Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns

TL;DR

This paper introduces a transformer-based neural network approach for Wi-Fi motion recognition that maintains high accuracy under variable traffic-induced sampling rates, addressing a key limitation of existing systems.

Contribution

It proposes a novel sampling rate versatile neural network with dynamic augmentation, improving Wi-Fi sensing robustness across diverse traffic patterns.

Findings

Achieved high accuracy and stability across different sampling rates.

Reduced accuracy variance significantly compared to baseline models.

Validated on both self-collected and public datasets.

Abstract

Wi-Fi sensing detects human motions and activities by analysing the channel state information (CSI) derived from Wi-Fi transmissions. However, the impact of variable transmission traffic, which dictates the effective sampling rate and interval, is often overlooked. Existing Wi-Fi sensing systems are trained with fixed input size and sampling rate, which suffer from poor sampling rate generalisation. This paper proposes a novel Wi-Fi sensing approach for motion recognition applications, e.g., gesture and activity recognition, under variable traffic patterns. A sampling rate versatile neural network (SRV-NN) based on the transformer is proposed to efficiently handle variable input-sized sensing signals. A dynamic sampling rate augmentation is employed for variable sampling rates and intervals. To validate our approach, we have carried out extensive experimental evaluation, using two self-collected datasets, namely SRV activity and SRV gesture, as well as two publicly available datasets. Our method demonstrated exceptional performance and stability under variable sampling rates, with substantial improvements in average accuracy compared to baseline models without augmentation. The proposed approach significantly enhances stability by greatly reducing accuracy variance across different sampling rates.