Human Activity Recognition Using IR-UWB Radar: A Lightweight Transformer Approach

In this study, we introduce MobileViTX, an enhanced MobileViT architecture for human activity recognition (HAR) in impulse radio ultrawideband (IR-UWB) radar applications. MobileViT is a lightweight Vision Transformer mainly consisting of MobileViT blocks and MobileNetv2 blocks. Modifications to the MobileNetv2 block include adding a drop path and a squeeze-and-excitation (SE) module and altering activation functions to hard-sigmoid and hard-swish. Additionally, the self-attention in the MobileViT block is transformed to possess linear complexity. These adjustments aim to accelerate inference while preserving high accuracy. We experiment with a dataset from 20 individuals performing 20 distinct actions, using fivefold cross-validation to assess our model’s performance. Results show that MobileViTX outperforms the original MobileViT and other models in both recognition rate and efficiency.

I. Introduction

Human motion recognition has gained significant attention recently due to its potential applications in surveillance, healthcare, and human–computer interaction. Impulse radio ultrawideband (IR-UWB) radar has emerged as a promising technology for capturing human motion due to its high resolution, noninvasive, low power consumption, and robustness in different environments. Numerous investigations have been conducted into human activity recognition (HAR) based on IR-UWB radar.