@inproceedings{1e887e8eeee8498a95afb0277a7b6021,
title = "Deep neural network for RFID-based activity recognition",
abstract = "We propose a Deep Neural Network (DNN) structure for RFID-based activity recognition. RFID data collected from several reader antennas with overlapping coverage have potential spatiotemporal relationships that can be used for object tracking. We augmented the standard fully-connected DNN structure with additional pooling layers to extract the most representative features. For model training and testing, we used RFID data from 12 tagged objects collected during 25 actual trauma resuscitations. Our results showed 76% recognition micro-accuracy for 7 resuscitation activities and 85% average micro-accuracy for 5 resuscitation phases, which is similar to existing system that, however, require the user to wear an RFID antenna.",
keywords = "Activity recognition, Deep neural network, Max pooling, RFID",
author = "Xinyu Li and Yanyi Zhang and Mengzhu Li and Ivan Marsic and Yang, {Jae Won} and Burd, {Randall S.}",
note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 8th Wireless of the Students, by the Students, and for the Students Workshop, S3 ; Conference date: 03-10-2016 Through 07-10-2016",
year = "2016",
month = oct,
day = "3",
doi = "10.1145/2987354.2987355",
language = "English (US)",
series = "Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM",
publisher = "Association for Computing Machinery",
pages = "24--26",
booktitle = "Proceedings of the 8th Wireless of the Students, by the Students, and for the Students Workshop, S3",
}