Ari Sandy Kurniawan, - (2023) IMPLEMENTASI ALGORITMA SUPPORT VECTOR MACHINE (SVM) UNTUK MENGKLASIFIKASI TINGKAT STRES BERBASIS WEB PADA SISWA KELAS XII SMA SEDERAJAT DI KABUPATEN KARAWANG. S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_RPL_1904245_Title.pdf Download (980kB) |
|
Text
S_RPL_1904245_Chapter1.pdf Download (647kB) |
|
Text
S_RPL_1904245_Chapter2.pdf Restricted to Staf Perpustakaan Download (1MB) |
|
Text
S_RPL_1904245_Chapter3.pdf Download (827kB) |
|
Text
S_RPL_1904245_Chapter4.pdf Restricted to Staf Perpustakaan Download (1MB) |
|
Text
S_RPL_1904245_Chapter5.pdf Download (505kB) |
|
Text
S_RPL_1904245_Appendix.pdf Restricted to Staf Perpustakaan Download (523kB) |
Abstract
Stres didefinisikan sebagai ketidakseimbangan antara tuntutan dan kemampuan yang dimiliki oleh individu serta dapat mengancam kesejahteraan. Siswa kelas XII SMA Sederajat di Kabupaten Karawang mempunyai aktivitas akademik dan non akademik yang sangat tinggi membuat siswa berpotensi mengalamai stres. Dalam pengukuran tingkat stres tersebut masih menggunakan metode konvensional yaitu kuesioner DASS-42, dimana terdapat kesulitan dari efisiensi waktu dan kerumitan perhitungan statistik. Machine learning merupakan aplikasi komputer dan algoritma matematika dengan sumber pembelajaran yang berasal dari data dan menghasilkan prediksi di masa yang akan datang serta dapat menjadi solusi dari permasalahan diatas. Pada machine learning tersebut menggunakan algoritma Support Vector Machine (SVM). Algoritma SVM merupakan suatu metode yang digunakan dalam pemodelan machine learning untuk melakukan klasifikasi data kedalam kelas atau kategori mana dari suatu entitas berdasarkan fitur-fiturnya. Penelitian ini bertujuan untuk mengetahui bagaimana efektivitas model machine learning metode supervised learning dengan algoritma SVM dapat mengklasifikasi tingkat stres pada siswa kelas XII SMA Sederajat di Kabupaten Karawang. Tingkatan stres yang diukur adalah normal, ringan, sedang, parah, dan sangat parah. Hasil menunjukkan bahwa Algoritma SVM dapat membuat model machine learning dengan akurasi sebesar 98%, validasi sebesar 99%, recall sebesar 92%, precision sebesar 97%, dan f-score sebesar 94%. ----- Stress is defined as an imbalance between the demands and abilities of an individual and can threaten well-being. High school students in the Karawang District have high academic and non-academic activities, making them susceptible to stress. In measuring stress levels, conventional methods are still being used, such as the use of the DASS-42 questionnaire, where there are difficulties in terms of time efficiency and complexity in statistical calculations. Machine learning is a computer application and mathematical algorithm with a source of learning from data and resulting in predictions in the future and can be a solution to the above problems. In this machine learning, the Support Vector Machine (SVM) algorithm is used. The SVM algorithm is a method used in machine learning modeling to classify data into which class or category of an entity based on its features. This research aims to find out how effective the machine learning model method supervised learning with SVM algorithm can classify stress levels in high school students in the Karawang District. The stress levels measured are normal, light, moderate, severe, and very severe. The results showed that the SVM algorithm can create a machine learning model with an accuracy of 98%, validation of 99%, recall of 92%, precision of 97%, and f-score of 94%.
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | Link Google Scholar: ID SINTA Dosen Pembimbing: Indira Syawanodya: 6681751 Asyifa Imanda Septiana: 6681802 |
| Uncontrolled Keywords: | Algoritma SVM, Machine Learning, Tingkatan Stres |
| Subjects: | L Education > L Education (General) L Education > LB Theory and practice of education L Education > LB Theory and practice of education > LB1603 Secondary Education. High schools Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | UPI Kampus cibiru > S1 Rekayasa Perangkaat Lunak |
| Depositing User: | Ari Sandy Kurniawan |
| Date Deposited: | 16 Feb 2023 02:13 |
| Last Modified: | 16 Feb 2023 03:32 |
| URI: | http://repository.upi.edu/id/eprint/87679 |
Actions (login required)
 |
View Item |