時(shí)間序列神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)方法
TIME SERIES NEURAL NETWORK FORE- CASTING METHODS
-
摘要: 本文從信息論的角度出發(fā),討論了利用神經(jīng)網(wǎng)絡(luò)理論構(gòu)造時(shí)間序列預(yù)測(cè)模型的可能性和關(guān)鍵問題,并在此基礎(chǔ)上提出3種時(shí)間序列神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)方法,它們是:神經(jīng)網(wǎng)絡(luò)非線性時(shí)間序列模型、神經(jīng)網(wǎng)絡(luò)多維時(shí)間序列模型和神經(jīng)網(wǎng)絡(luò)組合預(yù)測(cè)模型,將上述模型應(yīng)用于實(shí)例的結(jié)果表明,在非線性信息的處理能力和預(yù)測(cè)精度方面都有很大提高。進(jìn)一步,對(duì)今后智能信息預(yù)測(cè)方法的發(fā)展方向進(jìn)行了探討,提出了智能信息預(yù)測(cè)系統(tǒng)的結(jié)構(gòu)模型。
-
關(guān)鍵詞:
- 信息論; 信息處理; 神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)方法
Abstract: This paper discussed the possibility and key problem of constructing the neural network time series model, and three time series neural network forecasting methods has been proposed. That is, the neural network nonlinear time series model, the neural network multi-dimension time model and the neural network com bining predictive model. These three methods are applied 10 real prcblems. The results show that these methods are better than the traditional ones. Furthermore, the comparison of the neural network with the traditional methods and the constructed model of intellectual information forecasting system are given. -
翁文波.預(yù)測(cè)論基礎(chǔ).北京:石油工業(yè)出版社,1984,第二章.[2]文新輝,陳開周.西安電子科技大學(xué)學(xué)報(bào),1994,21(1): 73-78.[3]文新輝,陳開周.預(yù)測(cè),1993,12(6): 48-51.[4]文新輝,牛明潔.預(yù)測(cè),1992,26(4): 58-61.[5]文新輝,陳開周.神經(jīng)網(wǎng)絡(luò)在經(jīng)濟(jì)管理中的應(yīng)用之二:神經(jīng)網(wǎng)絡(luò)廣義組合預(yù)測(cè)模型,中國(guó)神經(jīng)網(wǎng)絡(luò)1993年學(xué)術(shù)大會(huì),西安:1993,1034-1042.[6]Bates J M, Granger C W J. Operations Research Quarterly, 1969, 20(2): 319-324. -
計(jì)量
- 文章訪問數(shù): 2874
- HTML全文瀏覽量: 213
- PDF下載量: 471
- 被引次數(shù): 0
下載:
