A MODIFIED NEURAL-NETWORK-BASED GM(1,1)

被引:0
作者
Yeh, Ming-Feng [1 ]
Chen, Ti-Hung [2 ]
Lu, Hung-Ching [3 ]
机构
[1] Lunghwa Univ Sci & Technol, Dept Elect Engn, Taoyuan, Taiwan
[2] Lunghwa Univ Sci & Technol, Dept Comp Informat & Network Engn, Taoyuan, Taiwan
[3] Tatung Univ, Dept Elect Engn, Taoyuan, Taiwan
来源
PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 1 | 2018年
关键词
Forecasting model; Gradient descent method; Grey model; Neural network; MODEL;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Inspired by neural-network-based GM(1,1) (NN-GM(1,1)), this study attempts to drive a more simple and efficient learning rule to enhance the fitting/forecasting ability and convergence speed of the grey neural network. Simulation results on two real datasets show that the proposed modified NN-GM(1,1) performs better than the original NN-GM(1,1) in terms of fitting and forecasting accuracies. In addition, the modified NN-GM(1,1) has faster convergence speed.
引用
收藏
页码:1 / 5
页数:5
相关论文
共 10 条
[1]  
[Anonymous], 2014, CHIN STAT YB 2014
[2]  
Deng Julong, 1989, Journal of Grey Systems, V1, P1
[3]   Applications of improved grey prediction model for power demand forecasting [J].
Hsu, CC ;
Chen, CY .
ENERGY CONVERSION AND MANAGEMENT, 2003, 44 (14) :2241-2249
[4]   Forecasting energy demand using neural-network-based grey residual modification models [J].
Hu, Yi-Chung ;
Jiang, Peng .
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2017, 68 (05) :556-565
[5]  
Liewis C., 1982, IND BUSINESS FORECAS
[6]   An improved grey neural network model for predicting transportation disruptions [J].
Liu, Chunxia ;
Shu, Tong ;
Chen, Shou ;
Wang, Shouyang ;
Lai, Kin Keung ;
Gan, Lu .
EXPERT SYSTEMS WITH APPLICATIONS, 2016, 45 :331-340
[7]  
Liu SF, 2010, UNDERST COMPLEX SYST, P1
[8]  
Nan H.T., 2016, J GREY SYST-UK, V19, P7
[9]  
Shi X, 2011, INT J NONLIN SCI NUM, V11, P195
[10]   Discrete grey forecasting model and its optimization [J].
Xie, Nai-ming ;
Liu, Si-feng .
APPLIED MATHEMATICAL MODELLING, 2009, 33 (02) :1173-1186