Energy efficient classification approach for the detection of interference and malicious sensor node detection in wireless body area network

Abstract

Wireless Body Area Network (WBAN) is the specific type of Wireless Sensor Networks (WSN) to detect and diagnose the disease in the human body in an effective manner. WBAN networks are used for the human in health care monitoring in their daily life in order to predict the disease in human body. A typical WBAN contains a set of wireless sensors which are placed over the various part of the human body to capture the condition of the body and all these sensor nodes are connected to the body center in WBAN networks. The wireless sensor nodes observe only physiological parameter from the human body. The body head is also a sensor node which is placed in human body which collects the sensed data from various sensors and controls the body sensors. This thesis proposes a hybrid interference detection technique based on features and classification approach. The proposed methodology extracts the features from individual WBAN networks, which is connected to the local server. These features are trained and classified by Support Vector Machine (SVM) classifier to detect the interference of an individual WBAN newlinenetwork. The performance of the proposed interference detection algorithm is analyzed in terms of network utility factor, packet delivery ratio and average newlineenergy consumption of the networks. The soft computing based sensor node classification in WBAN network is proposed in this thesis using GA. This methodology can be operated in training which trains the input pattern and testing which is used to test the individual nodes in WBAN network. Initially, the features are extracted from the trusted and un-trusted nodes of WBAN network newline newline