Applying Deep Neural Network (DNN) for large-scale indoor localization using feed-forward neural network (FFNN) algorithm

In Internet of things (IoT), indoor localization plays a vital role in everyday applications such as locating mobile users, location-based mobile advertising and requesting nearest business. Received Signal Strength (RSS) is used due to minimum cost, less operational complexity, and easy usages. In this work, we proposed a Feed-Forward Deep Neural Network (FF-DNN) Algorithm. The simulation result shows 53.123%, 78.123% and 100% of the accuracy has estimation error less than 0.5, 0.75 and 1 meters respectively. The RMSE is 0.32.