计算机应用 ›› 2017, Vol. 37 ›› Issue (3): 782-785.DOI: 10.11772/j.issn.1001-9081.2017.03.782

• 人工智能 • 上一篇    下一篇

基于Plane-Gaussian神经网络的网络流状态监测

杨绪兵1, 冯哲1, 顾一凡1, 薛晖2   

  1. 1. 南京林业大学 信息科学技术学院, 南京 210037;
    2. 东南大学 计算机科学与工程学院, 南京 210096
  • 收稿日期:2016-07-25 修回日期:2016-08-02 出版日期:2017-03-10 发布日期:2017-03-22
  • 通讯作者: 杨绪兵
  • 作者简介:杨绪兵(1973-),男,安徽六安人,副教授,博士,主要研究方向:模式识别、神经计算;冯哲(1992-),女,江苏常州人,硕士研究生,主要研究方向:模式识别、神经计算;顾一凡(1996-),男,江苏无锡人,主要研究方向:数据分析;薛晖(1979-),女,江苏南京人,副教授,博士,主要研究方向:人工智能。
  • 基金资助:
    国家自然科学基金资助项目(61375057);江苏高校品牌专业建设工程资助项目。

Network traffic classification based on Plane-Gaussian artificial neural network

YANG Xubing1, FENG Zhe1, GU Yifan1, XUE Hui2   

  1. 1. College of Information Science and Technology, Nanjing Forestry University, Nanjing Jiangsu 210037, China;
    2. School of Computer Science and Engineering, Southeast University, Nanjing Jiangsu 210096, China
  • Received:2016-07-25 Revised:2016-08-02 Online:2017-03-10 Published:2017-03-22
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61375057) and Top-notch Academic Programs Project of Jiangsu Higher Education Institutions (TAPP).

摘要: 针对复杂网络环境下网络流监测(分类)问题,为实现多个类别直接分类以及提高学习方法的训练速度,提出了一种随机的人工神经网络学习方法。该方法借鉴平面高斯(PG)神经网络模型,引入随机投影思想,通过计算矩阵伪逆的方法解析获得网络连接矩阵,理论上可证明该网络具有全局逼近能力。在人工数据和标准网络流监测数据上进行了实验仿真,与同样采用随机方法的极限学习机(ELM)和PG网络相比,分析与实验结果表明:1)由于继承了PG网络的几何特性,对平面型分布数据更为有效;2)采用了随机方法,训练速度与ELM相当,但比PG网络快得多;3)三种方法中,该方法更有利于解决网络流监测问题。

关键词: Plane-Gaussian人工神经网络, 极限学习机, 随机投影, 全局逼近, 分类精度

Abstract: Aiming at the problems of network flow monitoring (classification) in complex network environment, a stochastic artificial neural network learning method was proposed to realize the direct classification of multiple classes and improve the training speed of learning methods. Using Plane-Gaussian (PG) artificial neural network model, the idea of stochastic projection was introduced, and the network connection matrix was obtained by calculating the pseudo-inverse analysis. Theoretically, it can be proved that the network has global approximation ability. The artificial simulation was carried out on artificial data and standard network flow monitoring data. Compared with the Extreme Learning Machine (ELM) and PG network using the random method, the analysis and experimental results show that: 1)the proposed method inherits the geometric characteristics of the PG network and is more effective for the planar distributed data; 2)it has comparable training speed to ELM, but significantly faster than PG network; 3)among the three methods, the proposed method is more suitable for solving the problem of network flow monitoring.

Key words: Plane-Gaussian (PG) artificial neural network, Extreme Learning Machine (ELM), random projection, global approximation, recognition accuracy

中图分类号: