论文标题
带有决策树和CNN的微控制器上的两个阶段人类活动识别
Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs
论文作者
论文摘要
人类活动识别（HAR）已成为嵌入式设备（例如智能手表）越来越受欢迎的任务。大多数用于超低功率设备的HAR系统基于经典的机器学习（ML）模型，而深度学习（DL）尽管达到最先进的精度，但由于其高能量消耗而不太受欢迎，这对电池操作和资源约束的设备构成了重大挑战。在这项工作中，由于由决策树（DT）和一个维度卷积神经网络（1D CNN）组成的层次结构，我们弥合了设备HAR和DL之间的差距。这两个分类器以两个不同的子任务的级联方式运行：DT仅分类最简单的活动，而CNN则处理更复杂的活动。通过对最先进的数据集进行实验并针对单核RISC-V MCU，我们表明这种方法可节省高达67.7％的能量W.R.T. ISO准确性的“独立” DL架构。此外，两阶段系统要么引入可忽略不计的内存开销（最多200 B），要么相反，可以减少总内存职业。
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.
