Outdoor Node Localization Using Random Neural Networks for Large-Scale Urban IoT LoRa Networks

Accurate localization for wireless sensor end devices is critical, particularly Internet of Things (IoT) location-based applications such as remote healthcare, where there a need quick response to emergency or maintenance services. Global Positioning Systems (GPS) are widely known outdoor services; however, high-power consumption and hardware cost become significant hindrance dense networks in large-scale urban areas. Therefore, technologies Long-Range Wide-Area Networks (LoRaWAN) being investigated different location-aware IoT due having more advantages with low-cost, long-range, low-power characteristics. Furthermore, various methods, including fingerprint techniques, present the literature but limitations. This study uses LoRaWAN Received Signal Strength Indicator (RSSI) values predict unknown X Y position coordinates on publicly available dataset Antwerp Belgium using Random Neural (RNN). The proposed system achieves an improved high-level accuracy areas outperforms conventional LoRa-based systems other work, minimum mean error 0.29 m.