Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/337075
Title: ONTOSkDS An Ontology based Clinical Decision Support System for Skin Disease using SVM FUZZY NEURO Hybrid
Researcher: Hema D
Guide(s): Vasantha Kalyani David
Keywords: Engineering and Technology
Computer Science
Computer Science Interdisciplinary Applications
University: Avinashilingam Deemed University For Women
Completed Date: 2020
Abstract: The Clinical Decision Support System (CDSS) is a health information technology system newlinedesigned to assist physicians and other health professionals with clinical decision-making tasks. newlineErythemato-Squamous Disease (ESD) is considered as one of the complex skin diseases comprising newlinesix types namely pityriasis rubra pilaris, lichen planus, chronic dermatitis, psoriasis, seborrheic newlinedermatitis and pityriasis rosea. Common morphological features make the skin disease diagnosis newlinestringent and cause inconsistencies. Moreover, ESD diagnosis concerning inculcated visible symptoms newlineand physician s expertise is challenging. newlineAn ESD skin disease has been less explored previously and given a relevant classification newlinesystem that would aid in its diagnosis. Numerous studies have shown the possible usage of newlineclassification and Ontology based information in healthcare. Disease-specific Ontology becomes an newlineessential entity to enable dermatology and medical software integration which in turn leads to the newlineevolution of the CDSS. newlineThis research is designed to develop a knowledge-based framework using newlinean advanced Ontology that would cluster, classify and establish relationships between newlinedifferent types of skin diseases. The proposed Ontology-based Skin Disease Decision newlineSupport System (ONTOSkDS) comprises of four phases that include pre-processing, classification, newlinehybrid knowledge reasoning and automatic construction of ONTOSkDS. These are interrelated newlinephases wherein, the output of one phase serves as the input to the subsequent phase. newlineThe pre-processed dataset is subjected to clustering using Fuzzy C Means (FCM) newlineand Simulated Annealing (SA) which in turn become input for classification algorithms. newlineIn the second phase, the clustered dataset undergoes training and testing through newlinefeature selection which give rise to Support Vector Machine (SVM) labels. In phase three, knowledge newlinereasoning of the resultant SVM dataset is performed through Fuzzy Logic (FL) applications newlineand Neural Network (NN) processing. This hybrid model builds a complete linguistic
Pagination: 233 p.
URI: http://hdl.handle.net/10603/337075
Appears in Departments:Department of Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File88.02 kBAdobe PDFView/Open
02_certificate.pdf338.46 kBAdobe PDFView/Open
03_acknowledgement.pdf93.15 kBAdobe PDFView/Open
04_contents.pdf108.32 kBAdobe PDFView/Open
05_list of tables, figures and abbreviations.pdf114.38 kBAdobe PDFView/Open
06_chapter 1.pdf11.55 MBAdobe PDFView/Open
07_chapter 2.pdf12.81 MBAdobe PDFView/Open
08_chapter 3.pdf11.44 MBAdobe PDFView/Open
09_chapter 4.pdf11.53 MBAdobe PDFView/Open
10_chapter 5.pdf11.62 MBAdobe PDFView/Open
11_chapter 6.pdf11.55 MBAdobe PDFView/Open
12_chapter 7.pdf11.58 MBAdobe PDFView/Open
13_chapter 8.pdf11.67 MBAdobe PDFView/Open
14_chapter 9.pdf11.36 MBAdobe PDFView/Open
15_bibliography.pdf11.72 MBAdobe PDFView/Open
80_recommendation.pdf274.57 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: