Thakur Dipanwita, Biswas Suparna
Banasthali Vidyapith, Jaipur, Rajasthan India.
Maulana Abul Kalam Azad University of Technology, Kolkata, WB India.
J Ambient Intell Humaniz Comput. 2023;14(7):9767-9779. doi: 10.1007/s12652-022-03862-5. Epub 2022 May 13.
Human activity recognition (HAR) is an eminent area of research due to its extensive scope of applications in remote health monitoring, sports, smart home, and many more. Smartphone-based HAR systems use high-dimensional sensor data to infer human physical activities. Researchers continuously endeavor to select pertinent and non-redundant features without compromising the classification accuracy. In this work, our aim is to build an efficient HAR model that not only extracts the most relevant features from the 3-axial accelerometer and gyroscope signal data but also enhances the classification accuracy of the HAR system, without data loss using time-frequency domain features. We propose a feature selection method based on guided regularized random forest (GRRF) to determine the most pertinent and non-redundant features to reduce the time to recognize the human activities efficiently. After selecting the most relevant features, a support vector machine (SVM) is used to identify various human physical activities. The UCI public dataset and a self-collected dataset are used to assess the generalization capability and performance of the proposed feature selection method. Eventually, the accuracy reached 99.10% and 99.30% on the self-collected and UCI HAR datasets, respectively.
人类活动识别（HAR）是一个重要的研究领域，因为它在远程健康监测、体育、智能家居等众多领域有着广泛的应用。基于智能手机的HAR系统利用高维传感器数据来推断人类的身体活动。研究人员不断努力选择相关且无冗余的特征，同时不影响分类准确率。在这项工作中，我们的目标是构建一个高效的HAR模型，该模型不仅能从三轴加速度计和陀螺仪信号数据中提取最相关的特征，还能提高HAR系统的分类准确率，且不使用时频域特征导致数据丢失。我们提出一种基于引导正则化随机森林（GRRF）的特征选择方法，以确定最相关且无冗余的特征，从而有效减少识别人类活动的时间。在选择最相关的特征后，使用支持向量机（SVM）来识别各种人类身体活动。使用UCI公共数据集和一个自行收集的数据集来评估所提出特征选择方法的泛化能力和性能。最终，在所收集的HAR数据集和UCI HAR数据集上，准确率分别达到了99.10%和99.30%。
