Department of Computer Engineering, School of Information and Communication Technology, University of Phayao, Phayao 56000, Thailand.
Intelligent and Nonlinear Dynamic Innovations Research Center, Department of Mathematics, Faculty of Applied Science, King Mongkut's University of Technology North Bangkok, Bangkok 10800, Thailand.
Sensors (Basel). 2021 Feb 26;21(5):1636. doi: 10.3390/s21051636.
Human Activity Recognition (HAR) employing inertial motion data has gained considerable momentum in recent years, both in research and industrial applications. From the abstract perspective, this has been driven by an acceleration in the building of intelligent and smart environments and systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc. Such environments and systems necessitate and subsume activity recognition, aimed at recognizing the actions, characteristics, and goals of one or more individuals from a temporal series of observations streamed from one or more sensors. Due to the reliance of conventional Machine Learning (ML) techniques on handcrafted features in the extraction process, current research suggests that deep-learning approaches are more applicable to automated feature extraction from raw sensor data. In this work, the generic HAR framework for smartphone sensor data is proposed, based on Long Short-Term Memory (LSTM) networks for time-series domains. Four baseline LSTM networks are comparatively studied to analyze the impact of using different kinds of smartphone sensor data. In addition, a hybrid LSTM network called 4-layer CNN-LSTM is proposed to improve recognition performance. The HAR method is evaluated on a public smartphone-based dataset of UCI-HAR through various combinations of sample generation processes (OW and NOW) and validation protocols (10-fold and LOSO cross validation). Moreover, Bayesian optimization techniques are used in this study since they are advantageous for tuning the hyperparameters of each LSTM network. The experimental results indicate that the proposed 4-layer CNN-LSTM network performs well in activity recognition, enhancing the average accuracy by up to 2.24% compared to prior state-of-the-art approaches.
人体活动识别（HAR）使用惯性运动数据近年来在研究和工业应用中都得到了迅猛的发展。从抽象的角度来看，这是由于智能和智能环境与系统的建设加速，这些环境与系统涵盖了人类生活的各个方面，包括医疗保健、体育、制造、商业等。这些环境与系统需要并包含活动识别，旨在从一个或多个传感器流式传输的时间序列观察中识别一个或多个人的动作、特征和目标。由于传统机器学习（ML）技术在提取过程中依赖于手工制作的特征，因此目前的研究表明，深度学习方法更适用于从原始传感器数据中自动提取特征。在这项工作中，提出了基于智能手机传感器数据的通用 HAR 框架，该框架基于用于时间序列域的长短期记忆（LSTM）网络。比较研究了四个基线 LSTM 网络，以分析使用不同类型的智能手机传感器数据的影响。此外，还提出了一种称为 4 层 CNN-LSTM 的混合 LSTM 网络，以提高识别性能。该 HAR 方法通过各种样本生成过程（OW 和 NOW）和验证协议（10 折和 LOSO 交叉验证）在 UCI-HAR 基于智能手机的公共数据集上进行评估。此外，本研究还使用了贝叶斯优化技术，因为它们有利于调整每个 LSTM 网络的超参数。实验结果表明，所提出的 4 层 CNN-LSTM 网络在活动识别中表现良好，与先前的最先进方法相比，平均准确率提高了 2.24%。
