BNAIC/BENELEARN 2019
Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg

Table of Contents

• Preface
  
  

ML1: Applied Machine Learning

• Understanding Telecom Customer Churn with Machine Learning: From Prediction to Causal Inference (abstract; invited to postproceedings)
  Théo Verhelst, Olivier Caelen, Jean-Christophe Dewitte, Bertrand Lebichot, Gianluca Bontempi
• Paired Supervised Learning and Unsupervised Pretraining of CNN-Architecture for Violence Detection in Videos (abstract; invited to postproceedings)
  Abel Díaz Berenguer, Meshia Cédric Oveneke, Mitchel Alioscha-Perez, Hichem Sahli
• Data-Driven Policy on Feasibility Determination for the Train Shunting Problem (extended abstract)
  Paulo Roberto de Oliveira da Costa, Jason Rhuggenaath, Yingqian Zhang, Alp Akcay, Wan-Jui Lee, Uzay Kaymak
• News Topic Recommendation Using an Extended Bayesian Personalized Ranking (abstract; invited to postproceedings)
  Alireza Gharahighehi, Celine Vens
• Analysing Visitor Flow Using a Bluetooth Positioning System (thesis abstract)
  Pieter van den Ham, Bert Bredeweg, Maartje Raijmakers

ML2: Deep Learning

• Cross-Domain Neural-Kernel Networks (extended abstract)
  Siamak Mehrkanoon
• Interpreting and Explaining Deep Models Visually (extended abstract)
  Jose Oramas, Kaili Wang, Tinne Tuytelaars
• DeepProbLog: Neural Probabilistic Logic Programming (extended abstract)
  Robin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, Luc De Raedt
• Temporal Factorization of 3D Convolutional Kernels (short paper)
  Gabrielle Ras, Luca Ambrogioni, Umut Guclu, Marcel van Gerven
• Unsupervised Deep Feature Extraction for Neonatal Sleep Stage Classification (thesis abstract)
  Nick Seeuws, Amir Hossein Ansari, Sabine Van Huffel, Gunnar Naulaers

AI1: Constraint Programming

• Stochastic Constraint Propagation for Mining Probabilistic Networks (extended abstract)
  Anna Louise Latour, Behrouz Babaki, Siegfried Nijssen
• Generic Constraint-Based Block Modeling Using Constraint Programming (extended abstract)
  Alex Mattenet, Ian Davidson, Siegfried Nijssen, Pierre Schaus
• Learning Optimal Decision Trees Using Constraint Programming (extended abstract)
  Hélène Verhaeghe, Siegfried Nijssen, Gilles Pesant, Claude-Guy Quimper, Pierre Schaus
• Vehicle Routing by Learning from Historical Solutions (extended abstract)
  Rocsildes Canoy, Tias Guns

RP1: Applied Machine Learning

• A Machine Learning-Based Approach for Predicting Tool Wear in Industrial Milling Processes (extended abstract)
  Mathias Van Herreweghe, Mathias Verbeke, Wannes Meert, Tom Jacobs
• Predictive Maintenance of a Rotating Condenser Inside a Synchrocyclotron (long paper)
  Valentin Hamaide, François Glineur
• Segmentation of Photovoltaic Panels in Aerial Photography Using Group Equivariant FCNs (long paper)
  Lars Bokkers, Luca Ambrogioni, Umut Güçlü
• Partial Convolution Based Multimodal Autoencoder for Art Investigation (long paper)
  Xianghui Xie, Laurens Meeus, Aleksandra Pizurica
• Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models (short paper)
  Pieter Delobelle, Bettina Berendt
• Designing MacPherson Suspension Architectures Using Bayesian Optimization (long paper)
  Sinnu Susan Thomas, Jacopo Palandri, Mohsen Lakehal-Ayat, Punarjay Chakravarty, Friedrich Wolf-Monheim, Matthew Blaschko
• Improving Machine Learning-Based Decision-Making Through Inclusion of Data Quality (short paper)
  Jens de Hoog, Siegfried Mercelis, Peter Hellinckx
• Industrial Assets Performance Labelling Based on Numerically Encoded Event Logs (long paper)
  Pierre Dagnely, Tom Tourwé, Elena Tsiporkova

RP2: Applications of Artificial Intelligence

• Deep Shared Representation Learning for Weather Elements Forecasting (extended abstract)
  Siamak Mehrkanoon
• Failure Avoidance for Wind Turbines through Fleetwide Control (extended abstract)
  Timothy Verstraeten, Ann Nowé, Jan Helsen
• Great Expectations & Aborted Business Initiatives: The Paradox of Social Robot Between Research and Industry (short paper)
  Silvia Tulli, Agustin Ambrossio, Amro Najjar, Francisco Javier Rodriguez Lera
• End-To-End Anomaly Detection, Correction and Prediction of Missing Values in Historical Daily Temperature Timeseries (abstract; invited to postproceedings)
  Mitchel Alioscha-Perez, Meshia Cédric Oveneke, Abel Díaz Berenguer, Cédric Bertrand, Hichem Sahli
• Learning to Transform, Combine, and Reason in Open-Domain Question Answering (extended abstract)
  Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke
• The XAI paradox: Systems that Perform Well for the Wrong Reasons (abstract; invited to postproceedings)
  Cor Steging, Lambert Schomaker, Bart Verheij
• Handling Unforeseen Failures Using Argumentation-Based Learning (extended abstract)
  Hamed Ayoobi, Ming Cao, Rineke Verbrugge, Bart Verheij
• Autoencoder-Learned Local Image Descriptor for Image Inpainting (long paper)
  Nina Zizakic, Izumi Ito, Laurens Meeus, Aleksandra Pizurica
• On Domination and Control in Strategic Ability (extended abstract)
  Damian Kurpiewski, Michał Knapik, Wojciech Jamroga

ML3: Applied ML & Machine Learning for Medicine

• Cost-Efficient Segmentation of Electron Microscopy Images Using Active Learning (abstract; invited to postproceedings)
  Joris Roels, Yvan Saeys
• Disentangled Variational Auto-Encoders for Explaining ECG Beat Embeddings (extended abstract)
  Tom Van Steenkiste, Dirk Deschrijver, Tom Dhaene
• Classification of Human White Blood Cells Using Machine Learning for Stain-Free Imaging Flow Cytometry (extended abstract)
  Maxim Lippeveld, Carly Knill, Emma Ladlow, Andrew Fuller, Louise J Michaelis, Yvan Saeys, Andrew Filby, Daniel Peralta
• SMURFF: A High-Performance Framework for Matrix Factorization Methods (extended abstract)
  Tom Vander Aa, Imen Chakroun, Tom Ashby, Jaak Simm, Adam Arany, Yves Moreau, Thanh Le Van, José Felipe Golib Dzib, Jörg Wegner, Vladimir Chupakhin, Hugo Ceulemans, Roel Wuyts, Wilfried Verachtert
• Predicting 120-Day Hospital Readmission Using Medical Administrative Patient Data (thesis abstract)
  Marijn van Wingerden, Jelle de Boer, Eric Postma

AI2: AI For Health & Medicine

• Towards a Phylogenetic Measure to Quantify HIV Incidence (abstract; invited to postproceedings)
  Pieter Libin, Nassim Versbraegen, Ana Abecasis, Perpetua Gomes, Tom Lenaerts, Ann Nowé
• A Residual Neural-Network Model to Predict Visual Cortex Measurements (short paper)
  Anne-Ruth José Meijer, Arnoud Visser
• Data Mining for ADHD & ASD Prediction Based on Resting-State fMRI Signals: A Literature Review (long paper)
  Sarah Itani, Fabian Lecron, Philippe Fortemps
• Integrating Clinically-Relevant Features into Skin Lesion Classification (thesis abstract)
  Emmeke Veltmeijer, Sezer Karaoglu, Theo Gevers

ML4: Supervised & Semi-Supervised Learning

• An Aggregate Learning Approach for Interpretable Semi-Supervised Population Prediction and Disaggregation Using Ancillary Data (extended abstract)
  Guillaume Derval, Frédéric Docquier, Pierre Schaus
• Set-Valued Prediction in Multi-Class Classification (extended abstract)
  Thomas Mortier, Marek Wydmuch, Krzysztof Dembczyński, Eyke Hüllermeier, Willem Waegeman
• Calibrated Multi-Probabilistic Prediction as a Defense against Adversarial Attacks (abstract; invited to postproceedings)
  Jonathan Peck, Bart Goossens, Yvan Saeys
• Machine Learning Methods for Ordinal Classification with Additional Relative Information (abstract; invited to postproceedings)
  Mengzi Tang, Raúl Pérez-Fernández, Bernard De Baets

AI3: Generative & Creative AI

• Synthesizing Personality-Dependent Body Postures Using Generative Adversarial Networks (long paper)
  Frederik Calsius, Stylianos Asteriadis
• Latent Space Exploration Using Generative Kernel PCA (abstract; invited to postproceedings)
  David Winant, Joachim Schreurs, Johan Suykens
• Modelling Mutually Interactive Fictional Character Conversational Agents (long paper)
  Thomas Winters
• Learning Hierarchical Spectral Representations of Human Speech with the Information Dynamics of Thinking (thesis abstract)
  Steven Homer
• Crafting Conversational Agents’ Personality in a User-Centric Context (thesis abstract)
  Catia Ferreira, Sviatlana Hoehn
• A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games (thesis abstract)
  René Raab, Kurt Driessens

AI4: Natural Language

• Training a Speech-to-Text Model for Dutch on the Corpus Gesproken Nederlands (long paper)
  Willem Röpke, Roxana Rădulescu, Kyriakos Efthymiadis, Ann Nowé
• Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models (extended abstract)
  Florian Kunneman, Thiago Castro Ferreira, Antal van Den Bosch, Emiel Krahmer
• Explaining Lexical Processing Times with Cognitively Plausible Computational Models (abstract; invited to postproceedings)
  Wietse de Vries
• Target-Based Sentiment Analysis as a Sequence-Tagging Task (long paper)
  Zoe Gerolemou, Johannes C. Scholtes

RP3: Reinforcement Learning

• Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics (extended abstract)
  Denis Steckelmacher, Hélène Plisnier, Diederik M. Roijers, Ann Nowé
• Action Learning and Grounding in Simulated Human-Robot Interactions (extended abstract)
  Oliver Roesler, Ann Nowé
• A Reinforcement Learning Method to Select Ad Networks in Waterfall Strategy (extended abstract)
  Reza Refaei Afshar, Yingqian Zhang, Murat Firat, Uzay Kaymak
• Transfer Reinforcement Learning across Environment Dynamics with Multiple Advisors (long paper)
  Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers, Ann Nowé
• Maximum Entropy Bayesian Actor Critic (long paper)
  Steven Homer
• Thompson Sampling for m-top Exploration (extended abstract)
  Pieter Libin, Timothy Verstraeten, Diederik Roijers, Wenjia Wang, Kristof Theys, Ann Nowé
• Distillation of Deep Reinforcement Learning Models Using Fuzzy Inference Systems (thesis abstract)
  Arne Gevaert, Jonathan Peck, Yvan Saeys

RP4: Machine Learning for Bioinformatics & Life Science

• Computer Aided Detection and Diagnosis System for Breast Cancer Detection Based on High Resolution 3D micro-CT Breast Microcalcifications (extended abstract)
  Redona Brahimetaj, Evgenia Papavasileiou, Frederik Temmermans, Bruno Cornelis, Inneke Willekens, Johan De Mey, Bart Jansen
• Investigating Time Series Classification Techniques for Rapid Pathogen Identification with Single-Cell MALDI-TOF Mass Spectrum Data (extended abstract)
  Christina Papagiannopoulou, René Parchen, Willem Waegeman
• ExCAPE-DB: An Integrated Large Scale Dataset Facilitating Big Data Analysis in Chemogenomics (extended abstract)
  Jiangming Sun, Nina Jeliazkova, Vladimir Chupakhin, Jose-Felipe Golib-Dzib, Lars Carlsson, Jörg Wegner, Hugo Ceulemans, Ivan Georgiev, Vedrin Jeliazkov, Nikolay Kochev, Thomas Ashby, Hongming Chen
• Nonlinear Causality Inference in Microarray Time Series (thesis abstract)
  Fateme Nateghi Haredasht, Mohammad Hassan Moradi
• A Study of Early Sepsis Detection Models Based on Multivariate Medical Time Series (thesis abstract)
  Aren Maes, Tom Van Steenkiste, Tom Dhaene, Dirk Deschrijver

ML5: Deep Learning & Reinforcement Learning

• Deep Quality-Value (DQV) Learning (extended abstract)
  Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
• Bayesian RL in Factored POMDPs (extended abstract)
  Sammie Katt, Frans Oliehoek, Chris Amato
• HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory (abstract; invited to postproceedings)
  Jakob Struye, Kevin Mets, Steven Latré
• Unconstrained Monotonic Neural Networks (extended abstract)
  Antoine Wehenkel, Gilles Louppe

ML6: Data & Network Mining

• Conditional Network Embeddings (extended abstract)
  Bo Kang, Jefrey Lijffijt, Tijl De Bie
• Adversarial Perturbations for Joint Entity and Relation Extraction (extended abstract)
  Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder
• Towards Deterministic Diverse Subset Sampling (abstract; invited to postproceedings)
  Joachim Schreurs, Michael Fanuel, Johan Suykens
• SubSect — An Interactive Itemset Visualization (abstract; invited to postproceedings)
  Joey De Pauw, Sandy Moens, Bart Goethals

AI5: Knowledge Representation & Hybrid AI

• A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems (extended abstract)
  Frank Van Harmelen, Annette ten Teije
• Learning Optimal Classification Trees Using a Binary Linear Program Formulation (extended abstract)
  Sicco Verwer, Yingqian Zhang
• SOGrounder: Modelling and Solving Second-Order Logic (extended abstract)
  Matthias van der Hallen, Gerda Janssens
• An Interactive Knowledge Base Application for Group Assignment (thesis abstract)
  Simon Vandevelde, Kylian Van Dessel, Herman Crauwels
• PARCo: A Knowledge-Based Agent for Context-Sensitive Reasoning and Decision-Making Regarding Privacy (thesis abstract)
  Andrei Popescu, Pinar Yolum

RP5: Supervised & Semi-Supervised Learning, Classification

• Term Based Semantic Clusters for Very Short Text Classification (extended abstract)
  Jasper Paalman, Shantanu Mullick, Kalliopi Zervanou, Yingqian Zhang
• Revision Classification for Current Events in Dutch Wikipedia Using a Long Short-Term Memory Network (short paper)
  Nienke Eijsvogel, Marijn Schraagen
• Reduction Methods for Multi-Label Datasets Based on Granular Computing (extended abstract)
  Marilyn Bello, Gonzalo Nápoles, Koen Vanhoof, Rafael Bello
• Scientific Machine Learning: Towards Predictive Closed-Form Models (long paper)
  Dimitri Papadimitriou, Steven Latre
• Towards Automated Grading of UML Class Diagrams with Machine Learning (long paper)
  Dave Stikkolorum, Peter van der Putten, Caroline Sperandio, Michel Chaudron
• Hierarchical Classification of Transposable Elements (thesis abstract)
  Felipe Kenji Nakano, Ricardo Cerri

RP6: Agents & Multi-Agent Systems

• Privacy Norms in Online Social Networks (extended abstract)
  Onuralp Ulusoy, Pinar Yolum
• What are we Measuring Anyway? A Literature Survey of Questionnaires Used in Studies Reported in the Intelligent Virtual Agent Conferences (extended abstract)
  Merijn Bruijnes, Siska Fitrianie, Deborah Richards, Amal Abdulrahman, Willem-Paul Brinkman
• Improving Zero-Intelligence Plus for Call Markets (short paper)
  Jannick Hemelhof, Mihail Mihaylov, Ann Nowé

BS1: Best Student Papers

• Iterative Model-Based Transfer in Deep Reinforcement Learning (thesis abstract)
  Jelmer Neeven
• Continuous Exploitative Measurement Trajectories Using Bayesian Optimisation (thesis abstract)
  Rémi Delanghe, Tom Van Steenkiste, Dirk Deschrijver, Tom Dhaene
• A Context Aware Deep Learning Architecture for Object Detection (thesis abstract)
  Kevin Bardool, Tinne Tuytelaars, Jose Oramas
• Privacy Preserving Reinforcement Learning over Distributed Datasets (thesis abstract)
  Regis Loeb, Timothy Verstraeten, Ann Nowe, Ann Dooms
• Formalization and Improvement of Ambulance Dispatching in Brabant-Zuidoost (thesis abstract)
  Nikki Theeuwes, Geert-Jan van Houtum, Yingqian Zhang, Björn Gadet
• Automated Artemia Detection and Length Measurement Using Deep Convolutional Networks (thesis abstract)
  Gang Wang, Bernard De Baets

AI6: Multi-Agent Systems

• Simulated Annealing as an Optimization Algorithm in the Automatic Modular Design of Robot Swarms (abstract; invited to postproceedings)
  Jonas Kuckling, Keneth Ubeda Arriaza, Mauro Birattari
• Runtime Revision of Norms and Sanctions Based on Agent Preferences (extended abstract)
  Davide Dell'Anna, Mehdi Dastani, Fabiano Dalpiaz
• Comparison of Different Exploration Schemes in the Automatic Modular Design of Robot Swarms (abstract; invited to postproceedings)
  Gaëtan Spaey, Miquel Kegeleirs, David Garzón Ramos, Mauro Birattari

AI7: Explainability

• Investigating People’s Attitudes Towards AI with a Smart Photo Booth (extended abstract)
  Hanna Schraffenberger, Yana van de Sande, Gabi Schaap, Tibor Bosse
• Explainable Robotics Applied to Bipedal Walking Gait Development (long paper)
  Nico Roos, Zhenglong Sun
• Visualising the Training Process of Convolutional Neural Networks for Non-Experts (long paper)
  Michelle Peters, Lindsay Kempen, Meike Nauta, Christin Seifert

RP7: Deep Learning

• Adversarial Variational Optimization of Non-Differentiable Simulators (extended abstract)
  Gilles Louppe, Joeri Hermans, Kyle Cranmer
• A Systematic Analysis of a Context Aware Deep Learning Architecture for Object Detection (long paper)
  Kevin Bardool, Tinne Tuytelaars, Jose Oramas
• A Scalable Logo Recognition Model with Deep Meta-Learning (thesis abstract)
  Mark de Blaauw, Diederik Roijers, Vesa Muhonen
• Deep Learning Applied to Sign Language (thesis abstract)
  Jérôme Fink, Anthony Clève, Benoît Frénay

Demo Session

• A Motorized Wheelchair that Learns to Make its Way through a Crowd (demo abstract)
  Denis Steckelmacher, Hélène Plisnier, Ann Nowé
• A Virtual Maze Game to Explain Reinforcement Learning (demo abstract)
  Youri Coppens, Eugenio Bargiacchi, Ann Nowé
• An Interactive Consultant (demo abstract)
  Pierre Carbonnelle, Bram Aerts, Marjolein Deryck, Joost Vennekens, Marc Denecker
• Virtual Screening on FPGA (demo abstract)
  Tom Vander Aa, Tom Ashby, Roel Wuyts
• DuStt – A Speech-to-Text Engine for Dutch (demo abstract)
  Willem Röpke, Roxana Rădulescu, Kyriakos Efthymiadis, Ann Nowé
• Gesture Recognition with an FMCW Radar (demo abstract)
  Habib-ur-Rehman Khalid, Sofie Pollin, Thomas Gielen, Hans Cappelle, Miguel Glassée, André Bourdoux, Hichem Sahli
• Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems (demo abstract)
  Jessica Coto Palacio, Yailen Martínez Jiménez, Ann Nowé
• Interactive Learning of Grounded Concepts (demo abstract)
  Jens Nevens, Paul Van Eecke, Katrien Beuls
• Politeness Detection in Speech for Human-Computer Interaction (demo abstract)
  Selma Yilmazyildiz Kayaarma, Sherik Lehal, Hichem Sahli
• ZebraTutor: Explaining How to Solve Logic Grid Puzzles (demo abstract)
  Jens Claes, Bart Bogaerts, Rocsildes Canoy, Emilio Gamba, Tias Guns