Research of Indoor Positioning Based on Channel State Information Using Gated Convolutional Neural Network

• Main Authors: Cheng-CheHsiesh, 謝政哲
• Other Authors: Wen-Long Chin
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/32nsrs

碩士 === 國立成功大學 === 工程科學系 === 107 === Location-based service (LBS) has become important part in people’s life in recent years, but the global positioning system(GPS) restricted by the shielding effect and noise isn’t available in indoor environments. Therefore, how to accurtely locate in indoor environment has become a popuplar issue in recent years. This thesis uses the channel state information(CSI) combined with convolutional neural network(CNN) to achieve a highly accurate indoor positioning. The CSI refers to known channel properties of a communication link in wireless communications. This information describes how a signal propagates from the transmitter to the receiver and represents the combined effect of, for example, scattering, fading, and power decay with distance. In multi-carrier comunnication systems, the CSI of adjacent subcarriers has high correlation, and CNN is promising to learn the relationship of these input information. Beyond that, we propose and improve CNN, i.e., the gated CNN, which has more talent to locate in indoor environments than traditional CNNs. Experimental results show that the proposed gated CNN can achieve an accuracy of less than 0.08 m with 16 antennas. We aslo demonstrate the accuracy under different number of antennas. With only 2 antennas, the accuracy can still be within 0.3 m.