Dendron让可穿戴设备在数据少时也能自主学习新动作识别
Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
- 基于TinyML在嵌入式设备上实现新动作的在线学习
- 在两个公开数据集和STM32设备上验证，支持低资源环境下的高效学习
- 适合资源受限的可穿戴设备开发者，尤其适用于标注数据稀缺场景
人体活动识别（HAR）是利用机器学习技术识别用户行为的研究领域。近年来，研究重点转向在可穿戴设备上直接执行的HAR解决方案，这得益于资源受限嵌入式设备中的微型机器学习（TinyML）范式。然而，现有方法缺乏在监督数据稀缺的情况下，在设备端学习新任务的能力。为此，本文提出Dendron，一种新型的TinyML方法，可在有限监督数据条件下，实现可穿戴设备对新HAR任务的本地学习。在两个公开数据集及一款现成设备（STM32-NUCLEO-F401RE）上的实验结果表明，该方案在效率与有效性方面表现优异。
原文摘要 · Abstract (English)
Human activity recognition (HAR) is a research field that employs Machine Learning (ML) techniques to identify user activities. Recent studies have prioritized the development of HAR solutions directly executed on wearable devices, enabling the on-device activity recognition. This approach is supported by the Tiny Machine Learning (TinyML) paradigm, which integrates ML within embedded devices with limited resources. However, existing approaches in the field lack in the capability for on-device learning of new HAR tasks, particularly when supervised data are scarce. To address this limitation, our paper introduces Dendron, a novel TinyML methodology designed to facilitate the on-device learning of new tasks for HAR, even in conditions of limited supervised data. Experimental results on two public-available datasets and an off-the-shelf device (STM32-NUCLEO-F401RE) show the effectiveness and efficiency of the proposed solution.
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。