试验台
计算机科学
特征(语言学)
无线
人工智能
深度学习
再培训
对抗制
机器学习
计算机网络
电信
语言学
哲学
业务
国际贸易
作者
Jie Wang,Yunong Zhao,Xiaorui Ma,Qinghua Gao,Miao Pan,Hongyu Wang
出处
期刊:IEEE Transactions on Vehicular Technology
[Institute of Electrical and Electronics Engineers]
日期:2020-05-01
卷期号:69 (5): 5416-5425
被引量:20
标识
DOI:10.1109/tvt.2020.2977973
摘要
Device-free activity recognition (DFAR) is an emerging technique which could infer human activities by analyzing his/her influence on surrounding wireless signals. It may empower wireless networks with the additional sensing ability. Existing studies have achieved reasonable accuracy in a pre-trained scenario. However, due to the feature shift incurred by different radio environments, a system typically achieves poor performance in a new scenario. Generally, retraining a system is laborious or even impossible in practical applications, since we have very few number of or even no labeled training samples in a new scenario. Therefore, how to realize cross-scenario DFAR in an unsupervised manner becomes an urgent problem to solve. To address this challenge, in this paper, we develop a deep learning network to guide the sample features of the target scenario shift to those of the source scenario without using any label information of the target scenario. Specifically, we develop a maximum-minimum adversarial approach to move the target features to the distribution of the source features, and design a center alignment strategy to further shift the target features to the distribution center. Benefit from the shifted features, extensive experimental results on a mmWave testbed demonstrate the effectiveness of the developed framework.
科研通智能强力驱动
Strongly Powered by AbleSci AI