Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/455012
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.coverage.spatial | Coronary artery disease diagnosis Using empirical transforms with Support vector machine | |
dc.date.accessioned | 2023-01-30T11:41:55Z | - |
dc.date.available | 2023-01-30T11:41:55Z | - |
dc.identifier.uri | http://hdl.handle.net/10603/455012 | - |
dc.description.abstract | The aim of the present study is to examine the coronary artery plaque conditions using Intra-Vascular UltrasSound (IVUS) images. Unlike wavelet transform, Empirical Wavelet Transform (EWT), Empirical Curvelet Transform (ECT), dependent decomposition approaches that provide superior temporal and frequency information than wavelets. Hence, EWT and ECT are considered as a feature extraction approach in this study with Support Vector Machine (SVM) classifier. Two Decision Support System (DSS) is designed for the classification using EWT and ECT independently. In both DSS, the given IVUS image is preprocessed at first to remove the speckle noise. After preprocessing, an image classification system is designed for the classification of plagues in the coronary arteries into different classes; normal, calcium, soft plaque, fibrous and necrotic (thrombus) by SVM using the spectral features from EWT and ECT. The DSSs are validated using 10-fold cross-validation using a total number of 400 IVUS images and their corresponding labeling are obtained from SHIFA hospitals, Tirunelveli, Tamilnadu, India. newlineIn the first method, textural energy features are obtained from EWT after preprocessing the IVUS images by Lee filter. The IVUS images are decomposed using four different boundary detections approaches; LocalMax (LM), LocalMaxMin (LMM), AdaptiveReg (AR) and Scale Space (SS) techniques. Based on the features, the plaque condition is classified using four- binary SVM classifiers. Experimental results show that the features extracted based on the boundaries of SS provide promising results in all stages of classification than others. newline | |
dc.format.extent | xiii,117p. | |
dc.language | English | |
dc.relation | p.103-116 | |
dc.rights | university | |
dc.title | Coronary artery disease diagnosis Using empirical transforms with Support vector machine | |
dc.title.alternative | ||
dc.creator.researcher | Swarnalatha, A | |
dc.subject.keyword | Engineering and Technology | |
dc.subject.keyword | Engineering | |
dc.subject.keyword | Engineering Electrical and Electronic | |
dc.subject.keyword | Coronary artery disease | |
dc.subject.keyword | empirical transforms | |
dc.subject.keyword | Support vector machine | |
dc.description.note | ||
dc.contributor.guide | Manikandan, M | |
dc.publisher.place | Chennai | |
dc.publisher.university | Anna University | |
dc.publisher.institution | Faculty of Electrical Engineering | |
dc.date.registered | ||
dc.date.completed | 2021 | |
dc.date.awarded | 2021 | |
dc.format.dimensions | 21cm | |
dc.format.accompanyingmaterial | None | |
dc.source.university | University | |
dc.type.degree | Ph.D. | |
Appears in Departments: | Faculty of Electrical Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 29.32 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 1.97 MB | Adobe PDF | View/Open | |
03_content.pdf | 39.58 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 14.38 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 539.37 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 219.16 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 328.78 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 350.6 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 1.51 MB | Adobe PDF | View/Open | |
10_annexures.pdf | 129.77 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 72.64 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: