Klasifikasi Penyakit Jantung Pada Suara Detak Jantung Menggunakan Hjorth Descriptor
Abstract
An early recognition tool for normal and abnormal heart sounds is needed to assist medical personnel in diagnosing abnormalities in the heart. Basic Health Research data shows that the death rate from non-communicable diseases in Indonesia has increased to 59.5% with deaths from heart disease occupying the seventh position of causes of death in various countries in the world. The design aims to identify two types of heart sounds, namely normal and abnormal (murmur), this system uses the Hjorth Descriptor feature extraction process. change activity values and variations. The classification process is carried out using MLP, MLP is able to analyze problems and perform pattern classification and system modeling in retrieval and determining features. The process of making this TA uses MATLAB software tools which will test the database that has been obtained which will later be designed on the GUI (Grapichal User Interface). In this final project the classification results obtained can be used with the possibility of a more accurate truth, in the results of this study, the highest level of accuracy is 100 % and the sensitivity value is 100 % and the specificity value is 100 % Keywords: Murmur, Hjorth Descriptor, MATLAB.Published
Issue
Section
License
Copyright info for authors
1. Authors hold the copyright in any process, procedure, or article described in the work and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors retain publishing rights to re-use all or portion of the work in different work but can not granting third-party requests for reprinting and republishing the work.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.