Klasifikasi Kabupaten di Provinsi Jawa Timur Berdasarkan Indikator Daerah Tertinggal Dengan Metode Support Vector Machine dan Entropy Bsed Fuzzy Support Vector Machine

Pranata, Jefry (2018) Klasifikasi Kabupaten di Provinsi Jawa Timur Berdasarkan Indikator Daerah Tertinggal Dengan Metode Support Vector Machine dan Entropy Bsed Fuzzy Support Vector Machine. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of Tugas Akhir.pdf]
Preview
Text
Tugas Akhir.pdf - Accepted Version

Download (2MB) | Preview

Abstract

Pemerintah menetapkan 4 Kabupaten dari 29 kabupaten di Provinsi Jawa Timur masuk dalam kategori daerah tertinggal pada tahun 2015. Penelitian ini akan digunakan metode Entropy Based Fuzzy Support Vector Machine (EFSVM) dan Support Vector Machine (SVM) untuk mengklasifikasikan kabupaten di Provinsi Jawa Timur dengan dan tanpa seleksi variabel. Terdapatnya imbalance pada data deerah tertinggal dimana kabupaten tertinggal jauh lebih sedikit dibandingkan kabupaten tidak tertinggal memerlukan metode klasifikasi untuk data imbalance, Salah satunya adalah EFSVM. Hasil menunjukan EFSVM memiliki Kinerja yang lebih baik pada AUC dibandingkan dengan SVM.. Seleksi variabel mampu meningkatkan AUC pada EFSVM namun tidak meningkatkan AUC adaSVM=========================================================================================
The government set four regions in East Java to fall into the category of underdeveloped regions. There is an imbalance in the left behind data where there are far fewer regions than the non-disadvantaged regions. Therefore, a classification method is required which takes into account the imbalance in the data. One method of classification is the Support Vector Machine (SVM). Suppor Vector Manchine does not have high accuracy if applied to imbalance data. Therefore, a classification method for imbalance data is required. One of the classification methods for imbalance data is Entropy Based Fuzzy Support Vector Machine. This research will use EFSVM and SVM method to classify the regency in East Java province with and without variable selection. The result shows that EFSVM has better classification performance with AUC of 92.26%

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Daerah Tertinggal, Data Imbalance, Entropy Based Fuzzy, Support Vector Machine (SVM)
Subjects: Q Science
Q Science > QA Mathematics
Q Science > QA Mathematics > QA9.64 Fuzzy logic
Divisions: Faculty of Mathematics, Computation, and Data Science > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User: Jefry Pranata Maulana
Date Deposited: 21 Jul 2021 22:54
Last Modified: 21 Jul 2021 22:54
URI: http://repository.its.ac.id/id/eprint/57626

Actions (login required)

View Item View Item