Evaluation of Wearable Sensor Tag Data Segmentation Approaches for Real Time Activity Classification in Elderly

Roberto Shinmoto Torres; Damith Ranasinghe; Qinfeng Shi

Mobile and Ubiquitous Systems: Computing, Networking, and Services. 10th International Conference, MOBIQUITOUS 2013, Tokyo, Japan, December 2-4, 2013, Revised Selected Papers

Research Article

Evaluation of Wearable Sensor Tag Data Segmentation Approaches for Real Time Activity Classification in Elderly

Download

422 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-11569-6_30,
    author={Roberto Shinmoto Torres and Damith Ranasinghe and Qinfeng Shi},
    title={Evaluation of Wearable Sensor Tag Data Segmentation Approaches for Real Time Activity Classification in Elderly},
    proceedings={Mobile and Ubiquitous Systems: Computing, Networking, and Services. 10th International Conference, MOBIQUITOUS 2013, Tokyo, Japan, December 2-4, 2013,  Revised Selected Papers},
    proceedings_a={MOBIQUITOUS},
    year={2014},
    month={12},
    keywords={Conditional random fields RFID Feature extraction},
    doi={10.1007/978-3-319-11569-6_30}
}

Roberto Shinmoto Torres
Damith Ranasinghe
Qinfeng Shi
Year: 2014
Evaluation of Wearable Sensor Tag Data Segmentation Approaches for Real Time Activity Classification in Elderly
MOBIQUITOUS
Springer
DOI: 10.1007/978-3-319-11569-6_30

Roberto Shinmoto Torres¹^,*, Damith Ranasinghe¹^,*, Qinfeng Shi¹^,*

1: The University of Adelaide South Australia

*Contact email: roberto.shinmototorres@adelaide.edu.au, damith.ranasinghe@adelaide.edu.au, javen.shi@adelaide.edu.au

Abstract

The development of human activity monitoring has allowed the creation of multiple applications, among them is the recognition of high falls risk activities of older people for the mitigation of falls occurrences. In this study, we apply a graphical model based classification technique (conditional random field) to evaluate various sliding window based techniques for the real time prediction of activities in older subjects wearing a passive (batteryless) sensor enabled RFID tag. The system achieved maximum overall real time activity prediction accuracy of using a time weighted windowing technique to aggregate contextual information to input sensor data.

Keywords: Conditional random fields RFID Feature extraction

Published: 2014-12-10

: http://dx.doi.org/10.1007/978-3-319-11569-6_30