IMPLEMENTASI EDUCATIONAL DATA MINING UNTUK KLASIFIKASI KONSENTRASI PADA PROGRAM STUDI PENDIDIKAN TEKNIK ELEKTRO

Dani Akbar Nopia, - (2018) IMPLEMENTASI EDUCATIONAL DATA MINING UNTUK KLASIFIKASI KONSENTRASI PADA PROGRAM STUDI PENDIDIKAN TEKNIK ELEKTRO. S1 thesis, Universitas Pendidikan Indonesia.

Baca Full Text klik disini
[img] Text
S_TE_1100606_Title.pdf
Download (151kB)
[img] Text
S_TE_1100606_Abstract.pdf
Download (60kB)
[img] Text
S_TE_1100606_Table_Of_Content.pdf
Download (81kB)
[img] Text
S_TE_1100606_Chapter1.pdf
Download (67kB)
[img] Text
S_TE_1100606_Chapter2.pdf
Restricted to Staf Perpustakaan
Download (202kB)
[img] Text
S_TE_1100606_Chapter3.pdf
Download (404kB)
[img] Text
S_TE_1100606_Chapter4.pdf
Restricted to Staf Perpustakaan
Download (616kB)
[img] Text
S_TE_1100606_Chapter5.pdf
Download (57kB)
[img] Text
S_TE_1100606_ Bibliography.pdf
Download (143kB)
[img] Text
S_TE_1100606_Appendix.pdf
Restricted to Staf Perpustakaan
Download (3MB)
Official URL: http://repository.upi.edu

Abstract

Penelitian ini bertujuan untuk mengetahui perbandingan kinerja algoritma data mining untuk klasifikasi konsentrasi pada Program Studi Pendidikan Teknik Elektro, mengetahui mata kuliah yang berpengaruh terhadap klasifikasi konsentrasi pada Program Studi Pendidikan Teknik Elektro, dan mengetahui model optimal untuk mengklasifikasikan konsentrasi pada Program Studi Pendidikan Teknik Elektro. Data akademik mahasiswa yang diperoleh dari Fakultas Teknologi dan Kejuruan dianalisis dengan menggunakan algoritma metode klasifikasi pada data mining yaitu deep learning, decision tree, dan naïve bayes melalui proses Knowledge Discovery in Databases (KDD). Algoritma klasifikasi diterapkan dalam perangkat lunak RapidMiner untuk membandingkan kinerja dan menghasilkan model optimal untuk klasifikasi. Hasil penelitian menunjukkan algoritma deep learning menghasilkan kinerja yang terbaik dibandingkan dengan algoritma decision tree dan naïve bayes. Diperoleh mata kuliah yang berpengaruh terhadap klasifikasi konsentrasi pada Program Studi Pendidikan Teknik Elektro yaitu Fisika I, Dasar Teknik Elektro, Fisika II, Praktikum Bengkel Teknik Elektro dan Keselamatan Kerja, Metode Pengukuran, Material Teknik Elektro, Rangkaian Elektrik I, Probabilitas dan Statistik, Elektronika Dasar, dan Praktikum Dasar Teknik Elektro. Model optimal untuk mengklasifikasikan konsentrasi pada Program Studi Pendidikan Teknik Elektro diraih melalui pola nilai akademik yang didapatkan oleh mahasiswa sesuai dengan mata kuliah yang berpengaruh terhadap konsentrasi Program Studi Pendidikan Teknik Elektro.;--- This work aims to identify data mining algorithm that provide the best performance to classify the field of concentration in Electrical Engineering Education Program, discover the courses that influence the classification of the field of concentration in Electrical Engineering Education Program, and discover the optimal model for classifying each field of concentration in Electrical Engineering Education Program. Student academic data derived from Faculty of Technology and Vocational Education being analyzed using data mining classification methods which are deep learning, decision tree and naïve bayes through the Knowledge Discovery in Databases (KDD) process. Data mining algorithms were applied in RapidMiner software to compare the performances and generate the optimal models for classification. The results showed that deep learning algorithm has provided the best performance compared to decision tree and naïve bayes algorithms. The courses that influenced the classification of the field of concentration in the Electrical Engineering Education Program have been obtained which included Physics I, Basic of Electrical Engineering, Physics II, Electrical Engineering and Work Safety Practicum, Measurement Methods, Electrical Engineering Material, Electrical Circuit I, Probability and Statistics, Basic of Electronics, and Practicum of Basic Electrical Engineering. The optimal model for classifying the field of concentration in the Electrical Engineering Education Program achieved through the pattern of academic scores obtained by students in accordance with the courses that affect the field of concentration of Electrical Engineering Education Program.

Item Type: Thesis (S1)
Additional Information: No. Panggil : S TE DAN i-2018; Nama Pembingbing : I. Erik Haritman, II. Agus Heri Setyabudi; NIM : 1100606;
Uncontrolled Keywords: educational data mining, klasifikasi, bidang konsentrasi, educational data mining, classification, field of concentration.
Subjects: L Education > L Education (General)
T Technology > T Technology (General)
Divisions: Fakultas Pendidikan Teknologi dan Kejuruan > Jurusan Pendidikan Teknik Elektro
Depositing User: salsabila
Date Deposited: 13 Feb 2020 02:44
Last Modified: 13 Feb 2020 02:44
URI: http://repository.upi.edu/id/eprint/45772

Actions (login required)

View Item View Item