Improved RSSI Indoor Localization in IoT Systems with Machine Learning Algorithms

Recent developments in machine learning algorithms are playing a significant role wireless communication and Internet of Things (IoT) systems. Location-based services (LBIoTS) considered one the primary applications among those IoT applications. The key information involved LBIoTS is finding an object’s geographical location. Global Positioning System (GPS) technique does not perform better indoor environments due to multipath. Numerous methods have been investigated for localization scenarios. However, precise location estimation moving object such application challenging high signal fluctuations. Therefore, this paper presents estimate based on Received Signal Strength Indicator (RSSI) values collected through Bluetooth low-energy (BLE)-based nodes. In experiment, we utilize publicly available RSSI dataset. data from different BLE ibeacon nodes installed complex environment with labels. Then, linearized using weighted least-squares method filtered average filters. Moreover, used training testing dataset objects. All proposed were tested evaluated under their hyperparameters. models provided approximately 85% accuracy KNN, 84% SVM 76% FFNN.