Search for collections on Undip Repository

ANALISA PENGGUNAAN RELIEFF FEATURE SELECTION DAN BACKPROPAGATION PADA PENYAKIT HEPATOCELLULAR CARCINOMA

WULANDARI, Umi Meganinditya and Warsito, Budi and Farikhin, Farikhin (2023) ANALISA PENGGUNAAN RELIEFF FEATURE SELECTION DAN BACKPROPAGATION PADA PENYAKIT HEPATOCELLULAR CARCINOMA. Masters thesis, UNIVERSITAS DIPONEGORO.

[img] Text
COVER.pdf

Download (1MB)
[img] Text
BAB I.pdf

Download (336kB)
[img] Text
BAB II.pdf

Download (329kB)
[img] Text
BAB III.pdf
Restricted to Repository staff only

Download (705kB)
[img] Text
BAB IV.pdf
Restricted to Repository staff only

Download (941kB)
[img] Text
BAB V.pdf

Download (113kB)
[img] Text
DAFTAR PUSTAKA.pdf

Download (190kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository staff only

Download (630kB)

Abstract

Penelitian ini dilakukan untuk mengetahui seberapa baik tingkat performa ReliefF dalam pemilihan fitur pada data penyakit HCC. Penelitian ini dilatarbelakangi karena dataset memiliki fitur-fitur yang berpengaruh dan sedikit berpengaruh. Fitur yang memiliki banyak pengaruh merupakan faktor risiko penyakit HCC. Salah satu cara untuk menanganinya dengan memanfaatkan teknologi komputer dalam pemilihan fitur pada rekam medis dengan informasi yang paling berpengaruh pada HCC. Pada penelitian ini, model yang diusulkan adalah penggunaan ReliefF pada tahap seleksi fitur dan Backpropagation pada tahap klasifikasi. Pada tahap seleksi fitur ini terdapat dua langkah yaitu perhitungan bobot dan proses reduksi fitur. Pada langkah perhitungan bobot fitur, setiap fitur diberi bobot dan fitur yang dihasilkan akan diproses dalam proses reduksi fitur. Hasil perhitungan bobot fitur akan menghasilkan rangking dari nilai tertinggi hingga nilai terendah yang kemudian akan dikurangi dengan rangking fitur. Fitur terbaik yang telah dihasilkan akan dijadikan input untuk tahap kedua yaitu tahap klasifikasi menggunakan Backpropagation. Berdasarkan hasil penelitian, ditemukan 10 fitur yang dianggap terbaik dari 39 fitur yang digunakan. Akurasi dihasilkan oleh metode ReliefF+BPNN sebesar 80%. Hasil perbandingan menunjukkan bahwa metode pemilihan fitur ReliefF dapat memberikan peningkatan pada hasil akurasi dan hasil recall. Hasil penelitian ini menunjukkan bahwa metode yang diusulkan berhasil. Namun, cara ini masih memerlukan pertimbangan dari tenaga medis karena bukan merupakan hasil akhir bagi pasien.
Kata Kunci : Feature Selection, ReliefF, klasifikasi, Backpropagation, Hepatocellular Carcinoma, Survival

This research was conducted to find out how well ReliefF performs in feature selection and implementation on unbalanced data on HCC disease data. The background of this research is because the dataset has influential and slightly influential features. Features that have multiple influences are risk factors for HCC disease. One way to handle this is by utilizing computer technology in selecting features in medical records with the most influential information on HCC. In this study, the model proposed is the use of ReliefF at the feature selection stage and Backpropagation at the classification stage. At this feature selection stage, there are two steps, namely the calculation of weights and the process of reducing features. In the feature weight calculation step, each feature is given a weight and the resulting features will be processed in the feature reduction process. The results of the feature weight calculation will produce a ranking from the highest value to the lowest value which will then be reduced by the ranking features. The best features that have been produced will be used as input for the second stage, namely the classification stage using Backpropagation. Based on the research results, 10 features were found that were considered the best out of the 39 features used. The accuracy produced by the ReliefF+BPNN method is 80%. The comparison results show that the ReliefF feature selection method can provide an increase in the results of the accuracy of data imbalances. The results of this study indicate that the proposed method is successful. However, this method still requires consideration from medical personnel because it is not the final result for the patient.
Keywords: Feature Selection, ReliefF, Classification, Backpropagation, Hepatocellular Carcinoma, Survival

Item Type: Thesis (Masters)
Uncontrolled Keywords: Feature Selection, ReliefF, klasifikasi, Backpropagation, Hepatocellular Carcinoma, Survival
Subjects: Sciences and Mathemathic
Divisions: Postgraduate Program > Master Program in Information System
Depositing User: ekana listianawati
Date Deposited: 23 Nov 2023 07:51
Last Modified: 23 Nov 2023 07:51
URI: https://eprints2.undip.ac.id/id/eprint/18274

Actions (login required)

View Item View Item