inSiTUEVO
A Research Project on Inductive Situation Evolution Modeling
Cognitive Situation Management | Situation Awareness | High-level Information Fusion | Artificial Intelligence | Intelligent Information Systems | Software Engineering
Publications:
Salfinger, A.: Situation Mining: Event Pattern Mining for Situation Model Induction: 2019 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). IEEE, Las Vegas, USA, 2019.
[Abstract] [IEEE Xplore] [pdf]
TL;DR: introduces a two-stage situation mining algorithm for deriving symbolic Situation Evolution Models from a situation database
Salfinger, A.: Framing Situation Prediction as a Sequence Prediction Problem: A Situation Evolution Model Based on Continuous-Time Markov Chains. 22nd International Conference on Information Fusion (FUSION). IEEE, Ottawa, Canada, 2019.
[Abstract] [IEEE Xplore] [pdf]
TL;DR: proposes to treat situation (evolution) prediction as a sequence prediction problem, addressed by extending the Situation Evolution Models learnt from the situation database to Continuous-Time Markov Chains
Salfinger, A.: Reinforcement Learning Meets Cognitive Situation Management: A Review of Recent Learning Approaches from the Cognitive Situation Management Perspective. 2020 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). IEEE, Victoria, Canada, 2020
[Abstract] [IEEE Xplore] [pdf]
TL;DR: introduces a reward formulation to adopt Reinforcement Learning (RL) for Cognitive Situation Management (CogSiMa) and reviews the implications and potential of recent RL developments for CogSiMa tasks
Salfinger, A.; Snidaro, L.: Towards Neural Situation Evolution Modeling: Learning a Distributed Representation for Predicting Complex Event Sequences. 23rd International Conference on Information Fusion (FUSION). ISIF, July 6-9, 2020
[Abstract] [IEEE Xplore] [pdf]
TL;DR: proposes a distributed representation for learning the evolution patterns in a given situation dataset, to capture the patterns between the situations' individual event types
Salfinger, A.: Deep Learning for Cognitive Load Monitoring: A Comparative Evaluation. In 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 (UbiComp/ISWC ’20 Adjunct), September 12–16, 2020, Virtual Event, Mexico. ACM, New York, NY, USA, 6 pages. https://doi.org/10.1145/3410530.3414433
[Abstract] [ACM Digital Library] [pdf]
TL;DR: evaluates the performance of different neural network architectures on a cognitive load monitoring problem
Pollak, M.; Salfinger, A.; Hummel, K. A.: Teaching Drones On The Fly: Can Emotional Feedback Serve as Learning Signal for Training Artificial Agents? In AAAI'22-Workshop on Interactive Machine Learning, Feb. 28 - March 1, 2022, Virtual Event, Canada.