• Sayali Alex Dive
• Gaurav Prashant Pande
• Soumitra Yatin Sathe
• Prof. Satyajit Sirsat

In 2021, a report from the Ministry of Road Transport and Highways Transport Research Wing revealed that road accidents caused the loss of 1,53,972 lives and injured 3,84,448 individuals. The majority of the affected drivers were between 18-45 years of age. Additionally, a survey conducted by the CDC found that approximately 1 in 25 adult drivers reported experiencing drowsiness and falling asleep while operating a vehicle within the past 30 days. The destruction of life, property, or infrastructure in many of these collisions putting the driver's life and the lives of others in danger. It has been determined that the transportation companies with overnight drivers face the greatest threat. Even if the driver is well-rested, nighttime driving can result in severe fatigue and drowsiness. A driver drowsiness detection system is now being implemented by a number of automakers as a result. The ECG machines that are mounted on the sides of the driver's seat are the components of the current systems that Toyota and Audi have implemented. These, on the other hand, have been uncomfortable. A fatigue detection and performance analysis system based on machine learning and deep learning is proposed for implementation in the concept idea. The project proposes providing a driver fitness assessment calculated using a given specific amount of time and alerting the driver based on levels of fatigue. The given framework being referred to utilizes equipment gear, for example, the web cam to catch the edges of the driver. The system implements CNN based model for eye closure detection and MAR to classify the subject as drowsy or not drowsy. If the system is put into place on a larger scale and at a price that is manageable, the benefit will be that we will be able to significantly lower the rate of road accidents. OLA and Uber, for example, can use the performance analysis module to monitor a driver's fitness level in relation to drowsiness.

CNN, Convolution neural network, eye aspect ratio, mouth aspect ratio, driver drowsiness

"YantaRakshak - A CNN based Driver Drowsiness Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.f232-f238, May-2023, Available :http://www.jetir.org/papers/JETIR2305534.pdf

"YantaRakshak - A CNN based Driver Drowsiness Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppf232-f238, May-2023, Available at : http://www.jetir.org/papers/JETIR2305534.pdf