Partners: Northeastern University, University of Minnesota, University of Piraeus
Funding: FWF
Employed Technologies: PostgreSQL, PostGIS, Visual Paradigm, Hibernate, JBoss Drools, Java, R, Python
Web: https://sites.google.com/view/insituevo
Team: DI Dr. Andrea Salfinger
Inductive Situation Evolution Modeling
inSiTUEVO is a research project in the area of Cognitive Situation Management. Broadly speaking, Cognitive Situation Management involves the problem of how machines can not only perceive the individual elements of their observed environment, but understand the whole "big picture", i.e., encountered situations, by interrelating these individual perceptions. To do so, artifical agents require suitable situation models representing the event patterns of interest, against which they can compare their sensed observations.
inSiTUEVO aims at supporting the acquisition of these situation models, by developing novel Knowledge Discovery & Data Mining approaches to automatically induce symbolic situation evolution models from data.
Publications:
@inproceedings{Salf2005:Reinforcement,
title = {Reinforcement Learning Meets Cognitive Situation Management: A Review of Recent Learning Approaches from the Cognitive Situation Management Perspective},
author = {Andrea Salfinger},
year = {2020},
booktitle = {2020 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). Canada},
month = {05}
}
@inproceedings{10.1145/3410530.3414433,
title = {Deep Learning for Cognitive Load Monitoring: A Comparative Evaluation},
author = {Salfinger, Andrea},
year = {2020},
publisher = {Association for Computing Machinery},
booktitle = {Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers},
pages = {462–467},
series = {UbiComp-ISWC '20},
address = {New York, NY, USA},
isbn = {9781450380768}
}
@inproceedings{ieee-9190165,
title = {Towards Neural Situation Evolution Modeling: Learning a Distributed Representation for Predicting Complex Event Sequences},
author = {Andrea {Salfinger} and Lauro {Snidaro}},
year = {2020},
booktitle = {2020 IEEE 23rd International Conference on Information Fusion (FUSION)},
pages = {1-8}
}
@inproceedings{DBLP:conf/inffus19/Salfinger_fusion19,
title = {Framing Situation Prediction as a Sequence Prediction Problem: A Situation Evolution Model Based on Continuous-Time Markov Chains},
author = {Salfinger, Andrea},
year = {2019},
booktitle = {22nd International Conference on Information Fusion (FUSION)},
month = {07}
}
@inproceedings{DBLP:conf/cogsima/Salfinger19,
title = {Situation Mining: Event Pattern Mining for Situation Model Induction},
author = {Andrea Salfinger},
year = {2019},
booktitle = {{IEEE} Conference on Cognitive and Computational Aspects of Situation Management, CogSIMA 2019, Las Vegas, NV, USA, April 8-11, 2019},
pages = {17--25},
month = {04}
}