INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Traffic accidents are the leading cause of human death and injury worldwide, accounting for approximately one million deaths annually. Driver drowsiness is a significant contributor to road accidents. Tired driving is a growing concern, leading to an increase in accidents. Detecting driver drowsiness in real time is important to solve this problem. Various devices have been developed that use artificial intelligence algorithms to detect drowsiness.
In this research, we will discuss driver drowsiness detection using facial and eye features. Our model will receive data like (eyes and mouth) at runtime. Using the dataset, the system will detect whether the eyes were closed for a certain range, and it can sound an alarm to alert the driver. The system adjusts the score based on eye position (open/closed). The proposed model is an important step towards developing a real-time drowsiness detector that can warn the driver in time and prevent accidents. We propose a driver drowsiness detection system using machine learning and facial and eye features. Our system uses a multitasking cascading convolutional neural network (MTCNN) to detect and align the driver's face and feature points, and an eye-mouth convolutional neural network (EM-CNN) to identify eye and mouth positions. We also calculate the percentage of eyelid closure (PERCLOS) and the degree of mouth opening (POM) over time to assess the driver's fatigue state. Experimental results of the developed approach outperformed comparable existing schemes in terms of accuracy (94.95%), F1-score (95.45%), sensitivity (85.71), specificity (99%), global accuracy (99.10%), AUC_ROC (98.55%). %), Mean-IOU (97.11%), SSIM (93.33%).
"Advanced Driver Monitoring: Adaptive Machine Learning for Drowsiness Detection", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 4, page no.i524-i534, April-2024, Available :http://www.ijnrd.org/papers/IJNRD2404863.pdf
Downloads:
00033
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn