【摘要】：為更好實現(xiàn)對入侵檢測樣本數(shù)據(jù)的優(yōu)化處理,提出了一種改進的快速獨立成分分析(Fast ICA)算法,采用基于加權相關系數(shù)進行白化處理以減少信息損失,并優(yōu)化牛頓迭代法使其滿足三階收斂。對算法進行了細致描述,分析了算法的時間復雜度。實驗結(jié)果表明,該方法可有效減少數(shù)據(jù)信息損失,具有迭代次數(shù)少、收斂速度快等優(yōu)點,可有效提高入侵檢測樣本數(shù)據(jù)的優(yōu)化效率。
[Abstract]:In order to achieve the optimal processing of intrusion detection sample data, an improved fast independent component analysis (Fast ICA) algorithm is proposed, which is whitened based on weighted correlation coefficient to reduce information loss. The Newton iteration method is optimized to satisfy the third order convergence. The algorithm is described in detail and its time complexity is analyzed. Experimental results show that this method can effectively reduce the loss of data information, has the advantages of less iteration times and faster convergence speed, and can effectively improve the optimization efficiency of intrusion detection sample data.
【作者單位】： 北京交通大學計算機與信息技術學院;
【基金】：北京高校青年英才計劃基金資助項目(No.YETP0548) 中央高校基本科研業(yè)務費基金資助項目(No.2014JBM030) 國家自然科學基金資助項目(No.61102105)~~
【分類號】：TP393.08

【相似文獻】

相關期刊論文 前1條

1 王建新;彭娜;;廣域網(wǎng)加速技術研究綜述[J];電信快報;2009年05期

，

本文編號：2340299