arXiv：cs.LG· E. Riveros (Institute of Computing, State University of Campinas, Campinas, Brazil), D. Vega-Oliveros (Institute of Science and Technology, Federal University of Sao Paulo, Sao Jose dos Campos, Brazil), A. Soriano-Vargas (Universidad de Ingenieria y Tecnologia, Lima, Peru), A. Rocha (Institute of Computing, State University of Campinas, Campinas, Brazil)·· 3 小时前AI 评分31
基于扩散模型合成数据预训练提升人体活动识别
Diffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition
AI 导读
研究团队提出用扩散模型生成合成传感器数据窗口，对CABiGRU模型采用两阶段训练：先在合成数据上预训练，再用真实数据微调。在DEO（饮水/进食/其他）数据集上，该流程实现90.6%的平衡准确率，优于强监督基线，改善了少数类欠拟合问题。
正文
Authors:E. Riveros (1), D. Vega-Oliveros (2), A. Soriano-Vargas (3), A. Rocha (1) ((1) Institute of Computing, State University of Campinas, Campinas, Brazil, (2) Institute of Science and Technology, Federal University of Sao Paulo, Sao Jose dos Campos, Brazil, (3) Universidad de Ingenieria y Tecnologia, Lima, Peru)
Abstract:Human activity recognition (HAR) is increasingly important for healthcare, well-being, and daily monitoring ap- plications, for which detecting alimentary activities such as eating and drinking can provide actionable insight into dietary habits and chronic disease management. HAR systems, however, often underperform on subtle and underrepresented classes, limiting their utility in real-world dietary monitoring. This work builds upon CABiGRU, a convolutional architecture with Bidirectional GRU layers, multi-head attention, and residual connections, designed to capture discriminative temporal patterns from smart- watch accelerometer, gyroscope, and magnetometer data. To improve CaBiGRU's generalization and reduce underfitting in the minority class, we leverage synthetic sensor data windows using a diffusion model and adopt a two-stage training strategy: pre-training CABiGRU on synthetic data, followed by fine-tuning on the real-world data. On the DEO (drinking/eating/other) dataset, the proposed pipeline achieves a balanced accuracy of 90.6%, improving over a strong supervised baseline and showing the benefits of diffusion-based synthetic pre-training for recognizing alimentary activities and representing a step forward dealing with unbalanced classes. These results suggest that combining diffusion-generated data with targeted fine-tuning enhances robust recognition of dietary behaviors, supporting more reliable deployment in healthcare and nutrition-monitoring settings.
| Comments: | 6 pages, 3 figures, 1 table |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| MSC classes: | 68T07 (Primary) 68T10, 62M10, 62H30 (Secondary) |
| Cite as: | arXiv:2610.02292 [cs.LG] |
| (or arXiv:2610.02292v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02292 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elian Riveros [view email]
[v1]
Thu, 1 Oct 2026 16:43:40 UTC (291 KB)
来源：arXiv：cs.LG · arxiv.org