摘要
人类活动识别(HAR)近年来已成为健康、人类行为分析、物联网、人机交互等领域的一个重要研究领域。智能手机是HAR的热门选择，因为它们是日常生活中常用的设备。然而，大多数可用的HAR数据集是在实验室环境中收集的，这并没有反映现实世界的情况。为了解决这个问题，收集了一个使用智能手机惯性传感器的真实世界数据集，涉及62人。收集到的数据集噪声小，频率可变。另一方面，在HAR的背景下，由于阶级内的多样性（指的是由不同的人或同一个人在不同的条件下进行活动的特征的差异）和阶级间的相似性（指的是高度相似的不同活动），Algo-Rithms面临着额外的挑战。因此，从数据集中准确地提取特征是非常必要的。集成学习是一种有效的提高泛化性能的方法。提出了一种基于智能手机传感器的混合深度模型加权集成方法。与现有方法相比，本文提出的集成方法具有更好的性能，在多个评价指标上取得了令人印象深刻的结果。具体地说，实验分析表明，该算法的准确率为97.15%，准确率为96.41%，召回率为95.62%，F1评分为96.01%。这些结果证明了我们的集成方法在解决现实世界中HAR挑战方面的有效性。
Abstract
Human Activity Recognition (HAR) has become a signifcant area of study in the felds of health, human behavior analysis, the Internet of Things, and human-machine interaction in recent years. Smartphones are a popular choice for HAR as they are common devices used in daily life. However, most available HAR datasets are gathered in laboratory settings, which do not refect real-world scenarios. To address this issue, a real-world dataset using smartphone inertial sensors, involving 62 individuals, is collected. The collected dataset is noisy, small, and has variable frequency. On the other hand, in the context of HAR, algo- rithms face additional challenges due to intra-class diversity (which refers to diferences in the characteristics of performing an activity by diferent people or by the same individual under diferent conditions) and inter-class similarity (which refers to diferent activities that are highly similar). Consequently, it is essential to extract features accurately from the dataset. Ensemble learning, which combines multiple models, is an efective approach to improve generalization performance. In this paper, a weighted ensemble of hybrid deep models for HAR using smartphone sensors is proposed. The proposed ensemble approach demonstrates superior performance compared to current methods, achieving impressive results across multiple evaluation metrics. Specifcally, the experimental analysis demon- strates an accuracy of 97.15%, precision of 96.41%, recall of 95.62%, and an F1-score of 96.01%. These results demonstrate the efectiveness of our ensemble approach in address- ing the challenges of HAR in real-world scenarios.
NETL
NSTL