Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity Recognition
This work addresses the problem of generalization for contactless human activity recognition using WiFi CSI, which is incremental as it adapts existing image augmentation methods to a new domain.
The paper tackled poor model generalization in WiFi CSI-based human activity recognition across varying environments and hardware by applying image-based data augmentation techniques to CSI amplitude spectrograms, finding that specific combinations significantly improved cross-scenario and cross-system generalization.
The recognition of human activities based on WiFi Channel State Information (CSI) enables contactless and visual privacy-preserving sensing in indoor environments. However, poor model generalization, due to varying environmental conditions and sensing hardware, is a well-known problem in this space. To address this issue, in this work, data augmentation techniques commonly used in image-based learning are applied to WiFi CSI to investigate their effects on model generalization performance in cross-scenario and cross-system settings. In particular, we focus on the generalization between line-of-sight (LOS) and non-line-of-sight (NLOS) through-wall scenarios, as well as on the generalization between different antenna systems, which remains under-explored. We collect and make publicly available a dataset of CSI amplitude spectrograms of human activities. Utilizing this data, an ablation study is conducted in which activity recognition models based on the EfficientNetV2 architecture are trained, allowing us to assess the effects of each augmentation on model generalization performance. The gathered results show that specific combinations of simple data augmentation techniques applied to CSI amplitude data can significantly improve cross-scenario and cross-system generalization.