Unobtrusive human localization and activity recognition for supporting independent living of the elderly

Files

RA_hdl_110034.pdf (219.19 KB)
  (Restricted Access)

Date

2016

Authors

Ruan, W.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the International Conference on Pervasive Computing and Communication Workshops, 2016, pp.1-3

Statement of Responsibility

Wenjie Ruan

Conference Name

18th Annual PhD Forum on Pervasive Computing and Communication (PerCom PhD) (14 Mar 2016 - 18 Mar 2016 : Sydney, NSW)

Abstract

Indoor localization and activity recognition is a fundamental research topic for a wide range of important applications such as fall detection of elderly people. It usually requires an intelligent environment to successfully infer where and what a person is doing. However, many of the existing techniques on localization and activity recognition rely heavily on people’s involvement such as wearing battery-powered sensors, which might not be practical in real-world situations (e.g., people may forget to wear sensors). In this project, we propose a device-free localization and activity recognition approach using passive RFID tags. It is achieved by learning how the Received Signal Strength Indicator (RSSI) from the passive RFID tag array is distributed when a person performs different activities in different locations. After activity patterns are discovered for a particular individual, we will also develop a context-aware, common-sense based activity reasoning engine that assists applications to make appropriate interpretation of detected activities. We believe the proposed system has the potential to better support the independent living of elderly people considering the continuously increased aging population.

School/Discipline

Dissertation Note

Provenance

Description

PhD Forum session

Access Status

Rights

© 2016 IEEE

License

Call number

Persistent link to this record