Machine learning in indoor localization prediction using Received Signal Strength Indicator and Wi-Fi network

Abstract

Indoor usage of smartphones and electronic devices can be a source of information to detect the indoor location, which is known as localization. Though the Global Positioning System (GPS) provides many effective location services using satellite signals, indoor localization is not included. Therefore, several technologies have been used for indoor localization, including Wireless Fidelity (Wi-Fi), Bluetooth Low Energy (BLE), and Received Signal Strength Indicator (RSSI), it has resulted in the proposal of Machine Learning (ML)-based indoor localization methodologies. Unlike the RSSI that indicates how well your device can hear a signal in a Wi-Fi network, this paper proposes indoor localization prediction using ML techniques based on Wi-Fi RSSI fingerprinting methodologies, encompassing data preprocessing, such as Data Cleansing (DC), Future Tuning (FT), and Feature Selection (FS). The proposed ML prediction models for indoor localization classifiers investigation in this paper are Support Vector Machine (SVM), K Nearest Neighbors (KNN), Decision Trees (DT), Random Forest (RF), and Linear Regression (LR). Moreover, a comprehensive performance comparison for the proposed prediction models is performed in this paper using nine datasets with different areas in a total of 31,470 records. The results show that KNN achieved the best performance for all parameters, making it the most recommended classifier for RSSI fingerprinting schemes.