The Indoor Positioning System Using Fingerprint Method Based Deep Neural Network

International Conference on SMART CITY Innovation 2018

Malik, R.F.^1 ; Gustifa, R.^1 ; Farissi, A.^1 ; Stiawan, D.^1 ; Ubaya, H.^1 ; Ahmad, M.R.^2 ; Khirbeet, A.S.^2

Communication Network and Information Security Research Lab, Faculty of Computer Science, Universitas Sriwijaya, Jalan Srijaya Negara Bukit Besar, Bukit Lama, Ilir Bar. I, Sumatera Selatan, Palembang

30128, Indonesia^1

Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka, Jalan Hang Tuah Jaya, Durian Tunggal, Melaka

76100, Malaysia^2

关键词: Fingerprint method;    Hidden layers;    Indoor environment;    Input layers;    Position estimation;    Received signal strength;    Reference points;    Wi-fi access points;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/248/1/012077/pdf
DOI  :  10.1088/1755-1315/248/1/012077

来源: IOP

【 摘 要 】

Highly dynamic indoor environments being one of the challenge in the Indoor Positioning System (IPS). Collecting the Received Signal Strength (RSS) value from every WiFi access point known fingerprint method is presented by previous researchers. They proposed with different techniques in fingerprint methods to compete similar existing technology such as GPS in term of accuracy. The drawback using fingerprint is the IPS cannot maintain the high performance constantly. In this research, we propose the Deep Neural Network (DNN) algorithm for improving the fingerprint method in the IPS. Basically, the fingerprint method consists of two phases, Online and Offline phases. In the off-line, RSS values will be collected from several coordinates as known reference points and stored in the database. The online phase has different step which the current position will be compared to RSS values stored in the database. The DNN method was used to calculate the closest position estimation probability. The IPS using DNN was successfully applied using 5 layers consisting of a 1 input layer, 3 hidden layers and 1 output layer. The input and hidden layer have 28 nodes for each layers and output layer has 2 nodes. The simulation results from RSS data set has achieved 2 meters accuracy. It concluded that DNN performance depends on the number of hidden layers and the number of nodes in each hidden layer.