arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.07652eess.SPcs.LG
收藏

基于决策树和CNN的单片机两阶段人体活动识别

Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs

Politecnico di Torino(都灵理工大学)

Francesco Daghero, Daniele Jahier Pagliari, Massimo Poncino

摘要:

人类活动识别(HAR)已经成为诸如智能手表之类的嵌入式设备越来越受欢迎的任务。大多数用于超低功耗设备的HAR系统都基于经典的机器学习(ML)模型,而深度学习(DL)虽然达到了最先进的精度,但由于其高能耗而不太受欢迎,这对电池供电和资源受限的设备构成了重大挑战。在这项工作中,我们通过由决策树(DT)和一维卷积神经网络(1D CNN)组成的分层架构弥合了设备上HAR和DL之间的差距。这两个分类器在两个不同的子任务上以级联的方式操作:DT只对最简单的活动进行分类,而CNN处理更复杂的活动。通过在最先进的数据集上进行实验,并针对单核RISC-V MCU,我们表明这种方法可以节省高达67.7%的w.r.t.等精度的“独立”DL架构。此外,两级系统要么引入了可忽略不计的内存开销(高达200 B),要么相反,减少了总内存占用。

英文摘要:

Human Activity Recognition (HAR) has become an increasingly popular task for embedded devices such as smartwatches. Most HAR systems for ultra-low power devices are based on classic Machine Learning (ML) models, whereas Deep Learning (DL), although reaching state-of-the-art accuracy, is less popular due to its high energy consumption, which poses a significant challenge for battery-operated and resource-constrained devices. In this work, we bridge the gap between on-device HAR and DL thanks to a hierarchical architecture composed of a decision tree (DT) and a one dimensional Convolutional Neural Network (1D CNN). The two classifiers operate in a cascaded fashion on two different sub-tasks: the DT classifies only the easiest activities, while the CNN deals with more complex ones. With experiments on a state-of-the-art dataset and targeting a single-core RISC-V MCU, we show that this approach allows to save up to 67.7% energy w.r.t. a "stand-alone" DL architecture at iso-accuracy. Additionally, the two-stage system either introduces a negligible memory overhead (up to 200 B) or on the contrary, reduces the total memory occupation.

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。

↑