Environment-Independent Wi-Fi Human Activity Recognition With Adversarial Network

Human activity recognition is an essential part of human-computer interaction systems. Environment-robust Wi-Fi-based systems for this task is still a challenging problem, due to the fact that most existing systems may drop in performance when the environment is changed. To address this issue, we in this paper present WiHARAN, a Wi-Fi-based activity recognition system that can learn environment-independent features from Channel State Information (CSI) traces. With a well-designed base network capable of extracting temporal information from spectrograms, we align the joint distribution of features and labels from multiple environments utilizing adversarial learning. Experimental results show that our system achieves better performance than state-of-the-art solutions and can improve performance in difficult environments.