期刊
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
卷 65, 期 5, 页码 2764-2768出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAP.2017.2677918
关键词
Convolutional neural network (CNN); deep learning; human activity classification; joint time-frequency transform; on-body channel
资金
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1609371] Funding Source: National Science Foundation
We propose to classify human activities based on transmission coefficient (S-21) and reflection coefficient (S-11) of on-body antennas with deep convolutional neural networks (DCNNs). It is shown that spectrograms of S-21 and S-11 exhibit unique time-varying signatures for different body motion activities that can be used for classification purposes. DCNN, a deep learning approach, is applied to spectrograms to learn the necessary features and classification boundaries. It is found that DCNN can achieve classification accuracies of 98.8% using S-21 and 97.1% using S-11. The effects of operating frequency and antenna location on the accuracy have been investigated.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据