Secure Data transmission in wireless networking through node deployment and Artificial Bird optimized Deep Learning Network

Abstract

Wireless Sensor Networks (WSNs) engage in monitoring, collecting, and communicating sensitive data from the application area to the sink node through the cluster heads (CHs). During the data transmission, there are chances that faulty nodes are available in the network, which increases the chances of communicating the data with the unauthorized nodes in the network. Therefore, in this research, secure data transmission is concentrated for which the messages and monitored WSN data are encrypted using the Hybrid encryption algorithm before the communication, which ensures data access only for the genuine nodes. Accordingly, the node status is assessed to ensure the fault-free nodes through the duty cycle management scheme based on the proposed Artificial Bird Optimized Deep Learning Model (ABO-deep CNN Model). The research aims to develop secure data transmission in WSN by effectively managing the duty cycles of sensor nodes and handling the security issues of the data transmission through the authentication scheme that is based on encryption schemes. Utilizing the Regional K-means approach allows for selecting energy-efficient heads to facilitate data transmission. Following the optimized Deep CNN to determine the state of the nodes, the data transmission takes place through the Hybrid encryption algorithm that allows the transmission with identical data decryption. In addition, the energy-efficient routes are selected using ABO for communicating the data securely in the WSNs. At the round of 1500, the proposed ABO-deep CNN WSN is evaluated with alive nodes, delay, energy, and, throughput of 90, 0.034 ms, 0.38J, and 0.30bps respectively for 200 nodes analysis which outperformed other existing methods and attained high efficiency.