Recurrent neural networks model for WiFi-based indoor positioning system

This research focus on the implementation of recurrent neural networks (RNN) model for indoor positioning system (IPS). Unlike global positioning system (GPS), IPS is used in closed structures such as hospitals, museums, shopping centers, office buildings, and warehouses. Positioning system is a key aspect in IPS. We propose, implemented, and evaluated an RNN model for positioning system. We used Wi-Fi-based IPS dataset from our previous research and made some comparison of RNN model performance with other methods. From the model evaluation results, we can conclude that RNN model is suitable for Wi-Fi-based IPS. It also produces generally higher accuracy compared with multi-layer perceptron model (MLP), Naïve Bayes, J48, and SVM. The RNN model training process still needs some tweaking on the parameters used in training.