COMBINING THE RESULTS OF SEVERAL NEURAL-NETWORK CLASSIFIERS

被引：252

作者：

ROGOVA, G ^{[1
]}

机构：

[1] CALSPAN CORP,BUFFALO,NY 14221

来源：

NEURAL NETWORKS | 1994年 / 7卷 / 05期

关键词：

CLASSIFIER; NEURAL NETWORK; CHARACTER RECOGNITION; THE DEMPSTER-SHAFER THEORY OF EVIDENCE; EVIDENCE;

D O I：

10.1016/0893-6080(94)90099-X

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Neural networks and traditional classifiers work well for optical character recognition; however, it is advantageous to combine the results of several algorithms to improve classification accuracies. This paper presents a combination method based on the Dempster-Shafer theory of evidence, which uses statistical information about the relative classification strengths of several classifiers. Numerous experiments show the effectiveness of this approach. Our method allows 15-30% reduction of misclassification error compared to the best individual classifier

引用

页码：777 / 781

页数：5

共 9 条

[1]

ANDERSON PG, 1993, P INT C NEUR NETW GE, P417

[2]

BARNETT JA, 1981, 7TH P INT JOINT C AR, P868

[3]

MANDLER EJ, 1988, PATTERN RECOGN, V10, P381

[4]

PAWLICKI TF, 1991, COMMUNICATION

[5]

Shafer G., 1976, MATH THEORY EVIDENCE, DOI 10.1515/9780691214696

[6]

SHUSTOROVICH A, IN PRESS NEURAL NETW

[7] METHODS OF COMBINING MULTIPLE CLASSIFIERS AND THEIR APPLICATIONS TO HANDWRITING RECOGNITION [J].

XU, L ;

KRZYZAK, A ;

SUEN, CY .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1992, 22 (03) :418-435

[8]

XU L, 1991, P INT JOINT C NEUR N, P43

[9]

1992, 1ST NIST OCR SYST C

← 1 →