Department of Anesthesiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA.
Department of Computer Science and Engineering, Islamic University and Technology (IUT), Gazipur 1704, Bangladesh.
Sensors (Basel). 2023 Aug 27;23(17):7452. doi: 10.3390/s23177452.
Electroencephalography (EEG) is a non-invasive method employed to discern human behaviors by monitoring the neurological responses during cognitive and motor tasks. Machine learning (ML) represents a promising tool for the recognition of human activities (HAR), and eXplainable artificial intelligence (XAI) can elucidate the role of EEG features in ML-based HAR models. The primary objective of this investigation is to investigate the feasibility of an EEG-based ML model for categorizing everyday activities, such as resting, motor, and cognitive tasks, and interpreting models clinically through XAI techniques to explicate the EEG features that contribute the most to different HAR states. The study involved an examination of 75 healthy individuals with no prior diagnosis of neurological disorders. EEG recordings were obtained during the resting state, as well as two motor control states (walking and working tasks), and a cognition state (reading task). Electrodes were placed in specific regions of the brain, including the frontal, central, temporal, and occipital lobes (Fz, C1, C2, T7, T8, Oz). Several ML models were trained using EEG data for activity recognition and LIME (Local Interpretable Model-Agnostic Explanations) was employed for interpreting clinically the most influential EEG spectral features in HAR models. The classification results of the HAR models, particularly the Random Forest and Gradient Boosting models, demonstrated outstanding performances in distinguishing the analyzed human activities. The ML models exhibited alignment with EEG spectral bands in the recognition of human activity, a finding supported by the XAI explanations. To sum up, incorporating eXplainable Artificial Intelligence (XAI) into Human Activity Recognition (HAR) studies may improve activity monitoring for patient recovery, motor imagery, the healthcare metaverse, and clinical virtual reality settings.
脑电图（EEG）是一种非侵入性方法，通过监测认知和运动任务期间的神经反应来识别人类行为。机器学习（ML）是识别人类活动（HAR）的有前途的工具，可解释人工智能（XAI）可以阐明 EEG 特征在基于 ML 的 HAR 模型中的作用。本研究的主要目的是研究基于 EEG 的 ML 模型在分类日常活动（如休息、运动和认知任务）方面的可行性，并通过 XAI 技术对模型进行临床解释，以阐明对不同 HAR 状态贡献最大的 EEG 特征。该研究涉及对 75 名没有神经障碍先前诊断的健康个体进行检查。在休息状态下以及两个运动控制状态（步行和工作任务）和认知状态（阅读任务）下获取 EEG 记录。电极放置在大脑的特定区域，包括额叶、中央、颞叶和枕叶（Fz、C1、C2、T7、T8、Oz）。使用 EEG 数据训练了几种 ML 模型，并使用 LIME（局部可解释模型不可知解释）对 HAR 模型中最具影响力的 EEG 谱特征进行临床解释。HAR 模型的分类结果，特别是随机森林和梯度提升模型，在区分分析的人类活动方面表现出出色的性能。ML 模型在识别人类活动时与 EEG 谱带一致，这一发现得到了 XAI 解释的支持。总之，将可解释人工智能（XAI）纳入人类活动识别（HAR）研究可能会改善患者康复、运动想象、医疗保健元宇宙和临床虚拟现实环境中的活动监测。
