Home > Research > Publications & Outputs > Evolving Human Activity Classifier from Sensor ...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

Evolving Human Activity Classifier from Sensor Streams

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Evolving Human Activity Classifier from Sensor Streams. / Iglesias, Jose Antonio; Angelov, Plamen; Ledezma, Agapito et al.
Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on. IEEE, 2011. p. 139-146.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Iglesias, JA, Angelov, P, Ledezma, A & Sanchis, A 2011, Evolving Human Activity Classifier from Sensor Streams. in Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on. IEEE, pp. 139-146, IEEE , Paris, France, 11/04/11. https://doi.org/10.1109/EAIS.2011.5945921

APA

Iglesias, J. A., Angelov, P., Ledezma, A., & Sanchis, A. (2011). Evolving Human Activity Classifier from Sensor Streams. In Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on (pp. 139-146). IEEE. https://doi.org/10.1109/EAIS.2011.5945921

Vancouver

Iglesias JA, Angelov P, Ledezma A, Sanchis A. Evolving Human Activity Classifier from Sensor Streams. In Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on. IEEE. 2011. p. 139-146 doi: 10.1109/EAIS.2011.5945921

Author

Iglesias, Jose Antonio ; Angelov, Plamen ; Ledezma, Agapito et al. / Evolving Human Activity Classifier from Sensor Streams. Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on. IEEE, 2011. pp. 139-146

Bibtex

@inproceedings{b68e4ae6daa74637949a696707903b77,
title = "Evolving Human Activity Classifier from Sensor Streams",
abstract = "Human activity recognition in intelligent environments is a very important task for many applications such as assisted living or surveillance. In order to make thoseenvironments sensitive to people, it is necessary to recognize and track the activities that they perform as part of their daily routines. Most of the current approaches for recognizing human activities do not consider the changes in how a human performs a speci{\textregistered}c activity. Those approaches rely on prede{\textregistered}ned activities which are represented as static models over time.In this paper, we propose an automated approach to track and recognize daily activities from sensor streams. Any activity is represented in this research as a sequence of raw sensors data. These sequences are treated using statistical methods in order to discover activity patterns. However, these patterns changedue to the dynamic nature of human activities. Therefore, as the way to perform an activity is usually not {\textregistered}xed but it changes and evolves, we propose a human activity recognition method based on Evolving Systems.",
keywords = "Human activity recognition ",
author = "Iglesias, {Jose Antonio} and Plamen Angelov and Agapito Ledezma and Araceli Sanchis",
year = "2011",
month = apr,
doi = "10.1109/EAIS.2011.5945921",
language = "English",
isbn = "978-1-4244-9978-6",
pages = "139--146",
booktitle = "Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on",
publisher = "IEEE",
note = "IEEE ; Conference date: 11-04-2011 Through 15-04-2011",

}

RIS

TY - GEN

T1 - Evolving Human Activity Classifier from Sensor Streams

AU - Iglesias, Jose Antonio

AU - Angelov, Plamen

AU - Ledezma, Agapito

AU - Sanchis, Araceli

PY - 2011/4

Y1 - 2011/4

N2 - Human activity recognition in intelligent environments is a very important task for many applications such as assisted living or surveillance. In order to make thoseenvironments sensitive to people, it is necessary to recognize and track the activities that they perform as part of their daily routines. Most of the current approaches for recognizing human activities do not consider the changes in how a human performs a speci®c activity. Those approaches rely on prede®ned activities which are represented as static models over time.In this paper, we propose an automated approach to track and recognize daily activities from sensor streams. Any activity is represented in this research as a sequence of raw sensors data. These sequences are treated using statistical methods in order to discover activity patterns. However, these patterns changedue to the dynamic nature of human activities. Therefore, as the way to perform an activity is usually not ®xed but it changes and evolves, we propose a human activity recognition method based on Evolving Systems.

AB - Human activity recognition in intelligent environments is a very important task for many applications such as assisted living or surveillance. In order to make thoseenvironments sensitive to people, it is necessary to recognize and track the activities that they perform as part of their daily routines. Most of the current approaches for recognizing human activities do not consider the changes in how a human performs a speci®c activity. Those approaches rely on prede®ned activities which are represented as static models over time.In this paper, we propose an automated approach to track and recognize daily activities from sensor streams. Any activity is represented in this research as a sequence of raw sensors data. These sequences are treated using statistical methods in order to discover activity patterns. However, these patterns changedue to the dynamic nature of human activities. Therefore, as the way to perform an activity is usually not ®xed but it changes and evolves, we propose a human activity recognition method based on Evolving Systems.

KW - Human activity recognition

U2 - 10.1109/EAIS.2011.5945921

DO - 10.1109/EAIS.2011.5945921

M3 - Conference contribution/Paper

SN - 978-1-4244-9978-6

SP - 139

EP - 146

BT - Evolving and Adaptive Intelligent Systems (EAIS), 2011 IEEE Workshop on

PB - IEEE

T2 - IEEE

Y2 - 11 April 2011 through 15 April 2011

ER -