Indoor Fingerprinting Localization Based on Fine-grained CSI using Principal Component Analysis

Abstract

With the development of Wi-Fi technology, the IEEE 802.11n series communication protocol and the subsequent wireless LAN protocols use multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) technologies. Channel state information (CSI) fingerprint positioning technology based on fine-grained channel state information is widely used in the field of WIFI indoor positioning. However, the propagation of CSI is still affected by indoor multipath, and we cannot obtain signals in some corner areas. Therefore, CSI needs a suitable calibration method to improve the accuracy of the position estimation system. This paper proposes a fine-grained CSI fingerprint location algorithm based on Principal Component Analysis (PCA). This novel algorithm uses a dimensionality reduction method on the basis of the Discrete Wavelet Transform (DWT) to optimize, eliminate the noise and redundancy of the original data and reduce the positioning error. Experimental results show that the proposed approach achieves significant localization accuracy improvement over using the RSSI fingerprint method and original CSI fingerprint method, while it incurs much less computational complexity. Meanwhile, the algorithm improves the influence of multiple paths in a complex indoor environment on location, and the method can obtain more accurate location results.