Machine Learning Approach towards LoRaWAN Indoor Localization

The growth of the Internet Things (IoT) continues to be rapid, making it an essential part information technology. As a result, IoT devices must able handle data collection, machine-to-machine (M2M) communication, and preprocessing data, while also considering cost, processing power, energy consumption. This paper introduces system for device indoor localization that uses variations in strength wireless signal. proposed addresses logistics use cases which is imperative achieve reliable end-to-end delivery, such as pharmaceutic delivery confidential documents court exhibits, even food, since same introduced into human organism presents potential risk terrorist or other attack. work proposes concept based on low-power low-cost LoRaWAN utilizes Machine Learning technique Neural Networks high accuracy by measuring signal beacon device. Furthermore, using measurements, is, RSSI SNR captured gateways, possible estimate location point with up 98.8%.