Abstract
Wi-Fi-based human activity recognition is emerging as a crucial supporting technology for various applications. Although great success has been achieved for location-dependent recognition tasks, it depends on adequate data collection, which is particularly laborious and time-consuming, being impractical for actual application scenarios. Therefore, mitigating the adverse impact on performance due to location variations with the restricted data samples is still a challenging issue. In this paper, we provide a location-independent human activity recognition approach. Specifically, aiming to adapt the model well across locations with quite limited samples, we propose a Channel–Time–Subcarrier Attention Mechanism (CTS-AM) enhanced few-shot learning method that fulfills the feature representation and recognition tasks. Consequently, the generalization capability of the model is significantly improved. Extensive experiments show that more than 90% average accuracy for location-independent human activity recognition can be achieved when very few samples are available.
Highlights
Human activity recognition (HAR) is an indispensable technique that has been widely used in many applications, such as personalized home automation, health surveillance, security and protection, and entertainment [1,2]
Device-free sensing (DFS) technology effectively overcomes the above shortcomings by only utilizing radio frequency (RF) signals for sensing without being aided by additional devices carried by people [7,8,9,10]
Considering the case of insufficient samples, we propose a model inspired by few-shot learning [32,33] to achieve LI-HAR in this paper
Summary
Human activity recognition (HAR) is an indispensable technique that has been widely used in many applications, such as personalized home automation, health surveillance, security and protection, and entertainment [1,2]. Perhaps the most well-known approaches involving human activity recognition are the wearable-devices-based methods [3,4] and the camera-based methods [5,6]. Both techniques can effectively classify diverse human activities with a low false-alarm rate, they expose certain shortcomings. People have to carry the motion sensors whenever and wherever using the wearable-devices-based method to identify the activity, which is inconvenient even if these sensors are harmless to human health. The study of Wi-Fi-based HAR has increased dramatically in recent years [21,22,23,24]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
