Alif Haykal Fitriawan, - (2023) IMPLEMENTASI PROGRAM SEE CHEATING WEB UNTUK KEGIATAN MENCONTEK DI KALANGAN PELAJAR. S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_TE_1908016_Title.pdf Download (241kB) |
|
Text
S_TE_1908016_Chapter I.pdf Download (49kB) |
|
Text
S_TE_1908016_Chapter II.pdf Restricted to Staf Perpustakaan Download (814kB) |
|
Text
S_TE_1908016_Chapter III.pdf Download (597kB) |
|
Text
S_TE_1908016_Chapter IV.pdf Restricted to Staf Perpustakaan Download (1MB) |
|
Text
S_TE_1908016_Chapter V.pdf Download (41kB) |
|
Text
S_TE_1908016_Appendix.pdf Restricted to Staf Perpustakaan Download (625kB) |
Abstract
Tujuan penelitian ini untuk membuat sistem yang dapat mendeteksi adanya kecurangan atau mencontek saat ujian berlangsung. Metode yang digunakan adalah metode eksperimen terencana, dimulai dari merancangan sistem deteksi mencontek, mengumpulkan Dataset, developing, implementasi dan evaluasi. Aplikasi Google Colab digunakan untuk membuat coding program, Dataset dikumpulkan melalui video-video yang ada di internet, Face capture dilakukan menggunakan kamera, deteksi objek dan fitur kamera menggunakan library opencv untuk menghubungkannya dengan Bahasa pemrograman python. Untuk hasil penelitian algoritma nya sendiri menggunakan algoritma YOLO dan Haar Cascade sebagai perbandingan sistem. Pada akhir penelitian diharapkan sistem secara real time dapat memberi peringatan awal adanya aktivitas mencontek melalui website dengan data gambar yang diolah memerlukan spesifikasi yaitu batch size 64 dan epoch 300 dengan ukuran gambar input 320x320 pixel. Dengan keluaran akurasi dari YOLO sebesar masing-masing kelas “mencontek” dan “tidak mencontek” memiliki tingkat akurasi 74,4 % dan 83,4 %. The purpose of this research is to create a system that can detect deceit or deceitful behaviour during exams. The method used is a planned experimental method, starting from designing a cheating detection system, collecting datasets, developing, implementing and evaluating. The Google Colab application is used to create program coding, Dataset is collected through videos on the internet, Face capture is done using a camera, object detection and camera features use the OpenCV library to connect it to the Python programming language. For the algorithm itself, it will use the YOLO and Haar Cascade algorithms as a comparison to the system. At the end of the research, it is hoped that the system in real time can provide an early warning of deceitful exam activity via the website with image data that is processed requires specifications, namely batch size 64 and epoch 300 with an input image size of 320x320 pixels. With an accuracy output from YOLO of each class "deceitful" and "not deceitful" it has an accuracy rate of 74.4% and 83.4%.
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | https://scholar.google.com/citations?user=DUbeMhQAAAAJ&hl=id&authuser=2 ID SINTA Dosen Pembimbing Agus Heri Setyabudhi: 0026087207 Tuti Suartini: 0021116303 |
| Uncontrolled Keywords: | YOLO, Haar Cascade, Mencontek YOLO, Haar Cascade, Deceitful |
| Subjects: | L Education > L Education (General) L Education > LB Theory and practice of education L Education > LC Special aspects of education |
| Divisions: | Fakultas Pendidikan Teknologi dan Kejuruan > Jurusan Pendidikan Teknik Elektro |
| Depositing User: | Alif Haykal Fitriawan |
| Date Deposited: | 01 Sep 2023 02:37 |
| Last Modified: | 01 Sep 2023 02:37 |
| URI: | http://repository.upi.edu/id/eprint/99820 |
Actions (login required)
 |
View Item |