Claim Missing Document
Check
Articles

Found 1 Documents
Search

Sistem Pendeteksi Kantuk Pengemudi berbasis Eye Aspect Ratio dan Mouth Opening Ratio menggunakan Algoritme C-LSTM Auliya Firdaus; Fitri Utaminingrum; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

There were 103,645 traffic accidents in Indonesia in 2021, an increase of 3.6% from the previous year. The second leading cause of accidents was freight transport, at a percentage of 12%. According to the National Committee for Transportation Safety of the Republic of Indonesia (KNKT), 80% of accidents were caused by driver fatigue, which resulted in microsleep. To address this problem, a system for early detection of driver fatigue is needed. This system uses the eye aspect ratio (EAR) and mouth opening ratio (MOR) as the main parameters for detecting microsleep and yawning as a sign of fatigue. With an adaptive threshold, the accuracy of the system in detecting microsleep is 97%. The system's detection of yawning uses a Convolutional Neural Network (C-LSTM) model. The C-LSTM model was chosen because it is a combination of CNN for better feature recognition and LSTM for sequential learning. The accuracy of the yawn detection system is 98%. It can be concluded that this system works well in detecting driver fatigue.