Qualitative Action Recognition by Wireless Radio Signals in Human-Machine Systems

TL;DR

This paper introduces WiQ, a radio signal-based system for qualitative assessment of human actions, particularly driving behaviors, achieving high accuracy in differentiating body statuses and driver identification.

Contribution

The paper presents WiQ, a novel system that uses radio signals and deep learning to assess action quality and differentiate behaviors in human-machine systems.

Findings

Achieves 97% accuracy in differentiating triple body statuses.

Attains 88% average accuracy in driver identification among 15 individuals.

Demonstrates fine-grained action characterization using radio signals.

Abstract

Human-machine systems required a deep understanding of human behaviors. Most existing research on action recognition has focused on discriminating between different actions, however, the quality of executing an action has received little attention thus far. In this paper, we study the quality assessment of driving behaviors and present WiQ, a system to assess the quality of actions based on radio signals. This system includes three key components, a deep neural network based learning engine to extract the quality information from the changes of signal strength, a gradient based method to detect the signal boundary for an individual action, and an activitybased fusion policy to improve the recognition performance in a noisy environment. By using the quality information, WiQ can differentiate a triple body status with an accuracy of 97%, while for identification among 15 drivers, the average accuracy is 88%. Our results show that, via dedicated analysis of radio signals, a fine-grained action characterization can be achieved, which can facilitate a large variety of applications, such as smart driving assistants.