Comparative Analysis of Machine Learning Algorithms for LOS/NLOS Identification

Identification of Line of Sight (LOS) and Non Line of Sight (NLOS) is a challenging task since majority of physical effects that take place at distinct temporal/spatial conditions can affect the LOS propagation. Ultra Wide Band communication technology is the key technology in indoor positioning to identify LOS and NLOS communication channels in different environmental conditions. Different machine learning algorithms are used to identify on the basis of various training feature which basically exploits several static and time-varying features of the channel impulse response (CIR).In ML, the choice of training features plays a crucial role. The paper addresses machine learning techniques i.e. K-Nearest neighbour, Logistic Regression, Support Vector Machine and Random Forest in terms of their performance on different parameters.