Improving physical activity recognition using a new deep learning architecture and post-processing techniques
Improving physical activity recognition using a new deep learning architecture and post-processing techniques
复制标题
DOI：
10.1016/j.engappai.2020.103679
复制
发表时间：
2020-06-01
影响因子：
8
通讯作者：
Ferreiros-Lopez, Javier
中科院分区：
文献类型：
--
作者：
Gil-Martin, Manuel;San-Segundo, Ruben;Ferreiros-Lopez, Javier
本文提出了一种由三个模块组成的人类活动识别系统。第一个将加速度信号分割成重叠的窗口，并从频域中的每个窗口中提取信息。第二个模块使用基于卷积神经网络 (CNN) 的深度学习结构检测每个窗口执行的活动。该结构的第一部分具有与每个传感器独立关联的多个层，第二部分结合了所有传感器的输出，以便对身体活动进行分类。第三个模块在更长的时间内集成了窗口级决策，获得了显着的性能提升（从89.83％到96.62％）。这些是 PAMAP2 数据集上采用留一主题排除 (LOSO) 评估的最佳分类结果。
This paper proposes a Human Activity Recognition system composed of three modules. The first one segments the acceleration signals into overlapped windows and extracts information from each window in the frequency domain. The second module detects the performed activity at each window using a deep learning structure based on Convolutional Neural Networks (CNNs). The first part of this structure has several layers associated to each sensor independently and the second part combines the outputs from all sensors in order to classify the physical activity. The third module integrates the window-level decision in longer periods of time, obtaining a significant performance improvement (from 89.83% to 96.62%). These are the best classification results on the PAMAP2 dataset with a Leave-One-Subject-Out (LOSO) evaluation.