Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier

Sulaimon Ibrahim, Pradeep Chowriappa, Sumeet Dua, U. Rajendra Acharya, Kevin Noronha, Sulatha Bhandary, Hatwib Mugasa

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Prolonged diabetes retinopathy leads to diabetes maculopathy, which causes gradual and irreversible loss of vision. It is important for physicians to have a decision system that detects the early symptoms of the disease. This can be achieved by building a classification model using machine learning algorithms. Fuzzy logic classifiers group data elements with a degree of membership in multiple classes by defining membership functions for each attribute. Various methods have been proposed to determine the partitioning of membership functions in a fuzzy logic inference system. A clustering method partitions the membership functions by grouping data that have high similarity into clusters, while an equalized universe method partitions data into predefined equal clusters. The distribution of each attribute determines its partitioning as fine or coarse. A simple grid partitioning partitions each attribute equally and is therefore not effective in handling varying distribution amongst the attributes. A data-adaptive method uses a data frequency-driven approach to partition each attribute based on the distribution of data in that attribute. A data-adaptive neuro-fuzzy inference system creates corresponding rules for both finely distributed and coarsely distributed attributes. This method produced more useful rules and a more effective classification system. We obtained an overall accuracy of 98.55 %.

Original languageEnglish
Pages (from-to)1345-1360
Number of pages16
JournalMedical and Biological Engineering and Computing
Volume53
Issue number12
DOIs
Publication statusPublished - 01-12-2015

Fingerprint

Fuzzy inference
Membership functions
Medical problems
Classifiers
Fuzzy logic
Learning algorithms
Learning systems

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Computer Science Applications

Cite this

Ibrahim, Sulaimon ; Chowriappa, Pradeep ; Dua, Sumeet ; Acharya, U. Rajendra ; Noronha, Kevin ; Bhandary, Sulatha ; Mugasa, Hatwib. / Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier. In: Medical and Biological Engineering and Computing. 2015 ; Vol. 53, No. 12. pp. 1345-1360.
@article{d0a0affe5c7d4af99be9c634f0b45637,
title = "Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier",
abstract = "Prolonged diabetes retinopathy leads to diabetes maculopathy, which causes gradual and irreversible loss of vision. It is important for physicians to have a decision system that detects the early symptoms of the disease. This can be achieved by building a classification model using machine learning algorithms. Fuzzy logic classifiers group data elements with a degree of membership in multiple classes by defining membership functions for each attribute. Various methods have been proposed to determine the partitioning of membership functions in a fuzzy logic inference system. A clustering method partitions the membership functions by grouping data that have high similarity into clusters, while an equalized universe method partitions data into predefined equal clusters. The distribution of each attribute determines its partitioning as fine or coarse. A simple grid partitioning partitions each attribute equally and is therefore not effective in handling varying distribution amongst the attributes. A data-adaptive method uses a data frequency-driven approach to partition each attribute based on the distribution of data in that attribute. A data-adaptive neuro-fuzzy inference system creates corresponding rules for both finely distributed and coarsely distributed attributes. This method produced more useful rules and a more effective classification system. We obtained an overall accuracy of 98.55 {\%}.",
author = "Sulaimon Ibrahim and Pradeep Chowriappa and Sumeet Dua and Acharya, {U. Rajendra} and Kevin Noronha and Sulatha Bhandary and Hatwib Mugasa",
year = "2015",
month = "12",
day = "1",
doi = "10.1007/s11517-015-1329-0",
language = "English",
volume = "53",
pages = "1345--1360",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer Verlag",
number = "12",

}

Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier. / Ibrahim, Sulaimon; Chowriappa, Pradeep; Dua, Sumeet; Acharya, U. Rajendra; Noronha, Kevin; Bhandary, Sulatha; Mugasa, Hatwib.

In: Medical and Biological Engineering and Computing, Vol. 53, No. 12, 01.12.2015, p. 1345-1360.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier

AU - Ibrahim, Sulaimon

AU - Chowriappa, Pradeep

AU - Dua, Sumeet

AU - Acharya, U. Rajendra

AU - Noronha, Kevin

AU - Bhandary, Sulatha

AU - Mugasa, Hatwib

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Prolonged diabetes retinopathy leads to diabetes maculopathy, which causes gradual and irreversible loss of vision. It is important for physicians to have a decision system that detects the early symptoms of the disease. This can be achieved by building a classification model using machine learning algorithms. Fuzzy logic classifiers group data elements with a degree of membership in multiple classes by defining membership functions for each attribute. Various methods have been proposed to determine the partitioning of membership functions in a fuzzy logic inference system. A clustering method partitions the membership functions by grouping data that have high similarity into clusters, while an equalized universe method partitions data into predefined equal clusters. The distribution of each attribute determines its partitioning as fine or coarse. A simple grid partitioning partitions each attribute equally and is therefore not effective in handling varying distribution amongst the attributes. A data-adaptive method uses a data frequency-driven approach to partition each attribute based on the distribution of data in that attribute. A data-adaptive neuro-fuzzy inference system creates corresponding rules for both finely distributed and coarsely distributed attributes. This method produced more useful rules and a more effective classification system. We obtained an overall accuracy of 98.55 %.

AB - Prolonged diabetes retinopathy leads to diabetes maculopathy, which causes gradual and irreversible loss of vision. It is important for physicians to have a decision system that detects the early symptoms of the disease. This can be achieved by building a classification model using machine learning algorithms. Fuzzy logic classifiers group data elements with a degree of membership in multiple classes by defining membership functions for each attribute. Various methods have been proposed to determine the partitioning of membership functions in a fuzzy logic inference system. A clustering method partitions the membership functions by grouping data that have high similarity into clusters, while an equalized universe method partitions data into predefined equal clusters. The distribution of each attribute determines its partitioning as fine or coarse. A simple grid partitioning partitions each attribute equally and is therefore not effective in handling varying distribution amongst the attributes. A data-adaptive method uses a data frequency-driven approach to partition each attribute based on the distribution of data in that attribute. A data-adaptive neuro-fuzzy inference system creates corresponding rules for both finely distributed and coarsely distributed attributes. This method produced more useful rules and a more effective classification system. We obtained an overall accuracy of 98.55 %.

UR - http://www.scopus.com/inward/record.url?scp=84948719894&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948719894&partnerID=8YFLogxK

U2 - 10.1007/s11517-015-1329-0

DO - 10.1007/s11517-015-1329-0

M3 - Article

C2 - 26109519

AN - SCOPUS:84948719894

VL - 53

SP - 1345

EP - 1360

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 12

ER -