UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya
Kampus ITS Sukolilo - Surabaya 60111
Phone
:
031-5921733 , 5923623
Fax
:
031-5937774
E-mail
:
libits@its.ac.id
Website
:
http://library.its.ac.id
Support (Customer Service) :
timit_perpus@its.ac.id
Welcome..guys!
Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT
Davi Wahyuni
Tondo Indra Nyata
Anis Wulandari
Ansi Aflacha
ITS » Master Theses » Matematika - S2 Posted by aprill@is.its.ac.id at 17/11/2015 09:29:55 • 1998 Views
COMPARISON METHODS OF LEARNING VECTOR QUANTIZATION LVQ AND SUPPORT VECTOR MACHINE SVM TO PREDICTION OF CORONARY HEART DISEASE
Author : LUSIYANTI, DESY ( 1212201012 )
ABSTRAK
Dewasa ini kecermatan dan ketepatan dalam hal klasifikasi data merupakan hal
yang sangat penting. Hasil klasifikasi data dengan beberapa metode yang telah
dikembangkan akan mempengaruhi sejumlah keputusan. Machine learning berpotensi untuk membantu mengambil sebuah keputusan yang sederhana namun
akurat. Metode-metode pada machine learning telah banyak digunakan dalam
banyak aplikasi salah satunya adalah pada permasalahan prediksi penyakit.
Penelitian ini menampilkan kinerja dari metode Learning Vector Quantization
LVQ dan support vector machine SVM. Tujuan penelitian ini adalah untuk
membandingkan kinerja LVQ dan SVM dalam memprediksi penyakit jantung koroner. Dataset yang digunakan yaitu data rekam medis yang terdiri dari jenis
kelamin usia pekerjaan kadar glukosa kadar kolesterol kadar trigliserida kadar Lactic Dhydrogenas kadar Density Lipoprotein dan kadar asam urat. Data ditraining dengan menggunakan kedua metode tersebut. Setelah semua data sampel ditraining selanjutnya hasil training keduanya dibandingkan untuk melihat performansi masing-masing metode dengan permasalahan penyakit jantung koroner. Meskipun arsitektur dari kedua metode memberikan performansi klasifikasi yang hampir sama namun terlihat bahwa jaringan SVM memberikan tingkat akurasi yang lebih tinggi yaitu sebesar 90.2778 dibandingkan jaringan LVQ sebesar 68.0556.
ABSTRACT
Nowadays incredible detail and accuracy in terms of data classification is very important. Results of classification data with some of the methods that have been
developed will affect a number of decisions. Machine learning has the potential to help take a simple yet accurate decision. Methods in machine learning has been widely used in many applications one of which is on problem prediction of disease. These studies showing the performance of the method of Learning Vector Quantization LVQ and support vector machine SVM. The purpose of this study was to compare the performance of the LVQ and SVM to predict coronary heart disease. The Dataset used i.e. medical record data consisting of gender age employment levels of glucose cholesterol levels triglyceride levels levels of Lactic Dhydrogenas Density Lipoprotein levels and the levels of uric acid. The Data might not trained to use both of these methods. The Dataset used i.e. medical record data consisting of gender age employment levels of glucose cholesterol levels triglyceride levels levels of Lactic Dhydrogenas Density Lipoprotein levels and the levels of uric acid. The Data might not trained to use both of these methods. After all the data samples and results might not trained training both in
comparison to see the performance of each method with coronary heart disease
problems. Although the architecture of both methods give similar classification
performance but to see that SVM networks provide higher accuracy is 90.2778 than the LVQ network. 68.0556.
Keywords:
Penyakit jantung koroner; Support Vectore Machine; Learning Vector Quantization
Subject
: Dukungan mesin vektor
Contributor
Prof. Dr. M. Isa Irawan, MT
Date Create
: 17/11/2015
Type
: Text
Format
: pdf
Language
: Indonesian
Identifier
: ITS-Master-12103150001544
Collection ID
: 12103150001544
Call Number
: RTMa 006.3 Lus p
Source Master Theses of Mathematics, RTMa 006.3 Lus p, 2015
Coverage ITS Community
Rights Copyright @2015 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library