Computational Sensemaking Lab

Research - About

The Computational Sensemaking Lab (CSLab) focuses on how to ‘make sense‘ in the context of complex information and knowledge processes from an interdisciplinary perspective. By collecting and analyzing rich data to transform our understanding of individuals, organizations, and societies, we aim at augmenting human intelligence for assisting the involved actors in all their purposes both online and in the physical world. This is enabled by developing computational methods and tools for computational sensemaking, focusing on advanced data modeling, explicative analysis, and transparent decision-support.
Our research focuses on:

• Explicative Data Science, e.g., using Pattern Mining
• Social Sensing, e.g., using Wearable Sensors
• Artificial Intelligence - Machine Learning
• Human-Machine Intelligence
• Social Signal Processing
• Complex Networks
• Big Data

CSLab is an interdisciplinary group of scholars, mainly based at the Department of Cognitive Science and Artificial Intelligence (DCA) at Tilburg University. With a branch at the Jheronimus Academy of Data Science (JADS), it also integrates a number of associated researchers from JADS.

News

• Journal paper accepted - International Journal of Transdisciplinary AI. Behavioral Link Analytics on Heterogeneous Human Interaction Networks by Martin Atzmueller, Cicek Güven, Parisa Shayan, Spyroula Masiala, Rick Mackenbach and Werner Liebregts


• Paper accepted - IEEE International Conference on Data Mining - Workshop: Large-scale Industrial Time Series Analysis. An Improved Wide-Kernel CNN for Classifying Multivariate Signals in Fault Diagnosis by Jurgen van den Hoogen, Stefan Bloemheuvel and Martin Atzmueller


• Paper accepted - IEEE International Conference on Control, Decision and Information Technologies. Centrality-Based Anomaly Detection on Multi-Layer Networks Using Many-Objective Optimization by Asep Maulana and Martin Atzmueller


• Paper accepted at the 22nd International Conference on Discovery Science (DS 2019): A Framework for Human-Centered Exploration of Complex Event Log Graphs, by Martin Atzmueller, Stefan Bloemheuvel, and Benjamin Kloepper


• Paper accepted at AfCAI 2019 - Affective Computing and Context Awareness in Ambient Intelligence: Towards Multimodal Characterization of Dialogic Moments On Social Group Face-to-Face Interaction - by Ngoc N. T. Doan, Andrius Penkauskas, Ecaterina Grigoriev, Lisa E. Rombout, Paris Mavromoustakos-Blom, Maryam Alimardani, and Martin Atzmueller


• Paper accepted at AfCAI 2019 - Affective Computing and Context Awareness in Ambient Intelligence: Towards Socio-Technical Design of Explicative Systems: Transparent, Interpretable and Explainable Analytics and its Perspectives in Social Interaction Contexts - by Martin Atzmueller


• Paper accepted at TransAI 2019 - IEEE International Conference on Transdisciplinary Artificial Intelligence: Observing and Modeling User Behavior on Socio-Spatial Interaction Networks: Conformance, Exceptions, and Anomalies. In Proc. IEEE International Conference on Transdisciplinary Artificial Intelligence, Boston, MA, USA, 2019. IEEE Press. - by Martin Atzmueller, Cicek Guven, Parisa Shayan, Spyroula Masiala, Rick Mackenbach, and Werner Liebregts.


• Paper accepted at the 22nd International Conference on Applications of Declarative Programming and Knowledge Management (INAP 2019): Towards Generating Explanations for ASP-Based Link Analysis using Declarative Program Transformations, by Martin Atzmueller, Cicek Güven and Dietmar Seipel.


• Paper accepted at the 22nd International Conference on Applications of Declarative Programming and Knowledge Management (INAP 2019): Finding Maximal Non–Redundant Association Rules in Tennis Data, by Daniel Weidner, Martin Atzmueller and Dietmar Seipel.


• Paper accepted at ABIS 2019/ACM Hypertext 2019: Descriptive Network Modeling and Analysis for Investigating User Acceptance in a Learning Management System Context, by Parisa Shayan, Roberto Rondinelli, Menno van Zaanen and Martin Atzmueller


• Paper accepted at ABIS 2019/ACM Hypertext 2019: Behavioral Analysis on Socio-Spatial Interaction Networks concerning User Preferences, Interactions and their Perception, by Martin Atzmueller, Cicek Güven, Spyroula Masiala, Rick Mackenbach, Parisa Shayan and Werner Liebregts


• Paper accepted at MIEL 2019/17th International Conference on Business Process Management (BPM 2019): Graph Summarization for Computational Sensemaking on Complex Industrial Event Logs, by Stefan Bloemheuvel, Benjamin Kloepper and Martin Atzmueller


• Journal Paper accepted at Applied Network Science (now - In Press): Martin Atzmueller, Henry Soldano, Guillaume Santini, and Dominique Bouthinon. MinerLSD: Efficient Mining of Local Patterns on Attributed Networks. Applied Network Science, 2019.


• Abstract accepted at EUSN 2019 - The 4th European Conference on Social Networks: Roberto Rondinelli, Martin Atzmueller, Giancarlo Ragozini. Looking for Best Descriptors to Map Networks via Subgroup Discovery. First Results From a Simulation Study.


• Paper accepted at the International Workshop on Transparent, Explainable and Affective AI in Medical Systems (TEAAM), co-located with the 17th International Conference on AI in Medicine: Erica Ramirez, Markus Wimmer, Martin Atzmueller. A Computational Framework for Interpretable Anomaly Detection and Classification of Multivariate Time Series with Application to Human Gait Data Analysis


• Abstract accepted at IFCS 2019 - The 16th Conference of the International Federation of Classification Societies: Roberto Rondinelli, Martin Atzmueller, Giancarlo Ragozini. Using Subgroup Discovery to Find the Best Descriptors to Map Networks: A Simulation Study.


• Abstract accepted at Performing Robots Conference: Homo Sentient AI: Investigating Moments of Shifting Consciousness. Team: Petra Ardai, Rinske Bosma, Lisa Rombout, Ecaterina Grigoriev, Andrius Penkauskas, Bo Doan, Maryam Alimardani, Paris Mavromoustakos Blom, Martin Atzmueller


• Journal Paper in Frontiers: Cicek Güven and Martin Atzmueller. Applying Answer Set Programming for Knowledge-Based Link Prediction on Social Interaction Networks.


• Journal Paper in Small Business Economics. Special Issue on Big Data and Artificial Intelligence: Werner Liebregts, Pourya Darnihamedani, Eric Postma and Martin Atzmueller. The Promise of Social Signal Processing for Research on Decision Making in Entrepreneurial Contexts


• Journal Paper in Scientometrics: Mark Kibanov, Raphael Heiberger, Simone Roedder, Martin Atzmueller and Gerd Stumme. Social Studies of Scholarly Live with Sensor-based Ethnographic Observations


• Journal Paper in Applied Network Science 2019, 4:4: Roberto Interdonato, Martin Atzmueller, Sabrina Gaito, Rushed Kanawati, Christine Largeron and Alessandra Sala. Feature-Rich Networks: Going Beyond Complex Network Topologies

Projects

• MODUS is a project funded by DFG for Model-based Anomaly Pattern Detection and Analysis in Ubiquitous and Social Interaction Networks.

• Di-Plast: Digital Circular Economy for the Plastics Industry (funded by Interreg NWE). Di-Plast improves processes for a more stable rPM material supply and quality: sensoring generates data within supply chains; data analytics provides information about rPM quality, amounts, and supply timing; Value Stream Management improves rPM processes & logistics, environmental assessments validate sustainability.

• Resilient Athletes: In this project (funded by ZonMW), a multidisciplinary personalized approach is being developed and applied. We focus on the resilience of athletes, with the aim that athletes can cope with the physical and mental stress factors to which they are exposed.

• DIaNE, i.e. the "Deprez Integrated and Networked Environment", aims to make the Deprez-building (where MindLabs is located) "intelligent", using sensors and smart data analytics.




Selected Recent Publications

• Martin Atzmueller. Compositional Subgroup Discovery on Attributed Social Interaction Networks Proc. DS 2018: International Conference on Discovery Sciene, Springer, 2018

• Stefan Bloemheuvel, Martin Atzmueller and Marie Postma: Evolution of Contacts and Communities in Social Interaction Networks of Face-to-Face Proximity Proc. BNAIC 2018, Jheronimus Academy of Data Science, Den Bosch, The Netherlands

• Sebastiaan Merino and Martin Atzmueller: Behavioral Topic Modeling on Naturalistic Driving Data Proc. BNAIC 2018, Jheronimus Academy of Data Science, Den Bosch, The Netherlands

• Martin Atzmueller, and Florian Lemmerich. Homophily at Academic Conferences. Proc. WWW 2018 (Companion), 2018.
  

• Martin Atzmueller, Lisa Thiele, Gerd Stumme, and Simone Kauffeld. Analyzing Group Interaction on Networks of Face-to-Face Proximity using Wearable Sensors. Proc. IEEE International Conference on Future IoT Technologies, IEEE Press, Boston, MA, USA, 2018.

• Martin Atzmueller, Daan Kolkman, Werner Liebregts and Arjan Haring. Towards Estimating Happiness using Social Sensing: Perspectives on Organizational Social Network Analysis. Proc. Workshop on Affective Computing and Context Awareness in Ambient Intelligence, Valencia, Spain, 2018
  

• Martin Atzmueller, Stephan Doerfel, and Folke Mitzlaff. Description-Oriented Community Detection using Exhaustive Subgroup Discovery. Information Sciences, (329):965-984, 2016.

• Martin Atzmueller, Benjamin Kloepper, Hassan Al Mawla, Benjamin Jäschke, Martin Hollender, Markus Graube, David Arnu, Andreas Schmidt, Sebastian Heinze, Lukas Schorer, Andreas Kroll, Gerd Stumme, and Leon Urbas. Big Data Analytics for Proactive Industrial Decision Support: Approaches & First Experiences in the Context of the FEE Project. atp edition, (58)9 2016.

• Lukas Eberhard, Christoph Trattner, and Martin Atzmueller. Predicting Trading Interactions in an Online Marketplace through Location-Based and Online Social Networks. Information Retrieval Journal, 22(2), 2019.

• Andrew Hendrickson, Jason Wang and Martin Atzmueller. Identifying Exceptional Descriptions of People using Topic Modeling and Subgroup Discovery.Proceedings ISMIS 2018, Springer, 2018.

• Florian Lemmerich, Martin Atzmueller, and Frank Puppe. Fast Exhaustive Subgroup Discovery with Numerical Target Concepts. Data Mining and Knowledge Discovery, (30):711-762, 2016.

• Grzegorz J. Nalepa, Martijn van Otterlo, Szymon Bobek and Martin Atzmueller: From Context Mediation to Declarative Values and ExplainabilityProc. FAIM/FIX/IJCAI 2018 Workshop on Explainable Artificial Intelligence (XAI), IJCAI 2018, Stockholm, Sweden.

Eric Sternberg and Martin Atzmueller. Knowledge-Based Mining of Exceptional Patterns in Logistics Data: Approaches and Experiences in an Industry 4.0 Context. Proceedings ISMIS 2018, Springer, 2018.




Software

The CSLab provides the VIKAMINE project for subgroup discovery and analytics, and the ConnectU software platform for enhancing physical and digital interactions, for connecting things, people, and minds.

• 
   
  

  VIKAMINE is an extensible open-source rich-client environment and platform for pattern mining and analytics. VIKAMINE features several powerful and intuitive visualizations complemented by fast automatic mining methods; it is provided as Open Source, under the GNU Lesser General Public License (LGPL). The R subgroup package (rsubgroup R package) provides a wrapper around the VIKAMINE core.




• ConnectU is based on Ubicon -- an extensible framework for building and hosting applications targeting both social and ubiquitous environments (see Conferator, EveryAware).
  Ubicon provides a powerful platform featuring several components and mechanisms in order to handle heterogeneous (Big) data in a scalable way. The source code of Ubicon is available as Open Source, see code.ubicon.eu. The main module of Ubicon is licensed under the GNU AGPL, while several modules are also licensed under GNU LGPL (see the URL above for details).

Links:
• Ubicon Platform for Ubiquitous Social Computing
• rsubgroup R package
• VIKAMINE