OPTIMASI METODE SUPPORT VECTOR MACHINE MENGGUNAKAN ALGORITMA GENETIKA UNTUK KLASIFIKASI PENYAKIT JANTUNG

SETIANI, SELIA NUNIK (2023) OPTIMASI METODE SUPPORT VECTOR MACHINE MENGGUNAKAN ALGORITMA GENETIKA UNTUK KLASIFIKASI PENYAKIT JANTUNG. S1 thesis, Universitas Muhammadiyah Purwokerto.

Preview	Text SELIA NUNIK SETIANI_COVER.pdf Download (7MB) | Preview
Preview	Text SELIA NUNIK SETIANI_BAB I.pdf Download (1MB) | Preview
Preview	Text SELIA NUNIK SETIANI_BAB II.pdf Download (1MB) | Preview
	Text SELIA NUNIK SETIANI_BAB III.pdf Restricted to Registered users only Download (1MB)
	Text SELIA NUNIK SETIANI_BAB IV.pdf Restricted to Registered users only Download (1MB)
	Text SELIA NUNIK SETIANI_BAB V.pdf Restricted to Registered users only Download (962kB)
Preview	Text SELIA NUNIK SETIANI_DAPUS.pdf Download (973kB) | Preview
	Text SELIA NUNIK SETIANI_LAMPIRAN.pdf Restricted to Registered users only Download (6MB)

Abstract

Heart disease is the result of plaque buildup inside the coronary arteries, which blocks blood flow to the heart and increases the risk of heart attack and other complications. The problem discussed in this study is why optimization is carried out to determine parameter values and produce optimal performance in a classification model, an algorithm is needed, namely a Genetic Algorithm, because Genetic Algorithms are able to find optimal solutions. The purpose of this study is to classify heart disease measuring the level of accuracy, precission, recall and f1-score using the Support Vector Machine method and Genetic Algorithms as research optimization. The type of research used in the classification of heart disease is to use applied research. The results of this study are classification performance using SVM with accuracy results of 0.80, precission of 0.79, recall of 0.79 and f1-score of 0.79. The SVM-GA method produces a more optimal classification by producing an accuracy of 0.83, precission of 0.83, recall of 0.83 and an f1-score of 0.83.

Actions (login required)

View Item