Applied Research on Discriminative-Adaptive Neural Network Algorithm in Indoor Positioning System

in this paper, a three-layer Discriminative-Adaptive Neural Network algorithm (DANN) is proposed in indoor Positioning System. By using Multivariate Discriminant Analysis, a weight matrix could be acquired, then it could input these weighting signals into the Neural Network for training, and it could get a minimum mean square error, finally, we could get the Minimum error positioning results. Experimental results show that using DANN algorithm can obviously improve the indoor positioning precision and speed.