Learning to Sense: Deep Learning for Wireless Sensing with Less Training Efforts
Authors:
- Jie WangJWJie Wang
- Qinhua GaoQGQinhua Gao
- Xiaorui MaXMXiaorui Ma
- Yunong ZhaoYZYunong Zhao
- Yuguang FangYFYuguang Fang
- 22 April 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. 27 (3) , 156-162
Abstract
Wireless sensing is an emerging technique which empowers wireless devices with additional sensing ability, that is, the ability to sense the target location, activity, gesture, vital signs, etc., in a device-free manner by analyzing the influence of the target on surrounding wireless signals. Benefiting from its excellent feature extraction and analysis capability, deep learning has emerged as a promising tool to realize wireless sensing. However, the labor intensive training efforts on collecting training samples or retraining a trained system limit its practical application. This article attempts to provide an integrated view on this field and discuss the feasibility of leveraging some new types of deep learning networks to accomplish wireless sensing tasks with less training efforts. Specifically, we first introduce the deep learning based wireless sensing framework, review the methods to construct radio images, and summarize different types of deep learning networks. Then, we focus on new types of deep learning networks which could reduce training efforts from two perspectives, that is, alleviating the efforts of retraining the system in a new scenario by learning a universal similarity evaluation ability utilizing a deep similarity evaluation networks, and reducing the efforts of collecting samples by generating virtual training samples using deep generative adversarial networks. Then, we elaborate existing challenges and forecast future research directions. Finally, we carry out experiments to evaluate the effectiveness of the introduced schemes using wireless gesture recognition as the case study.Keywords
This publication has 11 references indexed in Scilit:
- Towards Environment Independent Device Free Human Activity Recognition2018
- Structure-Preserved Unsupervised Domain AdaptationIEEE Transactions on Knowledge and Data Engineering, 2018
- Wi-Fi CSI-Based Behavior Recognition: From Signals and Actions to ActivitiesIEEE Communications Magazine, 2018
- Exploring Training Options for RF Sensing Using CSIIEEE Communications Magazine, 2018
- Device-Free Wireless Sensing: Challenges, Opportunities, and ApplicationsIEEE Network, 2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- CSI-Based Device-Free Wireless Localization and Activity Recognition Using Radio Image FeaturesIEEE Transactions on Vehicular Technology, 2017
- Device-Free Wireless Localization and Activity Recognition: A Deep Learning ApproachIEEE Transactions on Vehicular Technology, 2016
- Human respiration detection with commodity wifi devices2016
- Sensorless sensing with WiFiTsinghua Science and Technology, 2015