Effect of fuzzy partitioning in Crohn's disease classification: a neuro-fuzzy-based approach

被引：45

作者：

Ahmed, Sk. Saddam ^{[1
]}

Dey, Nilanjan ^{[2
]}

Ashour, Amira S. ^{[3
,4
]}

Sifaki-Pistolla, Dimitra ^{[5
]}

Balas-Timar, Dana ^{[6
]}

Balas, Valentina E. ^{[7
]}

Tavares, Joao Manuel R. S. ^{[8
]}

机构：

[1] JIS Coll Engn, Dept CSE, Kalyani, W Bengal, India

[2] Techno India Coll Technol, Dept Informat Technol, Kolkata, India

[3] Tanta Univ, Fac Engn, Dept Elect & Elect Commun Engn, Tanta, Egypt

[4] Taif Univ, Coll Comp & IT, At Taif, Saudi Arabia

[5] Univ Crete, Fac Med, Clin Social & Family Med, Iraklion, NE, Greece

[6] Aurel Vlaicu Univ Arad, Fac Educ Sci Psychol & Social Sci, Arad, Romania

[7] Aurel Vlaicu Univ Arad, Fac Engn, Arad, Romania

[8] Univ Porto, Fac Engn, Dept Engn Mecan, Inst Ciencia Inovacao Engn Mecan & Engn Ind, Rua Dr Roberto Frias S-N, P-4200465 Oporto, Portugal

来源：

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING | 2017年 / 55卷 / 01期

关键词：

Genome sequencing; Factor analysis; Backpropagation neural network; Neuro-fuzzy; Classification; REGIONAL ENTERITIS; IMMUNE-DEFICIENCY; DIAGNOSIS; NETWORKS; IMMUNODEFICIENCY; RULES; AREA;

D O I：

10.1007/s11517-016-1508-7

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Crohn's disease (CD) diagnosis is a tremendously serious health problem due to its ultimately effect on the gastrointestinal tract that leads to the need of complex medical assistance. In this study, the backpropagation neural network fuzzy classifier and a neuro-fuzzy model are combined for diagnosing the CD. Factor analysis is used for data dimension reduction. The effect on the system performance has been investigated when using fuzzy partitioning and dimension reduction. Additionally, further comparison is done between the different levels of the fuzzy partition to reach the optimal performance accuracy level. The performance evaluation of the proposed system is estimated using the classification accuracy and other metrics. The experimental results revealed that the classification with level-8 partitioning provides a classification accuracy of 97.67 %, with a sensitivity and specificity of 96.07 and 100 %, respectively.

引用

页码：101 / 115

页数：15

共 57 条

[1]

Alayon S, 2013, Arch Soc Esp Oftalmol, V88, P168, DOI 10.1016/j.oftal.2012.07.008

[2]

[Anonymous], 2007, 2007 IEEE INT S SIGN

[3]

[Anonymous], 2008, World Applied Sciences Journal

[4]

[Anonymous], 1994, Neural networks: a comprehensive foundation