Process Optimization and Deployment for Sensor-Based Human Activity Recognition Based on Deep Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916674723119104 |
|---|---|
| author | Liu, Hanyu Yu, Ying Xiao, Hang Li, Siyao Li, Xuze Li, Jiarui Tang, Haotian |
| author_facet | Liu, Hanyu Yu, Ying Xiao, Hang Li, Siyao Li, Xuze Li, Jiarui Tang, Haotian |
| contents | Sensor-based human activity recognition is a key technology for many human-centered intelligent applications. However, this research is still in its infancy and faces many unresolved challenges. To address these, we propose a comprehensive optimization process approach centered on multi-attention interaction. We first utilize unsupervised statistical feature-guided diffusion models for highly adaptive data enhancement, and introduce a novel network architecture-Multi-branch Spatiotemporal Interaction Network, which uses multi-branch features at different levels to effectively Sequential ), which uses multi-branch features at different levels to effectively Sequential spatio-temporal interaction to enhance the ability to mine advanced latent features. In addition, we adopt a multi-loss function fusion strategy in the training phase to dynamically adjust the fusion weights between batches to optimize the training results. Finally, we also conducted actual deployment on embedded devices to extensively test the practical feasibility of the proposed method in existing work. We conduct extensive testing on three public datasets, including ablation studies, comparisons of related work, and embedded deployments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Process Optimization and Deployment for Sensor-Based Human Activity Recognition Based on Deep Learning Liu, Hanyu Yu, Ying Xiao, Hang Li, Siyao Li, Xuze Li, Jiarui Tang, Haotian Signal Processing Artificial Intelligence Computer Vision and Pattern Recognition Sensor-based human activity recognition is a key technology for many human-centered intelligent applications. However, this research is still in its infancy and faces many unresolved challenges. To address these, we propose a comprehensive optimization process approach centered on multi-attention interaction. We first utilize unsupervised statistical feature-guided diffusion models for highly adaptive data enhancement, and introduce a novel network architecture-Multi-branch Spatiotemporal Interaction Network, which uses multi-branch features at different levels to effectively Sequential ), which uses multi-branch features at different levels to effectively Sequential spatio-temporal interaction to enhance the ability to mine advanced latent features. In addition, we adopt a multi-loss function fusion strategy in the training phase to dynamically adjust the fusion weights between batches to optimize the training results. Finally, we also conducted actual deployment on embedded devices to extensively test the practical feasibility of the proposed method in existing work. We conduct extensive testing on three public datasets, including ablation studies, comparisons of related work, and embedded deployments. |
| title | Process Optimization and Deployment for Sensor-Based Human Activity Recognition Based on Deep Learning |
| topic | Signal Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.03687 |