Indoor Localization of Industrial IoT Devices and Applications Based on Recurrent Neural Networks

Abstract

Industrial Internet of Things (IIoT) has become an indispensable element of smart industrial facilities, predicted to continue to grow at a rapid rate. Wireless technologies have become a standard part of today’s industrial facilities with applications including programming and control of electric drives, remote system and environment monitoring and fault diagnostics of industrial equipment. However, installation of physical connections can be time consuming and require substantial economic resources, especially when considering long-term maintenance costs. With that regard, IoT applications that use sensor technology, RFID technology, network communication, data mining and machine learning could prove to be quite efficient in solving the previously presented problem of localization. A new indoor localization algorithm has been introduced based on recurring neural networks (RNNs) for the positioning of indoor devices. Experiments were conducted in relatively complex surroundings of a faculty building. According to experimental results, the presented system surpasses the state-of-the-art algorithms and can achieve 98.6% localization accuracy of indoor devices.

Keywords