Servicenavigation

Project Details

Back

Projekt Print View

BehavE: Behaviour Understanding through Situation Models for Situation-aware AssistancE

Subject Area Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
Term from 2019 to 2024
Project identifier Deutsche Forschungsgemeinschaft (DFG) - Project number 433339426
 
Final Report Year 2024

Final Report Abstract

A situation model (SM) is a semantic structure representing the relevant elements in a given domain (these are actions, objects, locations, properties of objects, abstraction of objects) and the corresponding causal, spatial, functional, and abstraction relations between the elements. Situation models allow representing domain knowledge about persons in a structured and consolidated manner. These models are later used for reasoning about the person’s behaviour, needs and assistance strategies. Currently, situation models are either built manually or when generated automatically, only a few information sources are used. To address this problem, this project aimed at developing a generalised methodology for generating situation models from various heterogenous sources. This methodology enables the learning of models for different problem domains. More precisely, it addresss the following problems: (1) automatically extracting the domain elements and semantics from heterogenous sources; (2) automatically consolidating the heterogenous knowledge into a unified situation model; (3) automatically optimising the learned model based on observed user preferences; (4) developing an evaluation methodology for situation models for real world problems. To achieve that, it combines existing and novel methods that address different problems of knowledge extraction and model learning from heterogenous sources. They include supervised and unsupervised techniques for semantics extraction and relations discovery; making use of existing structured knowledge to improve the discovered semantics, optimisation techniques for adjusting the situation model, as well as various machine learning techniques for learning the model heuristics. Given a textual input and existing structured knowledge bases, the methodology generates a situation model based on which computational state space models (CSSMs) for activity recognition are generated. By additionally providing sensor data and corresponding annotations, the SM can be extended with actions’ durations (as distributions). As the generated models are relatively general, one problem with activity recognition is that the model cannot correctly recognise the executed activities due to too many options. To address this problem, an optimisation phase follows where the action weights are adjusted based on existing plan traces and sensor data. To evaluate the approach, the learned models are applied to an activity recognition problem from the everyday life of elderly domain. The proposed approach allows us to reduce the need of expert knowledge and manual development by replacing it with automatically extracted models. It reduces the time and resources needed for building rich high quality situation models and for developing any system that relies on domain knowledge in order to reason about the solution of a given problem.

Publications

 
 

Additional Information

© 2026 DFG Disclaimer / Copyright / Privacy Policy

Textvergrößerung und Kontrastanpassung