TY - CHAP

T1 - Emergency detection based on probabilistic modeling in AAL-environments

AU - Busch, Björn-Helge

AU - Kujath, Alexander

AU - Welge, Ralph

N1 - Conference code: 7

PY - 2010

Y1 - 2010

N2 - The actual demographic trend predicts a significant increasing percentage of elderly people in the German society until 2050. According to this trend, it must be assumed that the number of elderly persons solitarily living at home will rise as well. In this paper a human centered assistance system is tightly described and proposed as a resolve for the coherent challenges of this changes; the focus of consideration lies thereby on the statistical analysis of process data in order to derive an intelligent emergency detection based on probabilistic modeling. Using room automation events to design and train Hidden Markov Models for position tracking, complemented with the stochastically evaluation of telemedical de-vices and contactless sensor networks, the main issue is to achieve a solid, robust situation recognition mechanism. Due to the knowledge of the hidden user states or i.e. situations this approach offers the opportunity to detect emergency situa-tions and to prevent harmful aftermath for the user through interventions like emergency calls. This paper illustrates the general functionality of the proposed solution and its key features by a vivid example. In addition to security aspects relating to the health status of the patient the recognition of the activities of daily life grants further advantageous options like energy management, comfort by assistance and building security completely adapted to people requirements.

AB - The actual demographic trend predicts a significant increasing percentage of elderly people in the German society until 2050. According to this trend, it must be assumed that the number of elderly persons solitarily living at home will rise as well. In this paper a human centered assistance system is tightly described and proposed as a resolve for the coherent challenges of this changes; the focus of consideration lies thereby on the statistical analysis of process data in order to derive an intelligent emergency detection based on probabilistic modeling. Using room automation events to design and train Hidden Markov Models for position tracking, complemented with the stochastically evaluation of telemedical de-vices and contactless sensor networks, the main issue is to achieve a solid, robust situation recognition mechanism. Due to the knowledge of the hidden user states or i.e. situations this approach offers the opportunity to detect emergency situa-tions and to prevent harmful aftermath for the user through interventions like emergency calls. This paper illustrates the general functionality of the proposed solution and its key features by a vivid example. In addition to security aspects relating to the health status of the patient the recognition of the activities of daily life grants further advantageous options like energy management, comfort by assistance and building security completely adapted to people requirements.

KW - Informatics

KW - Probabilistic

KW - situation recognition

KW - Hidden Markov Models

KW - distributed sensor networks

KW - assistance systems

M3 - Article in conference proceedings

SN - 978-972-8939-30-4

SP - 127

EP - 134

BT - Proceedings of the IADIS International Conference APPLIED COMPUTING 2010

PB - International Association for the Development of Information Society

T2 - 7th IADIS International Applied Computing Conference - 2010

Y2 - 14 October 2010 through 16 October 2010

ER -