«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

24

期数:

2014年07期

页码:

29-33

栏目:

出版日期:

2014-07-10

文章信息/Info

Title:

 Chaotic RBF Neural Network Anomaly Detection Algorithm

文章编号:

1673-629X（2014）07-0029-05

作者:

 翁鹤; 皮德常

 南京航空航天大学 计算机科学与技术学院

Author(s):

 WENG He ; PI De-chang

关键词:

 ; 电力负荷; 相空间重构; 混沌时间序列; RBF神经网络; 异常检测

Keywords:

 ; electricity load; phase space reconstruction; chaotic time series; RBF neural network; anomaly detection

分类号:

TP183

文献标志码:

A

摘要:

 针对传统神经网络异常检测算法的准确率问题，文中将混沌和RBF( Radial Basis Function)神经网络相结合，既可利用混沌的随机性、初值敏感性等特点，也可发挥RBF神经网络大规模并行处理、自组织自适应性等功能。文中对混沌时间序列进行相空间重构得到相空间向量，作为RBF神经网络的输入，通过RBF神经网络构建电力负荷序列的拟合函数，在此基础上进一步预测，比较预测值与真实值的偏差，从而判断检测信号是否为异常信号。实验结果表明，该方法相对其他算法预测精度更高，具有较好的异常检测能力。

Abstract:

 For the accuracy problem of traditional neural network anomaly detection algorithm,propose a method of combining chaos and RBF ( Radial Basis Function) neural network,not only can take advantages of the randomness and initial value sensitivity and others of chaos,but also make use of the large-scale parallel processing,self-organization and adaptive capability of RBF neural networks. Recon-struct the chaotic time sequence to obtain the phase space vector as the input of RBF neural network,by which build the electricity load sequence fitting function. Then use this function to take one-step prediction in the phrase space reconstruction. At last,compare predicted value and true value of the deviation,in order to determine whether the abnormal signal or detection signal. Experimental results show that this method has better prediction accuracy and anomaly detection capabilities.

常用功能

更新日期/Last Update: 2015-03-12