MLCEL: Machine Learning and Cost-Effective Localization Algorithms for WSNs

Abstract

Wireless communication systems provide an indispensable act in real-life scenarios and permit an extensive range of services based on the users' location. The forthcoming implementation of versatile localization networks and the formation of subsequent generation Wireless Sensor Network (WSN) will permit numerous applications. In this perspective, localization algorithms have converted into an essential tool to afford compact implementation for the location-based system to increase accuracy and reduce computational time, proposing a Machine Learning and Cost-Effective Localization (MLCEL) algorithm. MLCEL algorithm is assessed with considered localization algorithms called Support Vector Machine for Regression (SVR), Artificial Neural Network (ANN), and K-Nearest Neighbor (KNN). Numerous outcomes show that the MLCEL algorithm performs better than state art algorithms. The results are assessed on different parameters, and MLCEL achieves better results in localization error 13%-16%, cumulative probability 19%-21%, root mean square error 14%-18%, distance error 17%-20%, and computational time 22%-24% than SVR, ANN, and KNN.