Findiana, Rachmawati (2020) Klasifikasi Kelulusan Siswa Dalam Seleksi Masuk Perguruan Tinggi Negeri Melalui Jalur Nilai Rapor Menggunakan Metode Support Vector Machine (SVM). Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
BUKU TESIS RACHMA_FINAL.pdf - Accepted Version Download (1MB) | Preview |
Preview |
Text
BUKU TESIS RACHMA_FINAL.pdf Download (1MB) | Preview |
Preview |
Text
BUKU TESIS RACHMA_FINAL.pdf Download (1MB) | Preview |
Abstract
Seleksi Masuk Perguruan Tinggi Negeri melalui jalur nilai rapor merupakan salah satu cara penerimaan mahasiswa baru di Perguruan Tinggi Negeri yang tidak dipungut biaya pendaftaran dan tanpa ujian tertulis. Di Mojokerto
keikutsertaan siswa dalam proses seleksi ini masih dilakukan secara manual sehingga hasilnya belum maksimal dimana disaat siswa yang mempunyai nilai rapor baik belum tentu diterima dan sebaliknya siswa yang nilai rapornya cukup baik bisa diterima di salah satu Perguruan Tinggi Negeri. Oleh karena itu diperlukan klasifikasi untuk memprediksi kelulusan siswa pada Perguruan Tinggi Negeri
melalui jalur. Penelitian ini akan melakukan klasifikasi dengan menggunakan metode Support Vector Machine (SVM) dan Fuzzy Mamdani untuk menentukan kelulusan siswa pada SNMPTN, SPAN PTKIN, SNMPN, dan Tidak Lulus dengan
menggunakan nilai hasil ekstraksi fitur dari nilai rapor semester 1 sampai dengan nilai rapor semester 5. Berdasarkan hasil pengujian dan evaluasi untuk mengetahui seberapa baik hasil klasifikasi yang dilakukan dengan mengukur tingkat akurasi dari hasil klasifikasi data kelulusan siswa di SMA/MA Negeri di Mojokerto pada tahun 2018 dan 2019 dengan menggunakan metode Support Vector Machine mendapatkan hasil lebih baik dibandingkan dengan metode Fuzzy Mamdani dengan hasil akurasi terbaik 87% sedangkan nilai akurasi Fuzzy Mamdani 80%.
======================================================================================================
Entrance selection Public Higher Education through report card grades
path is one way of accepting new students at Public Higher Education, free of
registration fees, and without written examinations. To date, in Mojokerto, the
students’ participation in the selection process is still done manually, so the results
have not been maximized. Students with good report cards are not necessarily
accepted, and vice versa, students with average report cards can be one General
Higher Education through this pathway. Therefore, classification is needed to
predict student graduation at State Universities through pathways. This study will
classify using the Support Vector Machine (SVM) and Fuzzy Mamdani methods to
determine student graduation at SNMPTN, SPAN PTKIN, SNMPN, and Failed by
using the value of feature extraction results from semester 1 report cards to semester
5 report cards. Based on the results of testing and evaluation to find out how well
the classification results are carried out by measuring the accuracy of the
classification results of student graduation data at SMA/MA Negeri in Mojokerto
in 2018 and 2019 using the Support Vector Machine method, the results are better
than the fuzzy mamdani method. with the best accuracy of 87% while the Mamdani
fuzzy accuracy value is 80%.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Public Higher Education Entrance Selection, Public Higher Education, Report Card Grades Path, Support Vector Machine, Fuzzy Mamdani, Seleksi Masuk Perguruan Tinggi Negeri, Perguruan Tinggi Negeri, Jalur Nilai Rapor, Support Vector Machine, Fuzzy Mamdani |
| Subjects: | T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | RACHMAWATI FINDIANA |
| Date Deposited: | 18 Aug 2021 02:33 |
| Last Modified: | 07 Oct 2024 02:36 |
| URI: | http://repository.its.ac.id/id/eprint/87598 |
Actions (login required)
 |
View Item |