Network anomaly detection based on BQPSO-BN algorithm
Yuan Liu, Ruhui Ma · IETE Journal of Research · 2013
AbstractAs cloud computing becomes popular, intrusion detection has been focused again, since huge amount of network attacks have increased the requirement of efficient network intrusion detection techniques. Currently, lots of methods are used to solve this issue, but lower detection rate of these original models cannot satisfy complex Internet environment. In this paper, we propose a novel intrusion detection model–Bayesian Network-based binary quantum-behaved particle swarm optimization (BQPSO-BN). Since the classical QPSO algorithm only operates in continuous and real-valued space, and the problem of Bayesian networks learning is in discrete space, we redefine the position vector and the distance between two positions, and adjust the iterative equations of QPSO to binary search space. Experiment results with KDD’99 dataset show that BQPSO-BN is an efficient and effective algorithm and has better convergence speed compared with BPSO-BN and GA-BN models.