Rule extraction from support vector machines using ensemble learning approach: An application for diagnosis of diabetes

Longfei Han; Senlin Luo; Jianmin Yu; Limin Pan; Songjing Chen

doi:10.1109/JBHI.2014.2325615

Rule extraction from support vector machines using ensemble learning approach: An application for diagnosis of diabetes

Longfei Han, Senlin Luo, Jianmin Yu, Limin Pan, Songjing Chen

School of Information and Electronics

Beijing Institute of Technology

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

119 Citations (Scopus)

Abstract

Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the 'black box' of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

Original language	English
Article number	6818375
Pages (from-to)	728-734
Number of pages	7
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	19
Issue number	2
DOIs	https://doi.org/10.1109/JBHI.2014.2325615
Publication status	Published - 1 Mar 2015

Keywords

diagnosis of diabetes
ensemble learning
random forest (RF)
rule extraction
support vector machines (SVMs)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/JBHI.2014.2325615

Cite this

@article{4ada1a5258e246c3bc5b11e91f08c106,

title = "Rule extraction from support vector machines using ensemble learning approach: An application for diagnosis of diabetes",

abstract = "Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the 'black box' of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.",

keywords = "diagnosis of diabetes, ensemble learning, random forest (RF), rule extraction, support vector machines (SVMs)",

author = "Longfei Han and Senlin Luo and Jianmin Yu and Limin Pan and Songjing Chen",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2015",

month = mar,

day = "1",

doi = "10.1109/JBHI.2014.2325615",

language = "English",

volume = "19",

pages = "728--734",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Rule extraction from support vector machines using ensemble learning approach

T2 - An application for diagnosis of diabetes

AU - Han, Longfei

AU - Luo, Senlin

AU - Yu, Jianmin

AU - Pan, Limin

AU - Chen, Songjing

PY - 2015/3/1

Y1 - 2015/3/1

N2 - Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the 'black box' of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

AB - Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the 'black box' of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

KW - diagnosis of diabetes

KW - ensemble learning

KW - random forest (RF)

KW - rule extraction

KW - support vector machines (SVMs)

UR - http://www.scopus.com/inward/record.url?scp=84924674527&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2014.2325615

DO - 10.1109/JBHI.2014.2325615

M3 - Article

C2 - 24860043

AN - SCOPUS:84924674527

SN - 2168-2194

VL - 19

SP - 728

EP - 734

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

IS - 2

M1 - 6818375

ER -

Rule extraction from support vector machines using ensemble learning approach: An application for diagnosis of diabetes

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this