Machine Learning Based Localization Techniques

Internet of Things (IoT) is growing at a pace that can be called ubiquitous. IoTs can be nominated as a subfield of a superset known as Wireless Sensor Networks (WSNs). These sensors are used for remote monitoring, target tracking, efficient transportation, industrial monitoring, patient observation through physiological sensors, smart agriculture, smart homes, disaster monitoring and efficient management, and many other useful applications. Estimation of the location of wireless sensor nodes is known as Localization. Localization finds useful applications both indoors and outdoors. Different methods can be used to estimate the location; these include both range-based and range-free localization techniques. We apply supervised machine learning algorithms to estimate the performance of Localization using Received Signal Strength Indicator (RSSI) also known as Received Power, as a parameter for wireless sensor networks. The IEEECTW Challenge 2019 localization dataset for 1.25 GHz is used for training purposes. It consists of 16 elements of OFDM sounding data. The data set is collected through a massive MIMO channel sounder. Four algorithms are used for the purpose. The results show M