An anomaly detection algorithm in wireless sensor networks based on rough set theory and support vector machine

作者：Liang Guangwei; Sun Ziwen^*; Ji Zhicheng

来源：Journal of Computational Information Systems, 2013, 9(15): 6269-6276.

DOI：10.12733/jcisP0635

• Anomaly detection
• Anomaly-detection algorithms
• Attribute reduction
• Cluster-based
• Dimensionality reduction
• False negative rate
• False positive rates
• Support vector machine classification

An anomaly detection algorithm, which is based on rough set theory and support vector machine, is proposed to ensure the security of cluster-based wireless sensor networks. In the algorithm, the dimensions of samples are reduced by using the rough set theory based attribute reduction and then the samples are used to train the support vector machine classification model whose parameters are optimized by the genetic algorithms in the base station. The trained model is used to detect anomaly in the cluster head later. The simulation results show that the feature dimensionality reduction and using of the genetic algorithms to optimize the parameters of the support vector machine can improve both false positive rate and false negative rate effectively.

• 出版日期2013
• 单位江南大学