用手机传感器数据提升动作识别准确率，提出轻量新模型与数据增强方法。
Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition
- 设计非平稳BERT模型，分两阶段训练提升性能。
- 在多个数据集上达当前最优，跨用户识别效果显著。
- 适合移动端部署，尤其适合个性化动作识别场景。
由于移动设备普及及对用户日常活动数据监测的需求，人体动作识别（HAR）受到广泛关注。本文收集了一个名为OPPOHAR的人体动作识别数据集，包含手机惯性测量单元（IMU）数据。为促进HAR系统在手机端的应用并实现用户个性化识别，提出一种轻量级网络Non-stationary BERT，结合两阶段训练策略，并设计了一种简单但高效的数据增强方法，深入挖掘加速度计与陀螺仪数据间的关联关系。该模型在多个动作识别数据集上达到当前最优性能，所提数据增强方法也展现出广泛适用性。
原文摘要 · Abstract (English)
Human Activity Recognition (HAR) has gained great attention from researchers due to the popularity of mobile devices and the need to observe users' daily activity data for better human-computer interaction. In this work, we collect a human activity recognition dataset called OPPOHAR consisting of phone IMU data. To facilitate the employment of HAR system in mobile phone and to achieve user-specific activity recognition, we propose a novel light-weight network called Non-stationary BERT with a two-stage training method. We also propose a simple yet effective data augmentation method to explore the deeper relationship between the accelerator and gyroscope data from the IMU. The network achieves the state-of-the-art performance testing on various activity recognition datasets and the data augmentation method demonstrates its wide applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。