KLASIFIKASI PERGERAKAN TANGAN DAN FITUR WAJAH MENGGUNAKAN ALGORITMA CNN UNTUK DETEKSI INDIKASI KECURANGAN



Saiul Wahid, Azril (2024) KLASIFIKASI PERGERAKAN TANGAN DAN FITUR WAJAH MENGGUNAKAN ALGORITMA CNN UNTUK DETEKSI INDIKASI KECURANGAN. Skripsi (S1) thesis, Universitas Muhammadiyah Ponorogo.

[thumbnail of SURAT PERSETUJUAN UNGGAH KARYA ILMIAH] Text (SURAT PERSETUJUAN UNGGAH KARYA ILMIAH)
1. SURAT PERSETUJUAN UNGGAH KARYA ILMIAH.pdf
Download (152kB)
[thumbnail of HALAMAN DEPAN] Text (HALAMAN DEPAN)
2. HALAMAN DEPAN-1.pdf
Download (3MB)
[thumbnail of BAB I] Text (BAB I)
3. BAB I.pdf
Download (173kB)
[thumbnail of BAB II] Text (BAB II)
4. BAB II.pdf
Restricted to Repository staff only
Download (784kB)
[thumbnail of BAB III] Text (BAB III)
5. BAB III.pdf
Restricted to Repository staff only
Download (320kB)
[thumbnail of BAB IV] Text (BAB IV)
6. BAB IV.pdf
Restricted to Repository staff only
Download (953kB)
[thumbnail of BAB V] Text (BAB V)
7. BAB V.pdf
Restricted to Repository staff only
Download (163kB)
[thumbnail of DAFTAR PUSTAKA] Text (DAFTAR PUSTAKA)
8. DAFTAR PUSTAKA.pdf
Download (231kB)
[thumbnail of LAMPIRAN] Text (LAMPIRAN)
9. LAMPIRAN.pdf
Restricted to Repository staff only
Download (245kB)
[thumbnail of SKRIPSI FULL] Text (SKRIPSI FULL)
10. SKRIPSI FULL TEXT AZRIL SAIUL WAHID.pdf
Restricted to Repository staff only
Download (5MB)

Abstract

Learning and examinations, thereby increasing the demand for automated cheating detection systems. This research aims to develop and process a representative dataset to detect cheating by analyzing eyebrow, eye, head, and hand movements using Convolutional Neural Network (CNN) and MediaPipe Hands. The study focuses on detecting movements such as "Furrowed Brow," "Look Up," "Look Down," "Normal," "Look Right," "Look Left," "Side Glance Left," "Side Glance Right," and "Raise Eyebrows." The results show that the model achieves an average accuracy of 76% in adequate lighting conditions (90 lux) but significantly decreases to 60.56% in low lighting conditions (20 lux). Lighting measurements were conducted in real-time using a lux meter. Despite the reduction in accuracy under low lighting, the model remained effective at predicting within a distance range of 30-70 cm between the subject and the camera. This research provides a foundation for further development of more accurate cheating detection systems across various lighting conditions.

Item Type: Thesis (Skripsi (S1))
Uncontrolled Keywords: Academic Cheating, Convolutional Neural Network (CNN), Motion Detection, Face Recognition, Machine Learning
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering > Department of Informatic Engineering
Depositing User: ft . userft
Date Deposited: 30 Aug 2024 07:35
Last Modified: 03 Nov 2025 06:07
URI: https://eprints.umpo.ac.id/id/eprint/14782

Actions (login required)

View Item View Item