Shallow Convolutional Neural Networks for Human Activity Recognition Using Wearable Sensors
Shallow Convolutional Neural Networks for Human Activity Recognition Using Wearable Sensors
复制标题
DOI：
10.1109/tim.2021.3091990
复制
发表时间：
2021-01-01
影响因子：
5.6
通讯作者：
He, Jun
中科院分区：
文献类型：
--
作者：
Huang, Wenbo;Zhang, Lei;He, Jun
由于传感器技术的快速发展，利用可穿戴惯性传感器进行人体活动识别已成为一个新的研究热点。深度学习，特别是卷积神经网络(CNN)能够自动学习复杂的活动特征，在泛在HAR任务中得到了广泛的关注。现有的CNN大多通过提取通道特征来处理传感器输入，每个通道的信息可以从低层到高层以分层的方式单独传播。因此，它们通常忽略了同一层内的通道之间的信息交换。在本文中，我们首先提出了一种浅层CNN，它考虑了HAR场景中的跨通道通信，其中同一层中的所有通道都具有全面的交互作用，以捕获传感器输入的更具区分性的特征。通过图神经网络，一个通道可以与所有其他通道进行通信，消除通道间积累的冗余信息，更有利于部署轻量级深度模型。在UCI-HAR、Opportunity、PAMAP2和UNIMIB-SHAR等多个基准HAR数据集上进行了大量的实验，结果表明，该方法能够使浅层CNN聚集更多的有用信息，并且优于基线深度网络和其他竞争性方法。通过将HAR系统部署在嵌入式系统上对推理速度进行了评估。
Due to rapid development of sensor technology, human activity recognition (HAR) using wearable inertial sensors has recently become a new research hotspot. Deep learning, especially convolutional neural network (CNN) that can automatically learn intricate activity features have gained a lot of attention in ubiquitous HAR task. Most existing CNNs process sensor input by extracting channel-wise features, and the information from each channel can be separately propagated in a hierarchical way from lower layers to higher layers. As a result, they typically overlook information exchange among channels within the same layer. In this article, we first propose a shallow CNN that considers cross-channel communication in HAR scenario, where all channels in the same layer have a comprehensive interaction to capture more discriminative features of sensor input. One channel can communicate with all other channels by graph neural network to remove redundant information accumulated among channels, which is more beneficial for deploying lightweight deep models. Extensive experiments are conducted on multiple benchmark HAR datasets, namely UCI-HAR, OPPORTUNITY, PAMAP2 and UniMib-SHAR, which indicates that the proposed method enables shallower CNNs to aggregate more useful information, and surpasses baseline deep networks and other competitive methods. The inference speed is evaluated via deploying the HAR systems on an embedded system.