Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems
This work addresses indoor positioning for smartphone users, presenting incremental improvements through hybrid deep learning models.
The authors tackled indoor positioning using WiFi fingerprints by proposing two deep learning models: a convolutional mixture density recurrent neural network for path prediction and a VAE-based semi-supervised model for unlabeled data. Experimental results on real-world datasets verified the effectiveness and superiority of their approaches over existing methods.
Predicting smartphone users location with WiFi fingerprints has been a popular research topic recently. In this work, we propose two novel deep learning-based models, the convolutional mixture density recurrent neural network and the VAE-based semi-supervised learning model. The convolutional mixture density recurrent neural network is designed for path prediction, in which the advantages of convolutional neural networks, recurrent neural networks and mixture density networks are combined. Further, since most of real-world datasets are not labeled, we devise the VAE-based model for the semi-supervised learning tasks. In order to test the proposed models, we conduct the validation experiments on the real-world datasets. The final results verify the effectiveness of our approaches and show the superiority over other existing methods.