Comparison of Machine Learning Algorithms for Localized GPS

Abstract

They are different positioning algorithms which are available to locate the position of person or target locations where GPS signal don’t reach, known as Local Positioning System (LPS) Algorithms. LPS uses same positioning algorithm like Triangulation, Trialteration, Proximity and Scene analysis with respect to Wi-Fi Access Point, Bluetooth devices etc. Triangulation, Trialteration, Proximity and Scene analysis makes use of signal properties such as Angle of Arrival (AoA), Time of arrival (ToA), Time difference of Arrival (TDOA) and Received signal strength indicator (RSSI) which is the conventional methods to locate the target. But in the Traditional Systems, Target Positioning Accuracy of all LPS is not at high precision Level. So we are employing Machine learning Algorithms to improve the accuracy and Precision of LPS. Principal component analysis (PCA), Support vector machines (SVN) and Linear Regression algorithms are employed with LPS Algorithms to improve the accuracy and results are being compared.