TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices

TL;DR

TinierHAR is an ultra-lightweight deep learning model for human activity recognition on edge devices, achieving state-of-the-art efficiency and performance through novel architectural components and systematic analysis.

Contribution

The paper introduces TinierHAR, a new ultra-lightweight architecture combining residual depthwise separable convolutions, GRUs, and temporal aggregation, with comprehensive ablation studies.

Findings

Reduces model parameters by up to 43.3x compared to DeepConvLSTM.

Achieves significant reductions in MACs, up to 58.6x.

Maintains high F1-scores across 14 HAR datasets.

Abstract

Human Activity Recognition (HAR) on resource-constrained wearable devices demands inference models that harmonize accuracy with computational efficiency. This paper introduces TinierHAR, an ultra-lightweight deep learning architecture that synergizes residual depthwise separable convolutions, gated recurrent units (GRUs), and temporal aggregation to achieve SOTA efficiency without compromising performance. Evaluated across 14 public HAR datasets, TinierHAR reduces Parameters by 2.7x (vs. TinyHAR) and 43.3x (vs. DeepConvLSTM), and MACs by 6.4x and 58.6x, respectively, while maintaining the averaged F1-scores. Beyond quantitative gains, this work provides the first systematic ablation study dissecting the contributions of spatial-temporal components across proposed TinierHAR, prior SOTA TinyHAR, and the classical DeepConvLSTM, offering actionable insights for designing efficient HAR systems. We finally discussed the findings and suggested principled design guidelines for future efficient HAR. To catalyze edge-HAR research, we open-source all materials in this work for future benchmarking\footnote{https://github.com/zhaxidele/TinierHAR}