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

Low-Power, Wide-Area Networks (LPWAN) are projected to support a significant number of devices within the Internet of Things (IoT). Long-Range Wide Area Network (LoRaWAN) is an open specification and emerging LPWAN connectivity solution for IoT platforms. However, LoRaWAN network performance in urban scenarios is a fundamental research topic with limited exploration and characteristic analysis. In this paper, ATDI ICS Telecom is used to investigate LoRaWAN radio network coverage at 868 MHz using the Okumura-Hata, COST-231 Hata, Extended Hata, and ITU-R 1225 propagation models. The predicted received signal strength simulation results are compared with real-world test measurements taken in the urban environment of Glasgow City to evaluate various propagation models' accuracy. The proposed work demonstrates ITU R 225 and Extended Hata overestimated the real measured received signal strength power whereas, COST-231 Hata and Okumura-Hata underestimated the same signal power. Our results and analysis give important insights into the performance, evaluation, and comparison of existing propagation models for IoT connectivity with LoRaWAN technology within an urban environment.

Global Positioning Systems (GPS) are frequently used as a potential solution for localization applications. However, GPS does not work indoors due to a lack of direct Line-of-Sight (LOS) satellite signals received from the End Device (ED) due to thick solid materials blocking the ultra-high frequency signals. Furthermore, fingerprint localization using Received Signal Strength Indicator (RSSI) values is typical for localization in indoor environments. Therefore, this paper develops a low-power intelligent localization system for indoor environments using Long-Range Wide-Area Networks (LoRaWAN) RSSI values with Random Neural Networks (RNN). The proposed localization system demonstrates 98.5% improvement in average localization error compared to related studies with a minimum average localization error of 0.12 m in the Line-of-Sight (LOS). The obtained results confirm LoRaWAN-RNN-based localization systems suitable for indoor environments in LOS applied in big sports halls, hospital wards, shopping malls, airports, and many more with the highest accuracy of 99.52%. Furthermore, a minimum average localization error of 13.94 m was obtained in the Non-Line-of-Sight (NLOS) scenario, and this result is appropriate for the management and control of vehicles in indoor car parks, industries, or any other fleet in a pre-defined area in the NLOS with the highest accuracy of 44.24%.