CoMSA²t

The Junior Research Group “Cognitive Methods for Situation-Aware Assistive Systems”, or CoMSA²t, is a research group at the University of Rostock. The group is associated with the Department of Computer Science and the Department of Visual & Analytic Computing. Its goal is to develop new computational methods for situation-aware assistance and to investigate their application in real world problems ranging from supporting people with cognitive and physical impairments and measuring healthy aging, to supporting students in interactively learning theoretical and practical material.

On the methodological level, the group’s research topics include the following areas:

  • automated knowledge acquisition from heterogenous sources, such as textual data, sensors, audio and video data;
  • behaviour analysis based on computational models and user observations in the form of sensor, audio, video or textual data;
  • computational models for assisting the user based on the detected situation.

The group was founded in September 2019 and I am its group leader.

Group-related publications

2019

  • Kristina Y. Yordanova, Burcu Demiray, Matthias R. Mehl, Mike Martin. Automatic Detection of Everyday Social Behaviours and Environments from Verbatim Transcripts of Daily Conversations. In Proceedings of IEEE International Conference on Pervasive Computing and Communications. Kyoto, Japan. 2019. [full text]
  • David Schindler, Kristina Yordanova, Frank Krüger. An annotation scheme for references to research artefacts in scientific publications. Workshops Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom Workshops). Kyoto, Japan. 2019. [full text]
  • Kristina Yordanova. Challenges Providing Ground Truth for Pervasive Healthcare Systems. In IEEE Pervasive Computing 18(2):100-104. 2019 [full text]
  • Kristina Yordanova, Stefan Lüdtke, Samuel Whitehouse, Frank Krüger, Adeline Paiement, Majid Mirmehdi, Ian Craddock, Thomas Kirste. Analysing Cooking Behaviour in Home Settings: Towards Health Monitoring. In Sensors, 2019 [full text]

2018

  • Kristina Yordanova. Extracting Planning Operators from Instructional Texts for Behaviour Interpretation. In German Conference on Artificial Intelligence, Berlin, Germany, 2018. [full text]
  • Samuel Whitehouse, Kristina Yordanova, Stefan Lüdtke, Adeline Paiement, Majid Mirmehdi. Evaluation of cupboard door sensors for improving activity recognition in the kitchen. In Workshops Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom Workshops), Athens, Greece, 2018. [full text]
  • Kristina Yordanova and Frank Krüger. Creating and Exploring Semantic Annotation for Behaviour Analysis. In Sensors, 2018 [full text]
  • Emma L. Tonkin,  Alison Burrows, Przemysław R. Woznowski, Pawel Laskowski, Kristina Y. Yordanova, Niall Twomey, Ian J Craddock. Talk, Text, Tag? Understanding Self-Annotation of Smart Home Data from a User’s Perspective. In Sensors, 2018 [full text]

2017

  • Kristina Yordanova, Carlos Monserrat, David Nieves, José Hernández-Orallo. Knowledge Extraction from Task Narratives. In Proceedings of 4th International Workshop on Sensor-based Activity Recognition and Interaction, Rostock, Germany, 2017 [full text]
  • Kristina Yordanova. Automatic Generation of Situation Models for Plan Recognition Problems. In Proceedings of Recent Advances in Natural Language Processing, Varna, Bulgaria, 2017 [full text]
  • Kristina Yordanova. A Simple Model for Improving the Performance of the Stanford Parser for Action Detection in Textual Instructions. In Proceedings of Recent Advances in Natural Language Processing, Varna, Bulgaria, 2017 [full text]
  • Przemyslaw Woznowski, Emma Tonkin, Pawel Laskowski, Niall Twomey, Kristina Yordanova, Alison Burrow. Talk, text or tag? The development of a self-annotation app for activity recognition in smart environments.  In Proceedings of the 1st International Workshop on Annotation of useR Data for UbiquitOUs Systems (ARDUOUS), PerCom 2017, Hawaii, USA, 2017 [full text]
  • Kristina Yordanova. TextToHBM: A Generalised Approach to Learning Models of Human Behaviour for Activity Recognition from Textual Instructions.  In AAAI Workshop Proceedings (PAIR 2017), 2017 [full text]
  • Kristina Yordanova, Samuel Whitehouse, Adeline Paiement, Majid Mirmehdi, Thomas Kirste, Ian Craddock. What’s cooking and Why? Behaviour Recognition during Unscripted Cooking Tasks for Health Monitoring.  In Companion Proceedings of PerCom 2017 (Work in Progress Session), Hawaii, USA, 2017. Best work in progress paper award [full text]