PECL: A Heterogeneous Parallel Multi-Domain Network for Radar-Based Human Activity Recognition

TL;DR

This paper introduces PECL, a multi-domain radar neural network that effectively captures temporal dependencies for human activity recognition, achieving high accuracy with moderate complexity.

Contribution

The novel PECL network processes three radar data domains simultaneously, integrating attention and temporal modules for improved activity classification.

Findings

Achieves 96.16% accuracy on benchmark dataset.

Outperforms existing methods by at least 4.78%.

Effectively distinguishes similar actions.

Abstract

Radar systems are increasingly favored for medical applications because they provide non-intrusive monitoring with high privacy and robustness to lighting conditions. However, existing research typically relies on single-domain radar signals and overlooks the temporal dependencies inherent in human activity, which complicates the classification of similar actions. To address this issue, we designed the Parallel-EfficientNet-CBAM-LSTM (PECL) network to process data in three complementary domains: Range-Time, Doppler-Time, and Range-Doppler. PECL combines a channel-spatial attention module and temporal units to capture more features and dynamic dependencies during action sequences, improving both accuracy and robustness. The experimental results show that PECL achieves an accuracy of 96.16% on the same dataset, outperforming existing methods by at least 4.78%. PECL also performs best in distinguishing between easily confused actions. Despite its strong performance, PECL maintains moderate model complexity, with 23.42M parameters and 1324.82M FLOPs. Its parameter-efficient design further reduces computational cost.