A Conditional Diffusion Model Based WiFi Sensing Enhancement Method

Driven by the rapid development of deep learning approaches, many novel WiFi sensing based applications have emerged, such as human activity recognition, pose estimation and indoor localization. However, due to the limited richness of collected WiFi data, the performance of WiFi sensing based models still lags behind conventional vision based models in terms of recognition accuracy and generalization. To break through the bottleneck of insufficient WiFi data, we propose a diffusion model based data augmentation scheme for human activity recognition task, in which the training dataset is composed of both real data and synthetic data. In particular, to reduce training overheads of the diffusion model, it is trained by taking activity classes as input conditions. Therefore, a single model is able to generate multiple types of WiFi data corresponding to activities, thereby avoiding the need to train separate models for each individual activity. Simulation results show that the generated WiFi data samples are visually indistinguishable from real ones, even when the model is trained on a small-scale dataset. Moreover, it also shows that adding an appropriate amount of synthetic data into training dataset can indeed improve the performance of WiFi sensing in most cases.