Human activity recognition is a core technology for applications such as rehabilitation, ambient health monitoring, and human-computer interactions. Wearable devices, particularly IMU sensors, can help us collect rich features of human movements that can be leveraged in activity recognition. Developing a robust classifier for activity recognition has always been of interest to researchers. One major problem is that there is usually a deficit of training data for some activities, making it difficult and sometimes impossible to develop a classifier. In this work, a novel GAN network called TheraGAN was developed to generate realistic IMU signals associated with a particular activity. The generated signal is of a 6-channel IMU. i.e., angular velocities and linear accelerations. Also, by introducing simple activities, which are meaningful subparts of a complex full-length activity, the generation process was facilitated for any activity with arbitrary length. To evaluate the generated signals, besides perceptual similarity metrics, they were applied along with real data to improve the accuracy of classifiers. The results show that the maximum increase in the f1-score belongs to the LSTM classifier by a 13.27% rise when generated data were added. This shows the validity of the generated data as well as TheraGAN as a tool to build more robust classifiers in case of imbalanced data problem.

翻译：人体活动识别是康复、环境健康监测和人机交互等应用的核心技术。可穿戴设备，特别是惯性测量单元（IMU）传感器，能够帮助我们采集人体动作的丰富特征，这些特征可用于活动识别。开发鲁棒的活动识别分类器一直是研究人员的关注点。主要问题在于某些活动往往缺乏训练数据，这使得开发分类器变得困难甚至不可能。本研究中，我们开发了一种名为TheraGAN的新型生成对抗网络（GAN），用于生成与特定活动相关的真实IMU信号。所生成的信号为6通道IMU信号，即角速度和线性加速度。此外，通过引入简单活动（即复杂全长活动中有意义的子部分），我们使得任意长度的活动生成过程得以简化。为了评估生成的信号，除了感知相似度指标外，我们还将其与真实数据结合使用，以提高分类器的准确率。结果表明，当加入生成数据后，f1分数的最大提升来自LSTM分类器，提高了13.27%。这验证了生成数据的有效性，同时也证明了TheraGAN作为工具在处理数据不平衡问题时构建更鲁棒分类器的能力。