Stiftungsprofessur Semantische Informationssysteme gefördert von der ROSEN Gruppe.
Semantic Information Systems
Research Group Semantic Information Systems
Prof. Dr. Martin Atzmüller
Semantic Information Systems
Institute of Computer Science
P.O. Box 4469
49069 Osnabrueck, Germany
- Best Paper Award (IEEE ETFA/IES Young Professionals & Students Paper Award) for the Paper Visual Detection of Tiny and Transparent Objects for Autonomous Robotic Pick-and-Place Operations, IEEE (2022) by Timo Markert, Sebastian Matich, Daniel Neykov, Markus Muenig, Andreas Theissler, and Martin Atzmueller
>> Check out our video <<
- New paper in International Journal of Data Science and Analytics
Stefan Bloemheuvel, Jurgen van den Hoogen, Dario Jozinovic, Alberto Michelini, and Martin Atzmueller (2022) Graph neural networks for multivariate time series regression with application to seismic data
- New paper Behavior Research Methods
Dan Hudson, Travis J. Wiltshire, and Martin Atzmueller (2022) multiSyncPy: A Python Package for Assessing Multivariate Coordination Dynamics
- New paper in Applied Network Science.
Stefan Bloemheuvel, Jurgen van den Hoogen and Martin Atzmueller (2021) A Computational Framework for Modeling Complex Sensor Network Data Using Graph Signal Processing and Graph Neural Networks in Structural Health Monitoring
- New Paper in Applied Sciences: Special Issue Data Mining Applications in Industry 4.0
Jurgen van den Hoogen, Stefan Bloemheuvel, and Martin Atzmueller (2021) Classifying Multivariate Signals in Rolling Bearing Fault Detection Using Adaptive Wide-Kernel CNNs
- Best Paper Award (IEEE ETFA/IES Young Professionals & Students Paper Award) for the Paper Fingertip 6-Axis Force/Torque Sensing for Texture Recognition in Robotic Manipulation, IEEE (2021) by Timo Markert, Sebastian Matich, Elias Hoerner, Andreas Theissler, and Martin Atzmueller
>> Check out our video <<
- New Paper accepted at DSAA 2021 (8th IEEE International Conference on Data Science and Advanced Analytics) Leonid Schwenke and Martin Atzmueller (2021) Constructing Global Coherence Representations: Identifying Interpretability and Coherences of Transformer Attention in Time Series Data
- New Paper - nominated for Best Paper Award - at the 34th International FLAIRS Conference.
Leonid Schwenke and Martin Atzmueller (2021) Show Me What You’re Looking For: Visualizing Abstracted Transformer Attention for Enhancing Their Local Interpretability on Time Series Data.
SIS Research & Mission
The research of the ROSEN-Group-Endowed Chair of Semantic Information Systems and the according research group, headed by Prof. Dr. Martin Atzmueller, centers around Artificial Intelligence and Data Science. Its major focus is on data analysis and machine learning on complex data such as graphs, networks, and temporal data, also with a human-centered perspective.
Overall, our work focuses on how to 'make sense' of complex information and knowledge processes - leveraging the massive amounts of data collected in science and industry by intelligent analytics and semantic interpretation. For instance, this includes the identification of interesting/exceptional patterns and structures, predictive modeling, analysis and exploration of complex heterogeneous and multi-modal data, as well as human-centered decision support.
By connecting computational approaches with the human cognitive, behavioral, and social contextual perspectives - thus linking technologies with their users - our goal is to augment human intelligence and to assist human actors in all their purposes, both online and in the physical world.
The Semantic Information Systems research group is founding member of the Research Unit Data Science at Osnabrück University. In addition, the group is also connected with the German Research Center for Artificial Intelligence (DFKI), in particular DFKI Niedersachsen where Prof. Atzmueller is an Affiliated Professor.
|Prof. Dr. Martin Atzmueller
Head of Semantic Information Systems group.
Research Interests:: Artificial Intelligence, Knowledge Discovery, Machine Learning, Network Science, Pattern Mining
Research Assistants/PhD Students/External PhD Students
|Arnab Ghosh Chowdhury
Deep Learning, Information Engineering, Multi-Modal Learning, Document Intelligence
Anomaly and Exceptionality Detection, Deep Capsule Networks, Time Series Analysis, Sensor Data
Deep Learning, Transformer Architectures, Knowledge-Aware Explanation Engineering, Time Series Analysis
|Harihara Bharathy Swaminathan
Automotive Radar Sensors, Environment Perception, HD Map Reliability, Machine Learning, Autonomous Driving.
Explainability, Supervised Machine Learning, Deep Learning, Cyber-Security.
|Stefan Bloemheuvel (JADS):
Graph Signal Processing, Graph Neural Networks, Time Series Analysis, Sensor Networks
|Frank Ehebrecht (ROSEN):
Informed Machine Learning, Deep Learning, Physical Models, Sensor Data Analysis
|Timo Markert (Wittenstein SE):
Machine Learning, Sensor Data Analysis, Tactile Object Recognition, Robotic Manipulation
|Parisa Shayan (TiU):
Educational Data Mining, Network Analysis, User Modeling, Learning Management Systems
|Jurgen van den Hoogen (JADS):
Deep Learning, Time Series Analysis/Classification, Fault Diagnosis, Sensor Data
Di-Plast: Digital Circular Economy for the Plastics Industry (funded by Interreg NWE (EFRE, EU regional development fond)). Di-Plast improves processes for a more stable rPM material supply and quality using artificial intelligence methods and data science approaches: 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.
NWO KIEM ICT ODYN: Observing Team Dynamics and Communication using Sensor-Based Social Analytics.
Resilient Athletes: In this interdisciplinary project (funded by ZonMW), a multidisciplinary personalized human-sensor-based data science 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.
- VIKAMINE is an extensible open-source rich-client environment and platform for exploratory pattern mining and analytics. VIKAMINE features 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.