隨著網(wǎng)絡(luò)技術(shù)和網(wǎng)絡(luò)規(guī)模的不斷發(fā)展，網(wǎng)絡(luò)安全已經(jīng)成為人們無法回避的問題，因此為了保護(hù)現(xiàn)在越來越多的敏感信息，入侵檢測技術(shù)也成為了一種非常重要的技術(shù)，得到了越來越多的重視。然而對其中一個重要部分―特征的自動選擇的研究非常少。本文提出了一個EA 用來執(zhí)行特征的自動選擇以及對RBF 網(wǎng)絡(luò)的自動優(yōu)化。經(jīng)過特征選擇這個步驟可以顯著的減少輸入特征的數(shù)量，這樣可以有效的減少過適應(yīng)。此外，減少輸入特征數(shù)目，還可以減少神經(jīng)網(wǎng)絡(luò)的執(zhí)行時間。
關(guān)鍵詞：入侵，入侵檢測，神經(jīng)網(wǎng)絡(luò)，特征選擇。

Abstract: With the ongoing growth of the Internet, intrusion detection systems (IDS) play an increasing role in securing communication networks. Although, feature selection is an important task for almost all neural network applications, only very few investigations
dealing with any type of automated feature selection are known in the area of intrusion? detection. This article sets ant an evolutionary algorithm (EA) that performs the tasks of feature selection and architecture optimization for radial basis function (RBF) networks
automatically.
Key Words: IDS, neural network, feather selection.