Computational state space models for activity and intention recognition. A feasibility study

F Krüger, M Nyolt, K Yordanova, A Hein, T Kirste - PloS one, 2014 - journals.plos.org
Background Computational state space models (CSSMs) enable the knowledge-based
construction of Bayesian filters for recognizing intentions and reconstructing activities of …

[PDF][PDF] Activity, context, and plan recognition with computational causal behaviour models

F Krüger - 2016 - core.ac.uk
As computers are becoming more and more a part of our everyday life, the vision of Mark
Weiser about ubiquitous computing becomes true. One of the core tasks of such devices is …

Analysing cooking behaviour in home settings: Towards health monitoring

K Yordanova, S Lüdtke, S Whitehouse, F Krüger… - Sensors, 2019 - mdpi.com
Wellbeing is often affected by health-related conditions. Among them are nutrition-related
health conditions, which can significantly decrease the quality of life. We envision a system …

Combining symbolic reasoning and deep learning for human activity recognition

FM Rueda, S Lüdtke, M Schröder… - 2019 IEEE …, 2019 - ieeexplore.ieee.org
Activity recognition (AR) plays an important role in situation aware systems. Recently, deep
learning approaches have shown promising results in the field of AR. However, their …

Modeling agents and their environment in multi-level-DEVS

A Steiniger, F Krüger… - Proceedings of the 2012 …, 2012 - ieeexplore.ieee.org
Environments play an important role in multi-agent systems. They present the context agents
operate in. When testing multi-agent systems by simulation, the environment and partly …

[HTML][HTML] Machine learning on large databases: Transforming hidden markov models to sql statements

D Marten, A Heuer - Open Journal of Databases (OJDB), 2017 - ronpub.com
Machine Learning is a research field with substantial relevance for many applications in
different areas. Because of technical improvements in sensor technology, its value for real …

A process for systematic development of symbolic models for activity recognition

K Yordanova, T Kirste - ACM Transactions on Interactive Intelligent …, 2015 - dl.acm.org
Several emerging approaches to activity recognition (AR) combine symbolic representation
of user actions with probabilistic elements for reasoning under uncertainty. These …

Situation model for situation-aware assistance of dementia patients in outdoor mobility

K Yordanova, P Koldrack, C Heine… - Journal of …, 2017 - content.iospress.com
Background: Dementia impairs spatial orientation and route planning, thus often affecting
the patient's ability to move outdoors and maintain social activities. Situation-aware …

What's cooking and why? Behaviour recognition during unscripted cooking tasks for health monitoring

K Yordanova, S Whitehouse… - 2017 IEEE …, 2017 - ieeexplore.ieee.org
Nutrition related health conditions can seriously decrease quality of life; a system able to
monitor the kitchen activities and eating behaviour of patients could provide clinicians with …

Supporting situation awareness of dementia patients in outdoor environments

P Koldrack, R Henkel, F Krüger… - 2015 9th International …, 2015 - ieeexplore.ieee.org
Engagement in cognitively stimulating activities is today among the most effective measures
against the decline of cognitive abilities due to dementing disorders. Outdoor and social …