Institut Pluridisciplinaire Hubert Curien (IPHC) UMR 7178 Centre National de la Recherche Scientifique (CNRS), Université de Strasbourg, 67000 Strasbourg, France.
Division of Endocrinology, Metabolism, and Diabetes and Anschutz Health and Wellness Center, University of Colorado, School of Medicine, Aurora, CO 80045, USA.
Sensors (Basel). 2020 May 29;20(11):3090. doi: 10.3390/s20113090.
Here we propose a new machine learning algorithm for classification of human activities by means of accelerometer and gyroscope signals. Based on a novel hierarchical system of logistic regression classifiers and a relatively small set of features extracted from the filtered signals, the proposed algorithm outperformed previous work on the DaLiAc (Daily Life Activity) and mHealth datasets. The algorithm also represents a significant improvement in terms of computational costs and requires no feature selection and hyper-parameter tuning. The algorithm still showed a robust performance with only two (ankle and wrist) out of the four devices (chest, wrist, hip and ankle) placed on the body (96.8% vs. 97.3% mean accuracy for the DaLiAc dataset). The present work shows that low-complexity models can compete with heavy, inefficient models in classification of advanced activities when designed with a careful upstream inspection of the data.
我们提出了一种新的机器学习算法，用于通过加速度计和陀螺仪信号对人体活动进行分类。该算法基于一个新颖的逻辑回归分类器层次系统和从滤波信号中提取的相对较少的特征，在 DaLiAc（日常生活活动）和 mHealth 数据集上的表现优于以前的工作。该算法在计算成本方面也有显著的提高，并且不需要特征选择和超参数调整。该算法在仅使用四个设备中的两个（脚踝和手腕）（胸部、手腕、臀部和脚踝）放置在身体上时仍表现出稳健的性能（DaLiAc 数据集的平均准确率为 96.8%，而 97.3%）。本工作表明，当对数据进行仔细的上游检查时，低复杂度模型可以在高级活动的分类中与复杂、低效的模型竞争。
