As the energy and computing ability are limited in wireless sensor networks, so almost all of the traditional network intrusion detection schemes cannot be applied. That WSN’s intrusion detection based on Kernel Fisher Discriminant and SVM is brought forward. According to the principle that the classifiers’ sensitivity is different when different types of data is processed, the data is assigned to Kernel Fisher Discriminant and SVM. So that Data can be processed by the corresponding optimal classifier, and detection efficiency can be raised. Theoretical analysis and simulation results show that the proposed schemes not only can detect intrusions effectively, but also lower energy consumption than others.
CITATION STYLE
Hu, Z., Zhang, J., & Wang, X. A. (2017). Intrusion detection for WSN based on kernel fisher discriminant and SVM. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 1, pp. 197–208). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-49109-7_19
Mendeley helps you to discover research relevant for your work.