Wireless broadcast systems provide an indispensable act in real-life circumstances and permit an extensive range of services based on the users' location. The forthcoming implementation of universal 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 indispensable tool to afford compact enactment for the location-based system to increase accuracy and reduce computational time, proposed a Cost-Effective Machine Learning based Localization (CEMLL) algorithm. CEMLL algorithm is assessed with considered localization algorithms, explicitly Support Vector Machine for Regression (SVR), Artificial Neural Network (ANN), and K-Nearest Neighbor (KNN). Numerous outcomes specify that the CEMLL algorithm has comparable correctness equated to state art algorithms. The results are assessed on different parameters, and CEMLL achieves better results in localization error 12%-15%, cumulative probability 18%-20%, root mean square error 13%-17%, distance error 16%-19%, and computational time 21%-23% than SVR, ANN, and KNN.

WSN, Localization, Machine Learning, SVR, ANN, KNN, and CEMLL.