Fani Oktaf Laurisa
STIKI Malang, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Cheating Detection During Exam with YOLO V4 Fani Oktaf Laurisa; Keith Marvin Sajul; Arif Tirtana
IC-ITECHS Vol 3 No 1 (2022): IC-ITECHS
Publisher : LPPM STIKI Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Computer-based exams have been widely implemented in various agencies in Indonesia, especially in the field of education. But in practice use Computer Based Test(CBT). Does not guarantee that examines do things honestly, if the supervisor is negligent then the opportunity to cheat appears. This can be minimized by using technology Artificial Intelligence(AI), especially in domains of computer vision (CV). Start with observation problems and then collect datasets in the form of human images facing the camera and looking sideways, then do the image annotation, pre-processing data, YOLOv4 architecture design, training data, model testing, and finally deployment of the application on the website. The model test result show accuracy with a precision score of 0.99 (99%), a recall score of 1.00(100%), and an F-1 Score of 0.99(99%).