Activity recognition in plant: Investigation on actions for preventing human error

Huiquan Zhang, Wonjung Kim, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Research on recognizing human activities has attracted much interest in pervasive sensing and machine learning. Usually, plants needs to know all information in relation to activities for the sake of security that require all the actions must be observable and recognizable. The existing learning-based approaches are not sufficient to capture the characteristics of human activity efficiently because they don't process the dimensional information enough. This paper describes a novel approach to recognize activity and prevent human error using monitoring data from RFID-based systems. Different from many approaches that analyz the human activity from event sequence first, the proposed approach start it from dimensional information, and the model can be applied to track activities in plants routine and more suitable for discovering the changing of activity. Finally, we prove our approach on data collected in simulation plant environment.

Original languageEnglish
Title of host publication21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings
PublisherFraunhofer-Verlag
ISBN (Print)9783839602935
Publication statusPublished - 2011
Event21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Stuttgart
Duration: 2011 Jul 312011 Aug 4

Other

Other21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011
CityStuttgart
Period11/7/3111/8/4

Fingerprint

Radio frequency identification (RFID)
Learning systems
Monitoring

Keywords

  • Data mining
  • Human error
  • Recognition
  • RFID

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

Zhang, H., Kim, W., & Yoshie, O. (2011). Activity recognition in plant: Investigation on actions for preventing human error. In 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings Fraunhofer-Verlag.

Activity recognition in plant : Investigation on actions for preventing human error. / Zhang, Huiquan; Kim, Wonjung; Yoshie, Osamu.

21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings. Fraunhofer-Verlag, 2011.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, H, Kim, W & Yoshie, O 2011, Activity recognition in plant: Investigation on actions for preventing human error. in 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings. Fraunhofer-Verlag, 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011, Stuttgart, 11/7/31.
Zhang H, Kim W, Yoshie O. Activity recognition in plant: Investigation on actions for preventing human error. In 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings. Fraunhofer-Verlag. 2011
Zhang, Huiquan ; Kim, Wonjung ; Yoshie, Osamu. / Activity recognition in plant : Investigation on actions for preventing human error. 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings. Fraunhofer-Verlag, 2011.
@inproceedings{0774e6d8468a4913a2deff1bbcff1a50,
title = "Activity recognition in plant: Investigation on actions for preventing human error",
abstract = "Research on recognizing human activities has attracted much interest in pervasive sensing and machine learning. Usually, plants needs to know all information in relation to activities for the sake of security that require all the actions must be observable and recognizable. The existing learning-based approaches are not sufficient to capture the characteristics of human activity efficiently because they don't process the dimensional information enough. This paper describes a novel approach to recognize activity and prevent human error using monitoring data from RFID-based systems. Different from many approaches that analyz the human activity from event sequence first, the proposed approach start it from dimensional information, and the model can be applied to track activities in plants routine and more suitable for discovering the changing of activity. Finally, we prove our approach on data collected in simulation plant environment.",
keywords = "Data mining, Human error, Recognition, RFID",
author = "Huiquan Zhang and Wonjung Kim and Osamu Yoshie",
year = "2011",
language = "English",
isbn = "9783839602935",
booktitle = "21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings",
publisher = "Fraunhofer-Verlag",

}

TY - GEN

T1 - Activity recognition in plant

T2 - Investigation on actions for preventing human error

AU - Zhang, Huiquan

AU - Kim, Wonjung

AU - Yoshie, Osamu

PY - 2011

Y1 - 2011

N2 - Research on recognizing human activities has attracted much interest in pervasive sensing and machine learning. Usually, plants needs to know all information in relation to activities for the sake of security that require all the actions must be observable and recognizable. The existing learning-based approaches are not sufficient to capture the characteristics of human activity efficiently because they don't process the dimensional information enough. This paper describes a novel approach to recognize activity and prevent human error using monitoring data from RFID-based systems. Different from many approaches that analyz the human activity from event sequence first, the proposed approach start it from dimensional information, and the model can be applied to track activities in plants routine and more suitable for discovering the changing of activity. Finally, we prove our approach on data collected in simulation plant environment.

AB - Research on recognizing human activities has attracted much interest in pervasive sensing and machine learning. Usually, plants needs to know all information in relation to activities for the sake of security that require all the actions must be observable and recognizable. The existing learning-based approaches are not sufficient to capture the characteristics of human activity efficiently because they don't process the dimensional information enough. This paper describes a novel approach to recognize activity and prevent human error using monitoring data from RFID-based systems. Different from many approaches that analyz the human activity from event sequence first, the proposed approach start it from dimensional information, and the model can be applied to track activities in plants routine and more suitable for discovering the changing of activity. Finally, we prove our approach on data collected in simulation plant environment.

KW - Data mining

KW - Human error

KW - Recognition

KW - RFID

UR - http://www.scopus.com/inward/record.url?scp=84923521965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923521965&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84923521965

SN - 9783839602935

BT - 21st International Conference on Production Research: Innovation in Product and Production, ICPR 2011 - Conference Proceedings

PB - Fraunhofer-Verlag

ER -