A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System

Reginald Russell; Tianhua Chen; Richard Hill

doi:10.1007/978-981-19-5272-2_15

A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System

Reginald Russell, Tianhua Chen, Richard Hill

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Diabetes is a complex disorder that can lead to numerous severe complications. Early diagnosis and treatment significantly contributes to a better quality of life for patients and can protect against associated complications. This chapter proposes the application of an Adaptive Neuro-fuzzy Inference System (ANFIS), with system parameters optimised by Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). A comparative experimental study is conducted with application upon the UCI Early-Stage Diabetes Risk Prediction dataset, demonstrating effectiveness of the neuro-fuzzy system in diagnosing diabetes.

Original language	English
Title of host publication	Artificial Intelligence in Healthcare
Subtitle of host publication	Recent Applications and Developments
Editors	Tianhua Chen, Jenny Carter, Mufti Mahmud, Arjab Singh Khuman
Publisher	Springer Singapore
Pages	277-298
Number of pages	22
ISBN (Electronic)	9789811952722
ISBN (Print)	9789811952715
DOIs	https://doi.org/10.1007/978-981-19-5272-2_15
Publication status	Published - 26 Oct 2022

Publication series

Name	Brain Informatics and Health
Publisher	Springer
ISSN (Print)	2367-1742
ISSN (Electronic)	2367-1750

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1007/978-981-19-5272-2_15Licence: Unspecified

Cite this

@inbook{6ae30e912f194d98a2e48c7f4f911486,

title = "A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System",

abstract = "Diabetes is a complex disorder that can lead to numerous severe complications. Early diagnosis and treatment significantly contributes to a better quality of life for patients and can protect against associated complications. This chapter proposes the application of an Adaptive Neuro-fuzzy Inference System (ANFIS), with system parameters optimised by Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). A comparative experimental study is conducted with application upon the UCI Early-Stage Diabetes Risk Prediction dataset, demonstrating effectiveness of the neuro-fuzzy system in diagnosing diabetes.",

keywords = "Diabetes, Fuzzy System, Neuro-fuzzy, ANFIS",

author = "Reginald Russell and Tianhua Chen and Richard Hill",

year = "2022",

month = oct,

day = "26",

doi = "10.1007/978-981-19-5272-2\_15",

language = "English",

isbn = "9789811952715",

series = "Brain Informatics and Health",

publisher = "Springer Singapore",

pages = "277--298",

editor = "Tianhua Chen and Jenny Carter and Mufti Mahmud and \{Singh Khuman\}, Arjab",

booktitle = "Artificial Intelligence in Healthcare",

address = "Singapore",

}

A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System. / Russell, Reginald; Chen, Tianhua ; Hill, Richard.
Artificial Intelligence in Healthcare: Recent Applications and Developments. ed. / Tianhua Chen; Jenny Carter; Mufti Mahmud; Arjab Singh Khuman. Springer Singapore, 2022. p. 277-298 (Brain Informatics and Health).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System

AU - Russell, Reginald

AU - Chen, Tianhua

AU - Hill, Richard

PY - 2022/10/26

Y1 - 2022/10/26

N2 - Diabetes is a complex disorder that can lead to numerous severe complications. Early diagnosis and treatment significantly contributes to a better quality of life for patients and can protect against associated complications. This chapter proposes the application of an Adaptive Neuro-fuzzy Inference System (ANFIS), with system parameters optimised by Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). A comparative experimental study is conducted with application upon the UCI Early-Stage Diabetes Risk Prediction dataset, demonstrating effectiveness of the neuro-fuzzy system in diagnosing diabetes.

AB - Diabetes is a complex disorder that can lead to numerous severe complications. Early diagnosis and treatment significantly contributes to a better quality of life for patients and can protect against associated complications. This chapter proposes the application of an Adaptive Neuro-fuzzy Inference System (ANFIS), with system parameters optimised by Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). A comparative experimental study is conducted with application upon the UCI Early-Stage Diabetes Risk Prediction dataset, demonstrating effectiveness of the neuro-fuzzy system in diagnosing diabetes.

KW - Diabetes

KW - Fuzzy System

KW - Neuro-fuzzy

KW - ANFIS

UR - https://link.springer.com/book/9789811952715

U2 - 10.1007/978-981-19-5272-2_15

DO - 10.1007/978-981-19-5272-2_15

M3 - Chapter

SN - 9789811952715

T3 - Brain Informatics and Health

SP - 277

EP - 298

BT - Artificial Intelligence in Healthcare

A2 - Chen, Tianhua

A2 - Carter, Jenny

A2 - Mahmud, Mufti

A2 - Singh Khuman, Arjab

PB - Springer Singapore

ER -

A Case Study of Diabetes Diagnosis Using a Neuro-Fuzzy System

Abstract

Publication series

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this