DNN-based WiFi positioning in 3GPP indoor office environment

As the development of the 4th industry begins, LBS(Location Based Service) technology is drawing attention. AI(Artificial Intelligence), IoT(Internet of Things), and Big Data, which are major technologies of the 4th industry, can be effectively applied to these LBS technologies. In addition, in order to provide LBS technology to users in an indoor environment, the positioning results must be provided in real time. Therefore, in this paper, we propose a scheme for providing real-time user positioning results based on AI technology. The proposed scheme is based on Wi-Fi(Wireless Fidelity) communication, and applies DNN(Deep Neural Network), one of the AI technologies, for location positioning in the indoor office environment proposed by 3GPP(The 3rd Generation Partnership Project). In order to perform the user's location positioning, the DNN model learns the RSSI(Received Signal Strength Indicator) value of a specific location collected in the offline step and the corresponding location with one label. After that, in the online step, the location of the actual user is estimated based on the learned model. It can be seen that the proposed scheme achieves higher performance than the existing scheme in terms of processing time for performing positioning through simulation. This can be considered in order for the scheme to achieve real-time location positioning later.