The Human Activity Recognition (HAR) tasks automatically identify human activities using the sensor data, which has numerous applications in healthcare, sports, security, and human-computer interaction. Despite significant advances in HAR, critical challenges still exist. Game theory has emerged as a promising solution to address these challenges in machine learning problems including HAR. However, there is a lack of research work on applying game theory solutions to the HAR problems. This review paper explores the potential of game theory as a solution for HAR tasks, and bridges the gap between game theory and HAR research work by suggesting novel game-theoretic approaches for HAR problems. The contributions of this work include exploring how game theory can improve the accuracy and robustness of HAR models, investigating how game-theoretic concepts can optimize recognition algorithms, and discussing the game-theoretic approaches against the existing HAR methods. The objective is to provide insights into the potential of game theory as a solution for sensor-based HAR, and contribute to develop a more accurate and efficient recognition system in the future research directions.

翻译：人体活动识别（HAR）任务利用传感器数据自动识别人类活动，在医疗健康、体育运动、安全防护和人机交互等领域具有广泛应用。尽管HAR取得了显著进展，但关键挑战依然存在。博弈论已成为解决包括HAR在内的机器学习问题中此类挑战的重要方案。然而，目前尚缺乏将博弈论解决方案应用于HAR问题的系统研究。本综述论文探索了博弈论作为HAR任务解决方案的潜力，通过提出针对HAR问题的创新博弈论方法，填补了博弈论与HAR研究之间的空白。本文的贡献包括：探究博弈论如何提升HAR模型的准确性和鲁棒性，分析博弈论概念如何优化识别算法，以及讨论现有HAR方法中博弈论方法的适用性。旨在深入揭示博弈论作为传感器HAR解决方案的潜力，为未来研究方向中构建更准确高效的识别系统提供参考。