Transparent and Resilient Activity Recognition via Attention-Based Distributed Radar Sensing

TL;DR

This paper introduces an end-to-end attention-based framework for distributed radar activity recognition that enhances interpretability, reduces complexity, and improves accuracy by processing raw data directly with local CNNs and a self-attention fusion mechanism.

Contribution

It presents a novel hybrid approach combining lightweight CNNs and self-attention for transparent, efficient data fusion in distributed radar sensing, with significant reductions in model complexity and communication overhead.

Findings

Reduces model complexity by 70.8%

Achieves higher average accuracy than baseline methods

Provides inherent interpretability through attention weights

Abstract

Distributed radar sensors enable robust human activity recognition. However, scaling the number of coordinated nodes introduces challenges in feature extraction from large datasets, and transparent data fusion. We propose an end-to-end framework that operates directly on raw radar data. Each radar node employs a lightweight 2D Convolutional Neural Network (CNN) to extract local features. A self-attention fusion block then models inter-node relationships and performs adaptive information fusion. Local feature extraction reduces the input dimensionality by up to 480x. This significantly lowers communication overhead and latency. The attention mechanism provides inherent interpretability by quantifying the contribution of each radar node. A hybrid supervised contrastive loss further improves feature separability, especially for fine-grained and imbalanced activity classes. Experiments on real-world distributed Ultra Wide Band (UWB) radar data demonstrate that the proposed method reduces model complexity by 70.8\%, while achieving higher average accuracy than baseline approaches. Overall, the framework enables transparent, efficient, and low-overhead distributed radar sensing.