Effective prediction of DEA model by neural network

Bai Qing Sun; Jing Wei Dong

Effective prediction of DEA model by neural network

Bai Qing Sun^*
, Jing Wei Dong

^*Corresponding author for this work

School of Management, Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

In this paper, a fast neural network model for the forecasting of effective points by DEA model is proposed, which is based on the SPDS training algorithm. The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm. Its training speed is much faster and its forecasting precision is much better than those of BP algorithm. By numeric examples, it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.

Original language	English
Pages (from-to)	683-686
Number of pages	4
Journal	Journal of Harbin Institute of Technology (New Series)
Volume	16
Issue number	5
State	Published - Oct 2009
Externally published	Yes

Keywords

BP algorithm
DEA forecasting
Multi-layer neural network
Single parameter dynamic searching algorithm

Cite this

@article{c9acb10daefb40829763804d2978aa19,

title = "Effective prediction of DEA model by neural network",

abstract = "In this paper, a fast neural network model for the forecasting of effective points by DEA model is proposed, which is based on the SPDS training algorithm. The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm. Its training speed is much faster and its forecasting precision is much better than those of BP algorithm. By numeric examples, it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.",

keywords = "BP algorithm, DEA forecasting, Multi-layer neural network, Single parameter dynamic searching algorithm",

author = "Sun, \{Bai Qing\} and Dong, \{Jing Wei\}",

year = "2009",

month = oct,

language = "英语",

volume = "16",

pages = "683--686",

journal = "Journal of Harbin Institute of Technology (New Series)",

issn = "1005-9113",

publisher = "Harbin Institute of Technology",

number = "5",

}

TY - JOUR

T1 - Effective prediction of DEA model by neural network

AU - Sun, Bai Qing

AU - Dong, Jing Wei

PY - 2009/10

Y1 - 2009/10

N2 - In this paper, a fast neural network model for the forecasting of effective points by DEA model is proposed, which is based on the SPDS training algorithm. The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm. Its training speed is much faster and its forecasting precision is much better than those of BP algorithm. By numeric examples, it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.

AB - In this paper, a fast neural network model for the forecasting of effective points by DEA model is proposed, which is based on the SPDS training algorithm. The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm. Its training speed is much faster and its forecasting precision is much better than those of BP algorithm. By numeric examples, it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.

KW - BP algorithm

KW - DEA forecasting

KW - Multi-layer neural network

KW - Single parameter dynamic searching algorithm

UR - https://www.scopus.com/pages/publications/72749114950

M3 - 文章

AN - SCOPUS:72749114950

SN - 1005-9113

VL - 16

SP - 683

EP - 686

JO - Journal of Harbin Institute of Technology (New Series)

JF - Journal of Harbin Institute of Technology (New Series)

IS - 5

ER -

Effective prediction of DEA model by neural network

Abstract

Keywords

Other files and links

Fingerprint

Cite this