In mobile ad hoc networks, the isolation of critical routing nodes may affect the routes and re-routing that result in significant routing disruption. This in turn degrades the network performance considerably. The existing anomaly-based detection and prevention technique does not involve any standard training technique like neural networks, support vector machines (SVMs) and so on. In order to overcome these issues, in this paper, it is proposed to design a SVM and fuzzy-based intrusion detection and prevention for MANET attacks. Initially, the nodes with the maximum stability index are chosen as cluster heads (CH) and the other nodes become cluster members (CM). The secure communication is established between CH and CMs. Then a support vector machine is utilised to distinguish misbehaving nodes from well-behaved nodes. Then fuzzy rules are used to isolation of misbehaving nodes to prevent intrusion. By simulation result, it is shown that the proposed technique enhances the network performance. 'Implementation of ADALINE on DSP and FPGA for measurement of harmonics'. He has completed more than 30 industrial consultancy projects in embedded systems, power quality studies and energy conservation. His areas of interest are embedded systems, neuro-fuzzy systems, power quality improvement and energy conservation.