Authors: Dr. P. Chandra Sekhar, K. Srilaxmi Reddy, K. Sri Vidya Reddy, G. Sanjana Bhargavi, D. Manasa
Certificate: View Certificate
Nowadays it is very difficult to stay active all the time due to busy schedules. Falling asleep at the wheel can lead to serious consequences, accidents, and even death. This situation is much more common than we realize and therefore it is very important to fight this problem. So, to solve this problem, we developed a sleep alarm for drivers. This system alerts the user when he falls asleep at the wheel, thus preventing accidents and saving lives. This system is handy for long- distance travelers and late-night drivers. Designed with a blink sensor, it takes safety measures a step further by designing a system to stop the vehicle when the driver\'s eyes are closed. The system is developed using Arduino microcontroller. The eye blinking sensor is connected to a microcontroller that continuously monitors the frequency of the driver\'s eye blinking. If the driver\'s blink rate falls below a certain threshold, the system warns the driver and sends a signal to the vehicle\'s control system to stop the vehicle.
It is important to be aware of potential risks in road traffic, domestically and internationally, and take measures to ensure your safety and health. According to Google, about 1.35 billion people die on the world's roads every year. Worldwide, about 3,700 people die and many are seriously injured in car, bus, motorcycle, bicycle or truck accidents every day. Car accident has been recognized as one of the biggest safety problems worldwide. The Out system is designed to reduce this. Our system uses an IR sensor that emits an inferred light when the driver's eyes are open. This light is not reflected, but when the eyes are closed, the light of time is reflected back onto the person's skin. After a certain time, the reflective buzzer will start and if the driver does not open his eyes, the vehicle's backlight will turn on and the vehicle will stop automatically. This helps in reducing the risk of accidents that may happen.
According to published data, every year 20-50 million people suffer non-fatal injuries from traffic accidents, and approximately 1.3 million people die in traffic. According to the US National Highway Traffic Safety Administration (NHTSA), driver fatigue causes 100,000 car accidents each year. About 1,550 people were injured in the collision. $12.5 billion in economic damage, 71,000 injuries and deaths. According to the German Road Safety Council (DVR), one in four motorway traffic deaths is due to driver fatigue. of road traffic as a result of driver fatigue. When the driver nods behind the wheel, he loses control of the vehicle, which often causes a collision with another car or stationary objects. Monitoring driver fatigue can help prevent these tragic accidents. Monitoring is typically reported using later technologies: vehicle- based measurements of multiple indicators such as lane changes, steering wheel movement and pressure. For example, the accelerator pedal is constantly monitored and a shift beyond to NREM is broken into three stages
One of the most common causes of car accidents is drowsy driving. Drowsy driving creates hazards, risks and other potentially fatal situations, including distracted driving. A certain threshold means a significantly increased risk that the driver is drowsy. Driving while tired, sleep-deprived, or both is called "drowsy driving." This often happens when the driver does not get enough sleep, but it can also be caused by poor concentration, certain medications, sleep disorders or alcohol consumption. or shift work. Although falling asleep at the wheel is dangerous, drowsiness also impairs the ability to drive safely without falling asleep. According to common understanding, one in twenty drivers fell asleep behind the wheel. Driving for more than 20 hours without rest or sleep is comparable to a 0.08 percent drinking rate. You are three times more likely to be in a car accident when you are tired. Drowsiness can be difficult to detect, so some drivers may not realize their fatigue. which are generalized, uncontrolled attention deficit disorders. However, due to its short duration 4-5 seconds, it is dangerous and can be dangerous and cause serious damage. More than 1.5 million people died as a result as a result of traffic accidents. According to India's Ministry of Road Accidents, an average of 1,280 accidents resulted in 417 deaths, or about 53 accidents and 17 deaths per hour.
II. LITERATURE SURVEY
Auto-driver drowsiness can be detected using artificial intelligence and visual information. The purpose of the system detect, track and study the faces and eyes of the drivers to make a real vehicle image different from the drivers to validate the algorithms. It is a real-time system that works in different lighting conditions. The frequency of accidents has increased due to several factors, one of is also implemented with a video-based approach.
This system is non-invasive and uses human-related elements. Band power and empirical state decomposition methods are used to study and extract the signal, SVM (Support Vector Machine) is used to confirm the analysis and classify the driver's vitality. The system intends to search for driver drowsiness using the hypothesis of Bayesian networks.
The interaction between driver and vehicle characteristics is extracted to obtain reliable driver drowsiness symptoms. It provides more appropriate and accurate strategies for designing a drowsy driver detection system. The sleepiness detection system uses brain and visual activity.
The EEG-based sleep detector uses the electroencephalographic (EEG) channel to monitor brain activity, diagnostic techniques and fuzzy logic. Use of eyeblink detection and characterization in visual activity monitoring. The electrooculography (EOG) channel is used to extract the blink functions. Image processing and pattern classification are used to photograph the driver's face, track the driver's facial features, and classify the driver's sleepiness.
After studying the activity of the facial muscles with the Active Appearance Model (AAM), 17 different characteristic points are determined. The k-nearest neighbor method classifies sleepiness into 6 levels, this method also detected the driver's smile. The head position estimation method is used to detect the deviation of the tired driver. In this method, Viola and Jones' algorithm for driver Tace detection.
This method is non-intrusive and robust to detect driver drowsiness in real time. Support Vector Machine (SVM) is used to extract faces from video frames, and Circular Hough Transform (CHT) is useful for analyzing mouth and eye condition. In this approach, machine excitation is used to determine human behavior while the driver is drowsy.
It collects 30 different facial actions, including blinks, yawns and head movements, to detect driver drowsiness. Different tasks are used in the design of drowsiness detection systems. Although "sleepiness" is a commonly mentioned term, "fatigue" is also used. Despite the differences, fatigue and sleep are used interchangeably. Fatigue means "reluctance to continue a task as a result of physical or mental strain or prolonged performance of the same task." However, sleepiness or sleepiness is defined as the desire to fall asleep. Basically, sleepiness is the result of an exciting biological need for sleep. Sleepiness can be caused by a number of reasons, such as medications, long working hours, sleep disorders, poor (or insufficient) sleep, and staying awake for long periods of time.
Thus, their relationship is obvious, because fatigue directly affects sleepiness. Although they are different concepts, some researchers have considered sleepiness and fatigue to be similar because of After that, machine leaning (ML) or deep learning is utilized to their similar consequences. In our work, we call these systems drowsiness detection systems. A driver does not suddenly fall asleep without showing any signs.
Examples of signs are:
These signs appear gradually as drowsiness progresses, and as such can act as indicators of driver drowsiness. To identify the different stages of drowsiness, researchers studied the driver vehicle reactions and driving behavior.
The Fig.2.1 Driver drowsiness detection measures illustrates all the measures currently used to classify driver drowsiness. Two of these indicators are observed in the leaders themselves: image and biological. The third dimension that I created from the car itself is called the vehicle-specific dimension. The fourth measure considered is a hybrid measure that combines at least two of the above.
Fig.2.2 illustrates a DDD system's general block diagram and data flow that can Normal employ any of the four measures mentioned above. data is initially collected with a suitable sensor device; targets are then extracted from the captured signals. This step is important because it simplifies input into the system by discarding irrelevant information and extracting useful information. Later, some systems can use feature transformation or dimensionality reduction to project the data into another domain. In the fourth step, the features that best correlate with sleepiness are selected using different feature selection algorithms, such as backward selection or envelope feature selection methods.
Generate a model in the training phase that is used to classify the driver's status. The trained model is used during the test phase to detect the driver and the level of sleep and take action if necessary, such as activating an alarm or giving the driver a break.
The methodology for creating an anti-sleep alarm for drivers using an Arduino Uno requires a combination of hardware components and software programming. The goal is to detect signs of drowsiness or inattention and then alert the driver. Here's a step- by-step methodology to build such a system,
Test the system under various driving conditions to ensure it responds correctly to drowsiness. Fine-tune the threshold values and alert durations to reduce false positives and negatives.
Fig.4.1 is block diagram that helps us to understand how to connect all the components to create the desired system.
Anti-drowsiness alarm for drivers using Arduino Uno is a device to help prevent tired or fatigued drivers from falling asleep at the wheel. It usually works by monitoring the driver's alertness and sounding an alarm when signs of drowsiness are detected. Here is a basic overview of how such a system can be designed and how it works:
A. Required Components
B. Working Principle
This basic setup can be expanded and customized to add additional functions such as data collection or integration with other vehicle security systems. Remember that the effectiveness of such a system can vary and it is very important to ensure that it does not distract the driver or create its own safety problems. Always put safety first when designing and implementing alarms to prevent drivers from falling asleep.
In conclusion, an anti-sleep alarm system for drivers is a technology that has the potential to improve road safety and reduce the number of accidents and fatalities on the roads. By alerting drivers when they are becoming drowsy, the system can help to keep them awake and alert at the wheel, reducing the risk of accidents due to fatigue. There are several potential ethical considerations that should be considered when developing and implementing an anti-sleep alarm system for drivers, including the potential impact on individual privacy, the potential for the system to create an expectation that drivers should always be alert and awake while driving, and the potential for the system to be used as a tool for monitoring and controlling the behavior of drivers. A sustainability plan is also important for ensuring that the system is developed and implemented in a way that is environmentally, socially, and economically sustainable. This might involve designing the system to be as energy efficient and environmentally friendly as possible, considering the impact of the system on the wellbeing and safety of drivers, and identifying long-term funding sources and a financially sustainable business model. In summary, anti-drowsiness warning systems for drivers can have a positive impact on society by improving road safety and reducing the number of accidents and fatalities on our roads. However, it is important to carefully consider the ethical and sustainable aspects of the system to ensure that it is developed and implemented responsibly and sustainably.
 M. Hemamalini and P. Muhilan, \"Accident prevention using an eye blink sensor\", volume l. Issue L11, 2017. 325.  C. Prabha, R. Sunitha, R. Anitha “Automatic Vehicle Accident Detection and Messaging System Using GSM and GPS Modem”, IJAREEIE, Vol. 3, Issue 7, pp: 10723 – 10727, July 2014  Arun Sahayadhas, Kenneth Sundaraj, \"Detecting Driver Drowsiness Based on Sensors A Review\",pp.16937- 16953, ISSN 1424-8220, Malaysia Raoul Lopes, D.J Sanghvi, Aditya Shah, \"Drowsiness Detection based on Eye Movement, Yawn Detection and Head Rotation\", Vol. 2, No.6,2012  Anirban dasgupta, Anjith George \"A Vision Based System For Monitoring The Loss Of Attention in Automotive Drivers\", IEEE Transaction, voI.l4, no.4 2013..  Drowsy Driver Sleeping Device and Driver Alert System, International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064  X. Xie, R. Sudhakar and H. Zhuang, -Real Time Eye Feature Tracking from a Video Image Sequence Using Kalman Filter, IIIEEE Transactions on Systems, Man, and Cybernetics, Vol. 25, No.12, pp. 1568-1577, 1995.  Kenneth J. Ayala, “8051 Micro-controller Architecture, Program & Application],2nd Edition.  Drowsy Driver Sleeping Device and Driver Alert System, International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064  Steven B. Ryan, Krystal L. Detweiler, Kyle H. Holland, Michael A. Hord and Vlastislav Bracha, “A long-range, wide field-of-view infrared eye blink detector  Tefft, B.C. Prevalence of Motor Vehicle Crashes Involving Drowsy Drivers, United States, 2009–2013; Citeseer: Washington, DC, USA, 2014  Fuletra, J.D.; Bosamiya, D. A survey on drivers drowsiness detection techniques. Int. J. Recent Innov. Trends Comput. Commun. 2013, 1, 816–819  Pratama, B.G.; Ardiyanto, I.; Adji, T.B. A review on driver drowsiness based on image, bio-signal, and driver behavior. In Proceedings of the 2017 3rd International Conference on Science and Technology-Computer (ICST), Bandung, Indonesia, 25–26 October 2017; pp. 70–75.  Ramzan, M.; Khan, H.U.; Awan, S.M.; Ismail, A.; Ilyas, M.; Mahmood, A. A survey on state-of-the-art drowsiness detection techniques. IEEE Access 2019, 7, 61904–61919  Sikander, G.; Anwar, S. Driver fatigue detection systems: A review. IEEE Trans. Intell. Transp. Syst. 2018, 20, 2339– 2352.  Ukwuoma, C.C.; Bo, C. Deep Learning Review on Drivers Drowsiness Detection. In Proceedings of the 2019 4th Technology Innovation Management and Engineering Science International Conference (TIMES-iCON), Bangkok, Thailand, 11–13 December 2019; pp. 1–5.  Dong, Y.; Hu, Z.; Uchimura, K.; Murayama, N. Driver inattention monitoring system for intelligent vehicles: A review. IEEE Trans. Intell. Transp. Syst. 2010, 12, 596–614.
Copyright © 2023 Dr. P. Chandra Sekhar, K. Srilaxmi Reddy, K. Sri Vidya Reddy, G. Sanjana Bhargavi, D. Manasa. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.