Semisupervised Generative Adversarial Networks With Temporal Convolutions for Human Activity Recognition

Many potential applications of human activity recognition (HAR) can be found in health, surveillance, manufacturing, sports, and so on. For instance, HAR can be exploited in ambient-assisted living (AAL) systems to provide users with assistance services intend to improve their well-being, safety, and autonomy. Data annotation in HAR is a complex and time-consuming process that limits the availability of labeled samples. Furthermore, the classification performance of supervised deep neural networks depends on the availability of large, annotated training data. This article proposes an alternative framework for semisupervised generative adversarial networks (GANs) using temporal convolutions for semisupervised action recognition to address several problems related to conventional approaches in the HAR context, such as high dimensionality, scarcity of annotated data, scalability, and robustness. The proposed framework employs a single architecture on different datasets and its effectiveness is tested under four conditions reflecting real-world semisupervised scenarios to investigate the impact of intersubject training, amount of labeled data, number of classes, and inertial measurement unit (IMU) positions on model performance. The evaluations are performed on the Physical Activity Monitoring for Aging People (PAMAP2), opportunity-locomotion, and Laboratory of Images, Signals and Intelligent Systems (LISSI) HAR datasets to evaluate the generalizability of the framework. The results show the proposed framework’s high classification performance and generalization ability compared with baseline methods, achieving up to 25% improvement when only a small amount of annotated data is available. A comparison with the previous work using the same datasets has also validated the performance of the framework.