Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems

TL;DR

This paper introduces two deep learning models for indoor positioning using WiFi fingerprints, combining path prediction and semi-supervised learning to improve accuracy on real-world datasets.

Contribution

The paper presents novel convolutional mixture density recurrent neural networks and VAE-based semi-supervised models for indoor positioning, addressing labeled data scarcity.

Findings

Models outperform existing methods in accuracy

Effective semi-supervised learning with unlabeled data

Validated on real-world WiFi datasets

Abstract

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.