"Deep learning for RFID-based activity recognition" by Xinyu Li, Yanyi Zhang et al.
 

Deep learning for RFID-based activity recognition

Document Type

Conference Proceeding

Publication Date

11-14-2016

Journal

Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems, SenSys 2016

DOI

10.1145/2994551.2994569

Keywords

Activity recognition; Convolutional neural network.; Deep learning; Passive RFID; Process phase detection

Abstract

© 2016 Copyright held by the owner/author(s). We present a system for activity recognition from passive RFID data using a deep convolutional neural network. We directly feed the RFID data into a deep convolutional neural network for activity recognition instead of selecting features and using a cascade structure that first detects object use from RFID data followed by predicting the activity. Because our system treats activity recognition as a multi-class classification problem, it is scalable for applications with large number of activity classes. We tested our system using RFID data collected in a trauma room, including 14 hours of RFID data from 16 actual trauma resuscitations. Our system outperformed existing systems developed for activity recognition and achieved similar performance with process-phase detection as systems that require wearable sensors or manually-generated input. We also analyzed the strengths and limitations of our current deep learning architecture for activity recognition from RFID data.

This document is currently not available here.

Plum Print visual indicator of research metrics
PlumX Metrics
  • Citations
    • Citation Indexes: 120
  • Usage
    • Abstract Views: 34
  • Captures
    • Readers: 125
see details

Share

COinS