[1]许少华,李盼池,何新贵.一种概率过程神经元网络模型及分类算法[J].智能系统学报,2009,4(04):283-287.
 XU Shao-hua,LI Pan-chi,HE Xin-gui.Combined probabilistic process neural network and classification algorithm[J].CAAI Transactions on Intelligent Systems,2009,4(04):283-287.
点击复制

一种概率过程神经元网络模型及分类算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第4卷
期数:
2009年04期
页码:
283-287
栏目:
出版日期:
2009-08-25

文章信息/Info

Title:
Combined probabilistic process neural network and classification algorithm
文章编号:
1673-4785(2009)04-0283-05
作者:
许少华12李盼池1何新贵2
1.大庆石油学院 计算机与信息技术学院,黑龙江 大庆 163318;
2.北京大学 信息科学技术学院,北京 100871
Author(s):
XU Shao-hua12 LI Pan-chi1 HE Xin-gui2
1. School of Computer and Information Technology, Daqing Petroleum Institute, Daqing 163318, China;
2. School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
关键词:
动态信号分类贝叶斯规则概率过程神经元网络
Keywords:
dynamic signal classification Bayesian rules probabilistic process neural networks
分类号:
TP183
文献标志码:
A
摘要:
针对动态信号分类及与先验类别知识融合问题,提出了一种概率过程神经元网络模型.模型将贝叶斯概率分类机制与过程神经元网络动态信号处理方法相结合,通过在前馈过程神经元网络中增加一个模式单元层,以及采用归一化指数类型激励函数,实现基于贝叶斯规则的动态信号分类.分析了概率过程神经元网络分类机制与贝叶斯分类规则的等价性,给出了具体的学习算法,实验结果验证了模型和算法的有效性.
Abstract:
A probabilistic process neural network has been proposed in order to provide integration of a priori knowledge with dynamic information classification. In this model, Bayesian classification was combined with the dynamic information processing of process neural networks. Dynamic information classification based on Bayesian rules was realized by adding a pattern neuron layer and a summing neuron layer to a feed forward process neural network and applying the normalized exponential activation function to the hidden layer. Classification equivalence between probabilistic process neural networks and Bayesian rules was analyzed and a concrete learning algorithm presented. Experimental results showed the effectiveness of the proposed model and algorithm.

参考文献/References:

[1]SPECHT D F. Probabilistic neural networks for classification mapping, or associative memory[C]//Proceedings of IEEE International Conference on Neural Networks. San Diego,CA,1988:525532.
 [2]史忠植. 神经网络[M]. 北京:高等教育出版社,2009: 203208.
[3]SPECHT D F. Probabilistic neural networks[J]. Neural Networks, 1990, 3(1): 109118.
[4]SPECHT D F, SHAPIRO P D. Generalization accuracy of probabilistic neural networks compared with back propagation networks[C]//International Joint Conference on Neural Networks(IJCNN91). Singapore:1991:887892.
[5]蔡曲林.一种新的概率神经网络有监督学习算法[J].模糊系统与数学,2006,20(6):8387.
CAI Qulin. New supervised learning algorithm for probabilistic neural network[J]. Fuzzy Systems and Mathematics, 2006, 20(6): 8387.
[6]邢 杰, 萧德云.基于PCA的概率神经网络结构优化[J].清华大学学报:自然科学版,2008,48(1):141144.
 XING Jie, XIAO Deyun. PCAbased probability neural network structure optimization[J]. Journal of Tsinghua University:Science and Technology, 2008,48(1):141144.
[7]杜吉祥, 汪增福. 基于径向基概率神经网络的植物叶片自动识别方法[J].模式识别与人工智能,2008,21(2):206213.
DU Jixiang, WANG Zengfu. Plant leaf identification based on radial basis probabilistic neural network[J]. Pattern Recognition and Artificial Intelligence, 2008,21(2):206213. 
[8]吴 婷, 颜国正, 杨帮华, 等.基于有监督学习的概率神经网络的脑电信号分类方法[J].上海交通大学学报,2008,42(5):803806.
 WU Ting, YAN Guozheng, YANG Banghua, et al. Electroencephalography classification based on probabilistic neural network with supervised learning in brain computer interface[J]. Journal of Shanghai Jiaotong University, 2008,42(5):803806
[9]王 昊,张 波,田蔚风.一种基于概率神经网络多信息融合的移动目标跟踪算法[J].上海交通大学学报,2007,41(5):792796.
 WANG Hao, ZHANG Bo, TIAN Weifeng. A multicue fused moving object tracker based on probabilistic neural networks[J]. Journal of Shanghai Jiaotong University, 2007,41(5):792796.
[10]何新贵, 梁久祯.过程神经元网络的若干理论问题[J].中国工程科学,2000,2(12): 4044.
HE Xingui, LIANG Jiuzhen. Some theoretical issues on 〖LL〗procedure neural networks[J]. Engineering Science, 2000,2(12):4044.
[11]何新贵, 梁久祯, 许少华. 过程神经网络的训练及其应用[J]. 中国工程科学,2001, 3(4): 3135.
 HE Xingui, LIANG Jiuzhen, XU Shaohua. Learning and applications of procedure neural networks[J]. Engineering Science, 2001, 3(4): 3135.
[12]许少华, 刘 扬, 何新贵. 基于过程神经网络的水淹层自动识别系统[J]. 石油学报,2004, 25(4): 5457.
 XU Shaohua, LIU Yang, HE Xingui. Automatic identification of waterflooded formation based on process neural network[J]. Acta Petrolei Sinica, 2004,25(4):5457.
[13]何新贵, 许少华. 一类反馈过程神经元网络模型及其学习算法[J]. 自动化学报,2004, 30(6): 801806. 
 HE Xingui, XU Shaohua. A feedback process neuron network model and its learning algorithm[J]. Acta Automatica Sinica, 2004,30(6):801806.
[14]丁 刚, 钟诗胜. 基于时变阈值过程神经网络的太阳黑子数预测[J]. 物理学报,2007, 56(2): 12241230.
DING Gang, ZHONG Shisheng. Sunspot number prediction based on process neural network with timevarying threshold functions[J]. Acta Physica Sinica,2007,56(2):12241230.

备注/Memo

备注/Memo:
收稿日期:2009-07-16.
基金项目:国家自然科学基金资助项目(60572174);黑龙江省教育厅科学技术研究资助项目(11521013);黑龙江省自然科学基金资助项目(ZA200611);黑龙江省科技攻关资助项目(GZ07A103).
通信作者:许少华.E-mail: xush62@163. com.
作者简介:
许少华, 男, 1962 年生, 博士, 教授, 博士生导师. 主要研究方向为模式识别、神经网络、智能信息处理. 在国内外学术期刊发表学术论文50余篇, 其中被SCI、EI检索20余篇.
李盼池, 男, 1969年生, 博士, 副教授, 主要研究方向为量子计算、智能优化算法及其在智能控制、智能信息处理等方面的应用. 在国内外学术期刊发表学术论文30余篇, 其中被SCI、EI 检索10余篇.
何新贵, 男, 1938年生, 教授, 博士生导师, 中国工程院院士, 北京计算机学会理事长,《计算机学报》副主编.主要研究方向为模糊逻辑、神经网络、进化计算、数据库理论, 发表学术论文140 余篇, 其中多篇被SCI、EI 检索.
更新日期/Last Update: 2009-11-16