PI-SIGMA NEURAL NETWORK FOR A ONE-STEP-AHEAD TEMPERATURE FORECASTING

被引：7

作者：

Husaini, Noor Aida ^{[1
]}

Ghazali, Rozaida ^{[1
]}

Nawi, Nazri Mohd ^{[1
]}

Ismail, Lokman Hakim ^{[2
]}

Deris, Mustafa Mat ^{[1
]}

Herawan, Tutut ^{[3
]}

机构：

[1] Univ Tun Hussein Onn Malaysia, Fac Comp Sci & Informat Technol, Batu Pahat 86400, Johor, Malaysia

[2] Univ Tun Hussein Onn Malaysia, Fac Environm & Civil Engn, Batu Pahat 86400, Johor, Malaysia

[3] Univ Ahmad Dahlan, Dept Informat Syst, Jalan Prof Dr Soepomo, Yogyakarta 55164, Indonesia

来源：

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS | 2014年 / 13卷 / 04期

关键词：

Pi-Sigma neural network; multilayer perceptron; temperature forecasting; one-stepahead; backpropagation;

D O I：

10.1142/S1469026814500230

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The main purpose of this study is to employ Pi-Sigma Neural Network (PSNN) for one-stepahead temperature forecasting. In this paper, we evaluate the performances of PSNN by comparing the network model with widely used Multilayer Perceptron (MLP). PSNN which is a class of Higher Order Neural Networks (HONN), has a highly regular structure, needs much smaller number of weights and less training time. The PSNN is use to overcome the drawbacks of MLP, which can easily trapped into local minima and prone to overfit. Both network models were trained with standard backpropagation algorithm. Through 1012 experiments, it has been demonstrated that the PSNN has a high practicability and better temperature forecasting for one-step-ahead using historical temperature data of Batu Pahat region.

引用

页数：16

共 38 条

[1] Performance of National Weather Service forecasts compared to operational, consensus, and weighted model output statistics [J].

Baars, JA ;

Mass, CF .

WEATHER AND FORECASTING, 2005, 20 (06) :1034-1047

[2]

Baboo S.S., 2010, INT J ENV SCI DEV, V1, P321, DOI DOI 10.7763/IJESD.2010.V1.63

[3] Long-term wind speed and power forecasting using local recurrent neural network models [J].

Barbounis, TG ;

Theocharis, JB ;

Alexiadis, MC ;

Dokopoulos, PS .

IEEE TRANSACTIONS ON ENERGY CONVERSION, 2006, 21 (01) :273-284

[4]

Barry R. G., 1982, ATMOSPHERE WEATHER C

[5] Neural networks and non-parametric methods for improving real-time flood forecasting through conceptual hydrological models [J].

Brath, A ;

Montanari, A ;

Toth, E .

HYDROLOGY AND EARTH SYSTEM SCIENCES, 2002, 6 (04) :627-639

[6] Assessing the effort of meteorological variables for evaporation estimation by self-organizing map neural network [J].

Chang, Fi-John ;

Chang, Li-Chiu ;

Kao, Huey-Shan ;

Wu, Gwo-Ru .

JOURNAL OF HYDROLOGY, 2010, 384 (1-2) :118-129

[7]

Childs P. R. N., 2001, PRACTICAL TEMPERATUR, DOI [10.1016/B978-075065080-9/50001-0, DOI 10.1016/B978-075065080-9/50001-0]

[8]

Cristos N. S., 1993, NEURAL NETW WORLD, V2, P219

[9]

Cybenko G., 1989, SIGNALS SYSTEMS, V2, P14

[10]

Fulcher J., 2008, ARTIFICIAL BRAINS EV, P797

← 1 2 3 4 →