SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing

TL;DR

SenseFi introduces a comprehensive benchmark and open-source library for evaluating deep learning models in WiFi human sensing, facilitating progress and standardization in this emerging field.

Contribution

This paper presents the first open-source benchmark and library for deep learning-based WiFi sensing, enabling systematic comparison and advancement in the field.

Findings

Deep learning models vary in recognition accuracy and computational complexity.

Transferability and unsupervised learning adaptability are key factors in model performance.

Extensive experiments provide insights into model design and training for real-world WiFi sensing applications.

Abstract

WiFi sensing has been evolving rapidly in recent years. Empowered by propagation models and deep learning methods, many challenging applications are realized such as WiFi-based human activity recognition and gesture recognition. However, in contrast to deep learning for visual recognition and natural language processing, no sufficiently comprehensive public benchmark exists. In this paper, we review the recent progress on deep learning enabled WiFi sensing, and then propose a benchmark, SenseFi, to study the effectiveness of various deep learning models for WiFi sensing. These advanced models are compared in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, feature transferability, and adaptability of unsupervised learning. It is also regarded as a tutorial for deep learning based WiFi sensing, starting from CSI hardware platform to sensing algorithms. The extensive experiments provide us with experiences in deep model design, learning strategy skills and training techniques for real-world applications. To the best of our knowledge, this is the first benchmark with an open-source library for deep learning in WiFi sensing research. The benchmark codes are available at https://github.com/xyanchen/WiFi-CSI-Sensing-Benchmark.