In the last years, location intelligence systems have been characterized by an increasing interest in several sectors. Among them, those of emergencies are mainly involved in order to enhance the rescue procedures and to reduce the intervention time, especially within indoor environment where GPS does not support the emergency operations. The authors define a low cost location intelligence system based on Channel State Information (CSI) of Wi-Fi and low-energy ESP32 SoC platform to analyze CSI data of Wi-Fi Signals. The technical solution utilizes wavelet filter to remove background noise in the CSI data, Principal component analysis (PCA) to reduce the dimensionality of the CSI data and get the most valuable data that are used as feature for the defined DNN model. The experimental results show the best performance of this model compared to the other machine learning (ML) algorithms analysed.