Smart Sensor Networks for Industrial IoT Applications

Abstract

Smart Sensor Networks (SSNs) are an indispensable part of the Industrial Internet of Things (IIoT), which seeks to improve efficiency, productivity, and safety in different industrial applications. SSNs consist of a large number of sensors, regularly deployed in a wireless ad-hoc network, which communicates with each other and with other devices, such as gateways and servers. Nevertheless, the building of SSNs in IIoT environments encounters many challenges, such as trust management, data reliability, privacy, and security. These challenges necessitate proposing novel solutions and protocols, to provide a reliable, secure, and efficient SSN. To this end, this study presents a novel DL system that can effectively discriminate between normal traffics and malicious traffic in SSNs. A convolutional feature extractor is developed to learn important discriminative features necessary for the early detection of security threats in SSNs. Then, an improved LSTM (ILSTM) is presented to model the temporal dynamics of the SSNs flows, which helps model long interdependency between traffic samples. A focal loss function is applied to deal with the imbalance between class samples. Experimental analysis is performed on an open-source SSN security dataset, named WSN-DS, the findings demonstrated the competitive advantages of our system over the prevailing solutions.