the three dimensional palletization which includes the main constraints met in the air cargo industry.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Early detection of university students in potential difficulty
Hoffait, Anne-Sophie; Schyns, Michael
2014 • 28th annual conference of the Belgian Operational Research Society
Rate of success in the first year at University in Belgium is very low regarding other foreign universities. The University of Liege, as other Universities, has already taken different initiatives.
But by early identifying students who have a high probability to face difficulties if nothing is done, the Universities might develop adapted methods to attack the problem with more emphasis where it is more needed and when it is still possible.
Thus we want to develop a decision tool able to identify these students to help them. For that, we consider three standard datamining methods: logistic regression, artificial neural networks and decision trees and focus on early detection, i.e. before starting at the University.
Then, we suggest to adapt these three methods as well as the classification framework in order to increase the probability of correct identification of the students. In our approach, we do not restrict the classification to two extreme classes, e.g. failure or success, but we create subcategories for different levels of confidence: high risk of failure, risk of failure, expected success or high probability of success. The algorithms are modified accordingly and to give more weight to the class that really matters.
Note that this approach remains valid for any other classification problems for which the focus is on some extreme classes; e.g. fraud detection, credit default...
We check if the factors of success/failure we can identify are similar to those reported in the literature.
We also make a ``what-if sensitivity analysis''. The goal is to measure in more depth the impact of some factors and the impact of some solutions, e.g., a complementary training or a reorientation.
Unpublished conference/Abstract (Scientific congresses and symposiums)
A best fit decreasing algorithm for the three dimensional bin packing problem
Paquay, Célia; Schyns, Michael; Limbourg, Sabine
2015 • XI International Workshop on Cutting and Packing problems and Related Topics
Unpublished conference/Abstract (Scientific congresses and symposiums)
Early detection of university students in potential difficulty
Hoffait, Anne-Sophie; Schyns, Michael
2016 • 28ème conférence européenne sur la recherche opérationnelle (EURO 2016)
Unpublished conference/Abstract (Scientific congresses and symposiums)
L’utilisation des nouvelles technologies dans l’étude des comportements de santé.
2021 • Annual Meeting of the Belgian Association of Psychological Sciences
Introduction/Context:
Nowadays public speaking is a vital skill in many circumstances and in very different fields: the sales representative who presents a product to customers, the manager who defends his project in front of stakeholders, the candidate during a job interview, the professor in front of students, etc. However, social anxiety may impede oral presentation performances . Repeated training in front of an audience can help to better control the speaker’s emotions and skills, and improve speaking performances (Wallach et al., 2009). Given that training in front of a real audience can be logistically difficult to organize, virtual reality (VR) can be the solution. Nevertheless, the emotional impact of the virtual audience on the speaker will depend on the emotional valence and arousal they attribute to the audience’s avatars.
Aim:
The goal of the present study is to assess the emotional valence and arousal attributed to the avatars of a new virtual audience, depending on the avatars’ attitude.
Method and material:
Based on the methods from Chollet & Scherer (2017), 125 adults participated in this study. They rated the emotional valence and arousal of 8 avatars depending on their body posture, their face’s expressions, or their head movements.
Results and conclusions:
Results show that head movements were more readily linked to the emotional valence attributed to the avatars by the participants than were body postures and facial expressions. Furthermore, arousal seems to be directly linked with head movements and facial expressions. Full results from each parameter will be discussed.
Peer reviewed
Unpublished conference/Abstract (Scientific congresses and symposiums)
Predictive Maintenance of Technical Faults in Aircraft
Peters, Florian; Aerts, Stéphanie; Schyns, Michael
2020 • 34th Annual Conference of the Belgian Operational Research Society
A key issue for handlers in the air cargo industry is arrival delays due to aircraft maintenance. This work focuses on a particular delay caused by technical faults called technical delays. Using real data from a cargo handler company, different classification models that can predict technical delay occurrence are compared. A new decision tree extension is also proposed based on a study by Hoffait & Schyns (2017). The final results present a good starting point for future research.
Unpublished conference/Abstract (Scientific congresses and symposiums)
Validation of a virtual framework for public speaking training
Speaking out in public or during meetings is a challenge for many of us. It is nonetheless a competency required in
many activities: the sales representative who presents a product to customers, the tourist guide visiting a city with a group,
the manager who defends his project in front of stakeholders, the candidate during a job interview, the professor in front of
students… Unfortunately, many firms complain about the too low level of this skill within their staff. To fight public
speaking anxiety, which may impede oral presentation performances, we need to prepare and train the speakers. It can be
done efficiently by immersing the speaker in totally controlled Virtual Reality (VR) environments. This paper first aims to
validate the emotional valence and level of arousal of the attitudes of a virtual public through an experiment with 125
participants. Based on these results, a library of public attitudes corresponding to different levels of arousal and valence has
been created. Our experiment also investigates the benefits of using low-end and high-end VR headsets, as well as the use of
photo-realistic public compared to sketched avatars. In future work, we will use our library during the training of the
speakers to confront them in various situations in response to their speech.
Peer reviewed
Poster (Scientific congresses and symposiums)
A virtual audience for public speaking: A pilot study
2020 • Meeting of the Groupe de Contact de Psycholinguistique et Neurolinguistique (GCPN)
Background. Public speaking is one of the most feared activities, with approximately two-thirds of undergraduates afraid to speak in public (Ferreira Marinho et al., 2017). This form of anxiety has consequences on communication performance (King & Finn, 2017), particularly on speech fluency (Goberman et al., 2011), and quality of speech can influence a speaker’s career success (Wörtwein et al., 2015). While the literature highlights the benefits of public speaking training on communication performance (Goberman et al., 2011), its implementation is complex. Therefore, virtual reality (VR) seems to be an innovative and relevant tool for clinicians.
Aims. This study aims to validate the use of a virtual audience for public speaking by assessing its capacity to elicit emotional (i.e. anxiety) and behavioral (i.e. disfluencies) responses confirming its ecological validity.
Methodology. Eight participants made an oral presentation in front of a virtual audience. Their speech disfluencies and anxiety were analyzed. They also completed questionnaires assessing the quality of VR based on the feeling of presence and side effects (i.e. cybersickness).
Results. The emotional (anxiety) and behavioral responses (speech disfluencies), the sufficient feeling of presence, and the absence of cybersickness suggest that this virtual audience can be a relevant tool for public speaking training and rehabilitation.
Conclusions. This pilot study is the first step in a long-term project. It highlights the positive points of a virtual audience as well as those requiring improvement. Further studies are needed to enhance this virtual environment and statistically confirm its ecological validity.
References:
- Ferreira Marinho, A. C., Mesquita de Medeiros, A., Côrtes Gama, A. C., & Caldas Teixeira, L. (2017). Fear of Public Speaking: Perception of College Students and Correlates. Journal of Voice, 31(1), 7-11. https://doi.org/10.1016/j.jvoice.2015.12.012
- Goberman, A. M., Hughes, S., & Haydock, T. (2011). Acoustic characteristics of public speaking: Anxiety and practice effects. Speech Communication, 53(6), 867–876. https://doi.org/10.1016/j.specom.2011.02.005
- King, P. E., & Finn, A. N. (2017). A test of attention control theory in public speaking: cognitive load influences the relationship between state anxiety and verbal production. Communication Education, 66(2), 168–182. https://doi.org/10.1080/03634523.2016.1272128
- Wörtwein, T., Chollet, M., Schauerte, B., Morency, L.-P., Stiefelhagen, R., & Scherer, S. (2015). Multimodal Public Speaking Performance Assessment. International Conference on Multimodal Interaction, 43–50. https://doi.org/10.1145/2818346.2820762
Introduction à l'informatique en Sciences Sociales
Schyns, Michael
2010
Course notes (Learning materials)
Informatique en Sciences de Gestion
Schyns, Michael
2005
Course notes (Learning materials)
Informatique en Sciences de Gestion et en Sciences Economiques - Niveau 2
Schyns, Michael
2009
Other (Reports)
Doc'Data: mesure de la persévérance au doctorat à l'Université de Liège
Aerts, Stéphanie; Haesbroeck, Gentiane; Schyns, Michael
2015
Le Conseil du Doctorat a parmi ses missions celle d’accompagner les doctorants dans leur
parcours et de mettre en place des actions en vue de favoriser la réussite. Cependant, pour
réellement mesurer l’impact des actions mises en oeuvre dans cette optique, il faut d’abord
pouvoir quantifier le taux de réussite. Or, mesurer le taux de réussite dans les études de
3ème cycle n’est pas une démarche évidente. De nombreux raccourcis de raisonnement
sont tentants mais mènent à des résultats très variables et incorrects. Le but de ce document est de présenter les difficultés inhérentes au calcul d’un taux de réussite et de proposer quelques procédures appropriées. Dans un premier temps, les chances (ou, d’un point de vue plus formel, les
probabilités) de réussite et d'abandon des doctorants sont modélisées en fonction du nombre d’années d’inscription et en tenant compte de caractéristiques du doctorant comme son genre,
sa nationalité, son âge au moment de l’inscription, son statut professionnel... L'analyse descriptive et exploratoire est ensuite confirmée par l’application d’une analyse de survie avec risques compétitifs.
External report (Reports)
RAPPORT DE RECHERCHE SUR UNE APPLICATION DE GESTION DE LA COLLABORATION DU SERVICE EXPÉDITION DU CHARGEUR AVEC LE TRANSPORTEUR
Dans ce rapport, les échanges d'information d'un donneur d'ordre, d'un transporteur et d'un fournisseur au sein d'une chaîne de distribution sont analysés. Les possibilités de tracking et de tracing de TransLogisTIC sont utilisés pour générer des KPI de performance et un modèle d'optimisation de quais de chargement est décrit dans une version Off-line et On-line.
External report (Reports)
RAPPORT DE RECHERCHE SUR L’OPTIMISATION DU ROUTAGE ET DU CHARGEMENT DE VEHICULES.
Dans ce rapport confidentiel, un algorithme d'optimisation du chargement de véhicules a été mis au point dans le cadre d'une application avec un partenaire industriel.
External report (Reports)
RAPPORT INTERNE : REVUE DE LITTERATURE SUR LA GESTION DES RESSOURCES RÉUTILISABLES ET DES MÉTHODES D’OPTIMISATION
Dans cette revue de la littérature scientifique, on peut trouver une synthèse des thématiques liées aux modèles et aux techniques d'optimisation utilés pour la gestion de ressources réutilisables dans un réseau tels que les containers entre des ports de mers ou des wagons dans un réseau ferroviaire. Les textes fondateurs sont mentionnés dans un ordre historique et un commentaire est fait soit sur le modèle investiqué et ses particularités ou la technique de résolution.
