High Performance Activity Recognition Framework for Ambient Assisted Living in the Home Network Environment

Konlakorn WONGPATIKASEREE; Azman Osman LIM; Mitsuru IKEDA; Yasuo TAN

doi:10.1587/transcom.E97.B.1766

High Performance Activity Recognition Framework for Ambient Assisted Living in the Home Network Environment

Konlakorn WONGPATIKASEREE, Azman Osman LIM, Mitsuru IKEDA, Yasuo TAN

Full Text Views

0

Cite this

Summary :

Activity recognition has recently been playing an important role in several research domains, especially within the healthcare system. It is important for physicians to know what their patients do in daily life. Nevertheless, existing research work has failed to adequately identify human activity because of the variety of human lifestyles. To address this shortcoming, we propose the high performance activity recognition framework by introducing a new user context and activity location in the activity log (AL²). In this paper, the user's context is comprised by context-aware infrastructure and human posture. We propose a context sensor network to collect information from the surrounding home environment. We also propose a range-based algorithm to classify human posture for combination with the traditional user's context. For recognition process, ontology-based activity recognition (OBAR) is developed. The ontology concept is the main approach that uses to define the semantic information and model human activity in OBAR. We also introduce a new activity log ontology, called AL² for investigating activities that occur at the user's location at that time. Through experimental studies, the results reveal that the proposed context-aware activity recognition engine architecture can achieve an average accuracy of 96.60%.

Publication: IEICE TRANSACTIONS on Communications Vol.E97-B No.9 pp.1766-1778

Publication Date: 2014/09/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E97.B.1766

Type of Manuscript: Special Section PAPER (Special Section on Ambient Intelligence and Sensor Networks)

Category

Authors

Konlakorn WONGPATIKASEREE
  Japan Advanced Institute of Science and Technology (JAIST)
Azman Osman LIM
  Japan Advanced Institute of Science and Technology (JAIST)
Mitsuru IKEDA
  Japan Advanced Institute of Science and Technology (JAIST)
Yasuo TAN
  Japan Advanced Institute of Science and Technology (JAIST)

Keyword

activity recognition, context sensor network, human posture, range-based algorithm, ontology-based activity recognition, activity's location in activity log

Cite this

Copy

Konlakorn WONGPATIKASEREE, Azman Osman LIM, Mitsuru IKEDA, Yasuo TAN, "High Performance Activity Recognition Framework for Ambient Assisted Living in the Home Network Environment" in IEICE TRANSACTIONS on Communications, vol. E97-B, no. 9, pp. 1766-1778, September 2014, doi: 10.1587/transcom.E97.B.1766.
Abstract: Activity recognition has recently been playing an important role in several research domains, especially within the healthcare system. It is important for physicians to know what their patients do in daily life. Nevertheless, existing research work has failed to adequately identify human activity because of the variety of human lifestyles. To address this shortcoming, we propose the high performance activity recognition framework by introducing a new user context and activity location in the activity log (AL²). In this paper, the user's context is comprised by context-aware infrastructure and human posture. We propose a context sensor network to collect information from the surrounding home environment. We also propose a range-based algorithm to classify human posture for combination with the traditional user's context. For recognition process, ontology-based activity recognition (OBAR) is developed. The ontology concept is the main approach that uses to define the semantic information and model human activity in OBAR. We also introduce a new activity log ontology, called AL² for investigating activities that occur at the user's location at that time. Through experimental studies, the results reveal that the proposed context-aware activity recognition engine architecture can achieve an average accuracy of 96.60%.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.E97.B.1766/_p

Copy

@ARTICLE{e97-b_9_1766,
author={Konlakorn WONGPATIKASEREE, Azman Osman LIM, Mitsuru IKEDA, Yasuo TAN, },
journal={IEICE TRANSACTIONS on Communications},
title={High Performance Activity Recognition Framework for Ambient Assisted Living in the Home Network Environment},
year={2014},
volume={E97-B},
number={9},
pages={1766-1778},
abstract={Activity recognition has recently been playing an important role in several research domains, especially within the healthcare system. It is important for physicians to know what their patients do in daily life. Nevertheless, existing research work has failed to adequately identify human activity because of the variety of human lifestyles. To address this shortcoming, we propose the high performance activity recognition framework by introducing a new user context and activity location in the activity log (AL²). In this paper, the user's context is comprised by context-aware infrastructure and human posture. We propose a context sensor network to collect information from the surrounding home environment. We also propose a range-based algorithm to classify human posture for combination with the traditional user's context. For recognition process, ontology-based activity recognition (OBAR) is developed. The ontology concept is the main approach that uses to define the semantic information and model human activity in OBAR. We also introduce a new activity log ontology, called AL² for investigating activities that occur at the user's location at that time. Through experimental studies, the results reveal that the proposed context-aware activity recognition engine architecture can achieve an average accuracy of 96.60%.},
keywords={},
doi={10.1587/transcom.E97.B.1766},
ISSN={1745-1345},
month={September},}

Copy

TY - JOUR
TI - High Performance Activity Recognition Framework for Ambient Assisted Living in the Home Network Environment
T2 - IEICE TRANSACTIONS on Communications
SP - 1766
EP - 1778
AU - Konlakorn WONGPATIKASEREE
AU - Azman Osman LIM
AU - Mitsuru IKEDA
AU - Yasuo TAN
PY - 2014
DO - 10.1587/transcom.E97.B.1766
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E97-B
IS - 9
JA - IEICE TRANSACTIONS on Communications
Y1 - September 2014
AB - Activity recognition has recently been playing an important role in several research domains, especially within the healthcare system. It is important for physicians to know what their patients do in daily life. Nevertheless, existing research work has failed to adequately identify human activity because of the variety of human lifestyles. To address this shortcoming, we propose the high performance activity recognition framework by introducing a new user context and activity location in the activity log (AL²). In this paper, the user's context is comprised by context-aware infrastructure and human posture. We propose a context sensor network to collect information from the surrounding home environment. We also propose a range-based algorithm to classify human posture for combination with the traditional user's context. For recognition process, ontology-based activity recognition (OBAR) is developed. The ontology concept is the main approach that uses to define the semantic information and model human activity in OBAR. We also introduce a new activity log ontology, called AL² for investigating activities that occur at the user's location at that time. Through experimental studies, the results reveal that the proposed context-aware activity recognition engine architecture can achieve an average accuracy of 96.60%.
ER -