Deep neural network-based clustering technique for secure IIoT
- PDF / 965,030 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 325 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I. : APPLYING ARTIFICIAL INTELLIGENCE TO THE INTERNET OF THINGS
Deep neural network-based clustering technique for secure IIoT Amrit Mukherjee1 S. K. Mohapatra3
•
Pratik Goswami1 • Lixia Yang1 • Sumarga K. Sah Tyagi2 • U. C. Samal3
•
Received: 29 November 2019 / Accepted: 24 January 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The advent of Industrial Internet of Things (IIoT) has determined the proliferation of smart devices connected to the Internet and injected a vast amount of data into it, which may undergo many computational stages at several clusters. On the one hand, the benefits brought by these technologies are well known; however, in the envisaged scenario, the exposure of data, services and infrastructures to malicious attacks has definitely grown. Even a single breach on any of the links of the data–service–infrastructure chain may seriously compromise the security of the end-user application. Therefore, the logical and smart clustering while satisfying security and reliability is a key issue for IIoT networks. A novel clustering method proposed based on power demand assures security of data information in IIoT-based applications. First, security capacity of the system is calculated from mutual information of primary channel and eavesdropping channel. Then, under the maximum transmit power constraint, an optimal transmit power is found based on deep learning technique, which maximizes security capacity of the system. Finally, the network is clustered according to the calculated power demand. Experimental results accredit the proposed method has higher security and reliability, as well as lower network time overhead and power consumption. Keywords Power demand IIoT System’s security capacity Clustering Deep learning
1 Introduction With the development of 5G and artificial intelligence (AI), various emerging wireless communication technologies are rapidly developing. Demand of ultrafast and low latency wireless communication for the Internet of Things (IoT) will also be met [1, 2]. Here, AI is the key to unlock the potential of IoT and other future technologies. Therefore, it is important to embed intelligence in the IoT environment for efficient data transmission and resource allocation [3]
& Amrit Mukherjee [email protected] & Lixia Yang [email protected] 1
School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China
2
School of Electronic and Information, Zhongyuan University of Technology, Zhengzhou, China
3
School of Electronics Engineering, KIIT University, Bhubaneswar, India
among the physical layer, the network layer and the application layer to realize information ionization and automation. As an important research and application area of the IoT [4], WSNs must be indulged to achieve efficient data information perception, convergence and AI-based data information security, time delay and power consumption for IoT-based objects [5]. However, due to the openness of
Data Loading...
