A new parameter selection method of neural network

被引：1
|
作者：
Wu, Gui-Fang [1 ,2 ]
Jang, Se-young [1 ]
Kwak, Hoon-sung [1 ]
Pu, Jie-xin [2 ]
机构：
[1] Chonbuk Natl Univ Korea, Coll Engn, Dept Comp Engn, Jeonju 561756, South Korea
[2] Henan Univ Technol, Elect & Informat Engn Dept, Dept Automat, Luoyang, Peoples R China
来源：
MUE: 2008 INTERNATIONAL CONFERENCE ON MULTIMEDIA AND UBIQUITOUS ENGINEERING, PROCEEDINGS | 2008年
关键词：
D O I：
10.1109/MUE.2008.99
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
A new parameter selection method of neural network is presented after researching parameter selection method of neural network deeply, and it is applied to surface defect online inspection system Of cold rolled strips. The method exerted the merits of small-samples fully which was utilized to train and test neural network by every possible combination of parameters to get a group of neural network parameters by plotting histogram of recognition rate under different parameter combinations, and the parameters are regarded as optimized parameters of neural network. Experiments showed that a best recognition effect by using the parameters for neural network which are selected by the new parameter selection method can be achieved among all the parameters selected randomly for surface defect of cold rolled strips.
引用
收藏
页码：378 / +
页数：2
相关论文
共 50 条
  • [31] A Method of MRTD Parameter Measurement Based on CNN Neural Network
    Rong, Weigang
    Zhang, Wenwen
    He, Weiji
    Chen, Qian
    Gu, Guohua
    Zhao, Tiekun
    Qiu, Zhi
    2019 INTERNATIONAL CONFERENCE ON OPTICAL INSTRUMENTS AND TECHNOLOGY: OPTOELECTRONIC MEASUREMENT TECHNOLOGY AND SYSTEMS, 2020, 11439
  • [32] A neural network based parametrization method for distributed parameter identification
    Sun, M
    Zheng, C
    THIRTIETH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY (SSST), 1998, : 361 - 365
  • [33] Parameter whitening method for neural network modeling for gray problem
    Zhong, L.
    Bai, Z.G.
    Xia, H.X.
    Lu, H.H.
    Zhou, X.G.
    Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2001, 14 (02):
  • [34] Online Parameter Identification Method using Neural Network for IPMSM
    Minh Xuan Bui
    2022 25TH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS 2022), 2022,
  • [35] On the neural network method of the parameter identification in transient well testing
    Hu, Ze
    Xinan Shiyou Xueyuan Xuebao/Journal of Southwestern Petroleum Institute, 19 (04): : 57 - 63
  • [36] SAMPLE SELECTION METHOD OF NEURAL NETWORK BASED ON FCM AND NN METHOD
    Zhao, Zhenning
    Ling, Su
    Zhang, Qinfeng
    2011 INTERNATIONAL CONFERENCE ON MECHANICAL ENGINEERING AND TECHNOLOGY (ICMET 2011), 2011, : 811 - +
  • [37] Sample Selection Method of Neural Network Based on FCM and NN method
    Zhao, Zhenning
    Ling, Su
    Zhang, Qinfeng
    2011 INTERNATIONAL CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND AUTOMATION (CCCA 2011), VOL I, 2010, : 535 - 538
  • [38] A new genetic feature selection with neural network ensemble
    Lee, Heesung
    Hong, Sungjun
    Kim, Euntai
    INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS, 2009, 86 (07) : 1105 - 1117
  • [39] Artificial neural network classification of microarray data using new hybrid gene selection method
    Aziz, Rabia
    Verma, C. K.
    Jha, Manoj
    Srivastava, Namita
    INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 2017, 17 (01) : 42 - 65
  • [40] NEW PARAMETER-ADJUSTMENT METHOD FOR NETWORK TRANSIENTS
    DITORO, MJ
    WITTENBERG, RC
    PROCEEDINGS OF THE INSTITUTE OF RADIO ENGINEERS, 1948, 36 (03): : 368 - 368
12345