Semi-supervised variational autoencoder for WiFi indoor localization

We address the problem of indoor localization based on WiFi signal strengths. We develop a semi-supervised deep learning method able to train a prediction model from a small set of annotated WiFi observations and a massive set of non-annotated WiFi observations. Our method is based on the variational autoencoder deep network. We complement the network with an additional component of structural projection able to further improve the localization accuracy in a complex, multi-building and multi-floor environment. We consider several different network compositions which combine the classification and regression sub-tasks to achieve the optimal performance. We evaluate our method on the public UJI-IndoorLoc dataset and show that the proposed method allows to maintain the state of the art localization accuracy with a very limited amount of annotated data.