Deep Neural Networks for Human Activity Recognition With Wearable Sensors: Leave-One-Subject-Out Cross-Validation for Model Selection
Deep Neural Networks for Human Activity Recognition With Wearable Sensors: Leave-One-Subject-Out Cross-Validation for Model Selection
复制标题
DOI：
10.1109/access.2020.3010715
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Grolinger, Katarina
中科院分区：
文献类型：
--
作者：
Gholamiangonabadi, Davoud;Kiselov, Nikita;Grolinger, Katarina
人类活动识别（HAR）已经引起了广泛的研究关注，因为越来越多的环境和可穿戴传感器可用于收集HAR数据。近年来，深度学习方法由于其对复杂系统建模的能力而取得了巨大的成功。然而，这些模型通常与用于训练模型的模型在相同的主题上进行评估；因此，所提供的准确度估计并不适用于新的科目。偶尔，一个或几个科目被选中进行评估，但这种估计高度依赖于被选中进行评估的科目。因此，本文通过使用Leave-One-Subject-Out交叉验证（LOSOCV）来研究不同的机器学习架构如何基于新主题进行概括。LOSOCV在交叉验证的每一层中改变用于评估的受试者，为新受试者提供独立于受试者的性能估计。考虑了六种前馈和卷积神经网络（CNN）架构以及四种预处理方案。结果表明，具有两个卷积和一维滤波并带有滑动窗口和矢量幅度的CNN架构比其他架构具有更好的泛化能力。对于相同的CNN，准确率从使用LOSOCV评估时的85.1%提高到使用传统的10倍交叉验证评估时的99.85%，这表明使用LOSOCV进行评估的重要性。
Human Activity Recognition (HAR) has been attracting significant research attention because of the increasing availability of environmental and wearable sensors for collecting HAR data. In recent years, deep learning approaches have demonstrated a great success due to their ability to model complex systems. However, these models are often evaluated on the same subjects as those used to train the model; thus, the provided accuracy estimates do not pertain to new subjects. Occasionally, one or a few subjects are selected for the evaluation, but such estimates highly depend on the subjects selected for the evaluation. Consequently, this paper examines how well different machine learning architectures make generalizations based on a new subject(s) by using Leave-One-Subject-Out Cross-Validation (LOSOCV). Changing the subject used for the evaluation in each fold of the cross-validation, LOSOCV provides subject-independent estimate of the performance for new subjects. Six feed forward and convolutional neural network (CNN) architectures as well as four pre-processing scenarios have been considered. Results show that CNN architecture with two convolutions and one-dimensional filter accompanied by a sliding window and vector magnitude, generalizes better than other architectures. For the same CNN, the accuracy improves from 85.1% when evaluated with LOSOCV to 99.85% when evaluated with the traditional 10-fold cross-validation, demonstrating the importance of using LOSOCV for the evaluation.