arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03644cs.HC
收藏

面向人类活动识别的设备端训练赋能迁移学习

On-Device Training Empowered Transfer Learning For Human Activity Recognition

Pixi Kang, Julian Moosmann, Sizhen Bian, Michele Magno

AI总结:

本文提出面向资源受限物联网边缘设备的设备端迁移学习方案,在STM32F756ZG和GAP9上优化训练引擎,并在三类HAR场景中验证准确率提升及GAP9在延迟和功耗上的显著优势。

摘要:

人类活动识别(HAR)是一个具有吸引力的课题,旨在感知人类行为并提供辅助服务。除了经典的惯性单元和基于视觉的HAR方法之外,超声和体域电场等新型传感技术已在HAR中出现,以提升用户体验并适应新的应用场景。由于这些传感器通常与人工智能结合用于HAR,与更广泛使用的IMU或基于视觉的HAR方案相比,它们经常因训练数据有限而面临挑战。此外,用户引发的概念漂移(UICD)在此类HAR场景中很常见。UICD的特征在于新用户的样本分布偏离训练参与者的样本分布,导致识别性能下降。本文提出了一种面向能量和资源受限的物联网边缘设备的设备端迁移学习(ODTL)方案。针对两个代表性的MCU级边缘计算平台STM32F756ZG和GAP9开发了优化的设备端训练引擎。在此基础上,我们在三个HAR场景中评估了ODTL的收益:基于体电容的健身活动识别、基于QVAR和超声波的手势识别。我们证明了活动识别准确率分别提升了3.73%、17.38%和3.70%。此外,我们观察到在ODTL部署期间,基于RISC-V的GAP9相比STM32F7 MCU实现了20倍的延迟降低和280倍的功耗降低,展示了采用最新低功耗并行计算设备进行边缘任务的优势。

英文摘要:

Human Activity Recognition (HAR) is an attractive topic to perceive human behavior and supplying assistive services. Besides the classical inertial unit and vision-based HAR methods, new sensing technologies, such as ultrasound and body-area electric fields, have emerged in HAR to enhance user experience and accommodate new application scenarios. As those sensors are often paired with AI for HAR, they frequently encounter challenges due to limited training data compared to the more widely IMU or vision-based HAR solutions. Additionally, user-induced concept drift (UICD) is common in such HAR scenarios. UICD is characterized by deviations in the sample distribution of new users from that of the training participants, leading to deteriorated recognition performance. This paper proposes an on-device transfer learning (ODTL) scheme tailored for energy- and resource-constrained IoT edge devices. Optimized on-device training engines are developed for two representative MCU-level edge computing platforms: STM32F756ZG and GAP9. Based on this, we evaluated the ODTL benefits in three HAR scenarios: body capacitance-based gym activity recognition, QVAR- and ultrasonic-based hand gesture recognition. We demonstrated an improvement of 3.73%, 17.38%, and 3.70% in the activity recognition accuracy, respectively. Besides this, we observed that the RISC-V-based GAP9 achieves 20x and 280x less latency and power consumption than STM32F7 MCU during the ODTL deployment, demonstrating the advantages of employing the latest low-power parallel computing devices for edge tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑