Please use this identifier to cite or link to this item: https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/2553
Full metadata record
DC FieldValueLanguage
dc.contributor.authorVasantrao, Bhandare Trupti-
dc.contributor.authorRangasamy, Selvarani-
dc.contributor.authorShelke, Chetan J-
dc.date.accessioned2023-12-18T09:45:36Z-
dc.date.available2023-12-18T09:45:36Z-
dc.date.issued2023-
dc.identifier.citationChapter 7; pp. 103-120en_US
dc.identifier.isbn9781000930573-
dc.identifier.isbn9781032385150-
dc.identifier.urihttps://doi.org/10.1201/9781003345411-7-
dc.identifier.urihttp://gnanaganga.inflibnet.ac.in:8080/jspui/handle/123456789/2553-
dc.description.abstractEarly diagnosis of heart disease has tremendous importance in automated systems and medical data processing. Heart disease is a significant cause of casualties worldwide. Changes in lifestyle and eating habits affect health and cause cardiovascular disease. Many lives can be saved with early detection of heart disease. The diagnosis process can use different feature domains. In our work, we used spatial and frequency domain features to enhance the accuracy of the decision-making automation system used for heart disease recognition. The processing of features depends upon the nature and criticality of the feature with time dependency. The increase in features increases the accuracy of the automation system and the dispensation overhead and system delay. In the recent past, various regression algorithms were established to achieve improved accuracy and minimize the feature processing overhead based on the gain factor and the distance parameter. However, the nature of the feature and the criticality or significance of the feature are not considered. In the presented work, the feature selection is based on the feature's weight factor, which states the feature's significance or criticality in the decision-making of heart disease diagnosis. The feature fusion model is established per the new feature selection method, which considers the significance level of each feature and the diversion. We developed a deep learning model for the data organization based on the ECG signal data and the Cleveland data. The experimental result shows an improved accuracy of 99.2% in heart disease diagnosis for the developed feature fusion approach for heart disease detection. © 2024 selection and editorial matter, P. Karthikeyan, Polinpapilinho F. Katina and R. Rajagopal; individual chapters, the contributors.en_US
dc.language.isoenen_US
dc.publisherCRC Pressen_US
dc.subjectFusion modelen_US
dc.subjectHeart disease diagnosisen_US
dc.subjectHealthcare industryen_US
dc.subjectMedical data processingen_US
dc.subjectDiseaseen_US
dc.subjectHeart diseaseen_US
dc.titleFeature Fusion Model For Heart Disease Diagnosisen_US
dc.typeBook chapteren_US
Appears in Collections:Book/ Book Chapters

Files in This Item:
There are no files associated with this item.


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