TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909682972491776 |
|---|---|
| author | Bian, Sizhen Liu, Mengxi Rey, Vitor Fortes Geissler, Daniel Lukowicz, Paul |
| author_facet | Bian, Sizhen Liu, Mengxi Rey, Vitor Fortes Geissler, Daniel Lukowicz, Paul |
| contents | 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} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07949 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices Bian, Sizhen Liu, Mengxi Rey, Vitor Fortes Geissler, Daniel Lukowicz, Paul Computer Vision and Pattern Recognition Machine Learning 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} |
| title | TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.07949 |