TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Sizhen Bian, Mengxi Liu, Vítor Fortes Rey, Daniel Geißler, Paul Lukowicz
Abstract
Human Activity Recognition 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 depthwise separable convolutions, gated recurrent units, and temporal aggregation to achieve SOTA efficiency. Evaluated across 14 public datasets, TinierHAR reduces Parameters by 2.7× (vs. TinyHAR) and 43.3× (vs. DeepConvLSTM), and MACs by 6.4× and 58.6×, 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 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. All materials are open-sourced in this work for future benchmarking. https://github.com/zhaxidele/TinierHAR.