An Integrated Grasshopper Optimization Algorithm with Artificial Neural Network for Trusted Nodes Classification Problem

Wireless Body Area Network (WBAN) is a tool that improves real-time patient health observation in hospitals, asylums, especially at home. WBAN has grown popularity in recent years due to its critical role and vast range of medical applications. Due to the sensitive nature of the patient information being transmitted through the WBAN network, security is of paramount importance. To guarantee the safe movement of data between sensor nodes and various WBAN networks, a high level of security is required in a WBAN network. This research introduces a novel technique named Integrated Grasshopper Optimization Algorithm with Artificial Neural Network (IGO-ANN) for distinguishing between trusted nodes in WBAN networks by means of a classification approach, hence strengthening the safety of such networks. Feature extraction process is done by using Linear Regression-Based Principal Component Analysis (LR-PCA). The test results demonstrated that the proposed IGO-ANN method attains the greatest performance in terms of accuracy, end to end delay and packet delivery ratio regarding trusted WBAN nodes classification than certain existing methods.