CSI-MIMO: K-nearest Neighbor applied to Indoor Localization

Abstract

Indoor Localization has attracted interest in both academia and industry for its wide range of applications. In this paper, we propose an indoor localization solution based on Channel State Information (CSI). CSI is a fine-grain measure of the effect of the channel on the transmitted signal. It is computed for each subcarrier and each antenna in the Multiple-Input-Multiple-Output (MIMO) antenna case. It is also becoming a trend for indoor position fingerprinting. By using a K-nearest neighbor learning method a highly accurate indoor positioning is achieved. The input feature is the magnitude component of CSI which is preprocessed to reduce noise and allow for a quicker search. The euclidean distance between CSI is the criteria chosen for measuring the closeness between samples. The method is applied to a CSI dataset estimated at an 8 × 2 MIMO antenna that is published by the organizers of the Communication Theory Workshop Indoor Positioning Competition. The proposed method is compared with three other methods all based on deep learning approaches and tested with the same dataset. The Knearest neighbor method presented in this paper achieves a Mean Square Error (MSE) of 2.4 cm which outperforms its counterparts.

Nearest neighbour methods and their applications in design of 5G & beyond wireless networks

“…Further, improvement is possible by considering APs with antenna arrays and utilising the channel state information (CSI) instead of RSS. This has been recently explored in [20]. Similar approaches can be adopted for finger-printing RSS from Bluetooth enabled devices.…”

Using Channel State Information for Physical Tamper Attack Detection in OFDM Systems: A Deep Learning Approach

“…Thus, the main difficulty in detecting a physical tamper attack in form of movement or relocation of transmitters or receivers is to distinguish between changes caused by the physical tamper attack and changes caused by modifications in the surrounding like persons walking by. Our goal is to use a machine learning approach applied to the magnitude of CSI [6] that detects tamper attacks on the transmitter despite changes in the environment.…”

Semi-supervised t-SNE for Millimeter-wave Wireless Localization

“…We now investigate the performance of the proposed St-SNE method for mmWave localization in more detail, and compare it with kNN [20] and semi-supervised Laplacian Eigenmap (SLE) [18] method. kNN is widely used in RSSIbased and CSI-based fingerprinting.…”

“…SLE is shown to be better than kNN in [18]. For kNN, a small k can obtain good performance [20] and we use k = 3 neighbors which achieves smallest MLE in kNN here.…”