Abstract
Drowsiness is one of the main factors that influences performance and safety, especially in driving activities and productivity levels. This research develops a Drowsiness facial classification system using facial parameters such as Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR), as well as the Long Short-Term Memory (LSTM) algorithm. Data is collected via video of the subject's face and facial parameters are calculated from facial landmarks extracted using the dlib library. The LSTM model was chosen because of its ability to capture important temporal patterns in detecting changes in Drowsiness over time. With a data sequence of five frames as input, the dataset is divided into 80% training data and 20% test and validation data. Experimental results show that the LSTM model is able to detect drowsiness with high accuracy, showing that the combination of EAR and MAR is effective in identifying drowsiness. This system is expected to be applied in early warning systems for drivers and employee monitoring, making significant contributions in the field of drowsiness detection using LSTM algorithms and facial parameters.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: JIFOSI
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
