Data secure transmission intelligent prediction algorithm for mobile industrial IoT networks

Abstract

Mobile Industrial Internet of Things (IIoT) applications have achieved the explosive growth in recent years. The mobile IIoT has flourished and become the backbone of the industry, laying a solid foundation for the interconnection of all things. The variety of application scenarios has brought serious challenges to mobile IIoT networks, which face complex and changeable communication environments. Ensuring data secure transmission is critical for mobile IIoT networks. This paper investigates the data secure transmission performance prediction of mobile IIoT networks. To cut down computational complexity, we propose a data secure transmission scheme employing Transmit Antenna Selection (TAS). The novel secrecy performance expressions are first derived. Then, to realize real-time secrecy analysis, we design an improved Convolutional Neural Network (CNN) model, and propose an intelligent data secure transmission performance prediction algorithm. For mobile signals, the important features may be removed by the pooling layers. This will lead to negative effects on the secrecy performance prediction. A novel nine-layer improved CNN model is designed. Out of the input and output layers, it removes the pooling layer and contains six convolution layers. Elman, Back-Propagation (BP) and LeNet methods are employed to compare with the proposed algorithm. Through simulation analysis, good prediction accuracy is achieved by the CNN algorithm. The prediction accuracy obtains a 59% increase.

Keywords

• Mobile IIoT networks
• Data secure transmission
• Performance analysis
• Intelligent prediction
• Improved CNN