Abstract
Wi-Fi-based device-free human activity recognition has recently become a vital underpinning for various emerging applications, ranging from the Internet of Things (IoT) to Human–Computer Interaction (HCI). Although this technology has been successfully demonstrated for location-dependent sensing, it relies on sufficient data samples for large-scale sensing, which is enormously labor-intensive and time-consuming. However, in real-world applications, location-independent sensing is crucial and indispensable. Therefore, how to alleviate adverse effects on recognition accuracy caused by location variations with the limited dataset is still an open question. To address this concern, we present a location-independent human activity recognition system based on Wi-Fi named WiLiMetaSensing. Specifically, we first leverage a Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) feature representation method to focus on location-independent characteristics. Then, in order to well transfer the model across different positions with limited data samples, a metric learning-based activity recognition method is proposed. Consequently, not only the generalization ability but also the transferable capability of the model would be significantly promoted. To fully validate the feasibility of the presented approach, extensive experiments have been conducted in an office with 24 testing locations. The evaluation results demonstrate that our method can achieve more than 90% in location-independent human activity recognition accuracy. More importantly, it can adapt well to the data samples with a small number of subcarriers and a low sampling rate.
Highlights
Human Activity Recognition (HAR) has been considered as an indispensable technology in many Human–Computer Interaction (HCI) applications, such as smart home, health care, security surveillance, virtual reality, and location-based services (LBS) [1,2].Traditional human activity sensing approaches are the wearable sensor-based methods [3,4]and the camera-based methods [5,6]
We propose a device-free location-independent human activity recognition system named WiLiMetaSensing, which is based on meta learning to enable few-shot learning sensing
The workflow of the location-independent human activity recognition system WiLiMetaSensing is shown in Figure 10, which mainly consists of four parts, including data collection, data preprocessing, feature representation, and model training/testing
Summary
Human Activity Recognition (HAR) has been considered as an indispensable technology in many Human–Computer Interaction (HCI) applications, such as smart home, health care, security surveillance, virtual reality, and location-based services (LBS) [1,2]. The solutions fall into the following four categories: (1) Generate virtual data samples for each location [24], (2) Separate the activity signal from the background [25,26], (3) Extract domain-independent features [27], and (4) Domain adaptation and transfer learning. This work aims to realize device-free location-independent human activity recognition using as few samples as possible. It means that the model trained with the source domain data samples can perform well on the target domain with only very few data samples. We propose a device-free location-independent human activity recognition system named WiLiMetaSensing, which is based on meta learning to enable few-shot learning sensing. Experiments show that WiLiMetaSensing achieves satisfying results with robust performance in a variety of situations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
