INTRODUCTION ON ACCIDENT PREVENTION
According to WHO, road accidents crashes are the 9th leading cause of death and are responsible for 2.2% of all deaths worldwide. Almost 1.25 million people are dying in road accidents every year, about 3,287 deaths in a day. Additionally, 20-50 million people are injured or disabled. Unless action is taken, by 2030, road traffic accidents will become the fifth leading cause of death. Majority of the accidents in highways are due to over speeding and rash driving.
Some accidents are also due to human fatigue and health issues of automobile drivers.
IoT healthcare also known as the internet of health things is one of the application of IoT for health and medical purposes, data acquisition and research, as well as monitoring of health. IoT it has a number of applications such as remote monitoring, medical device integration, smart sensors, etc. The remote monitoring systems include blood pressure, heart-rate monitors to specialized devices such as Fitbit, hearing aids, etc.
Hospitals have also implemented “smart beds” that are able to detect when a patient is trying to get up. It can adjust the pressure and support without manual interaction. Additionally, the use of mobile devices for real-time monitoring, storage, and transmission of health-related data collected from sensors and biomedical devices is termed as m-health or mobile-health.
IoT systems have also been recognized as a potential solution to identify human fatigue and recognize other health-related issues of the drivers, and are also capable of detecting if the vehicle is over speeding or cases of rash driving, etc. There has been a considerable amount of research in the monitoring of health using IOT systems. Wearable ECG monitors, smart helmets to monitor neural and brain activity, systems to detect drowsiness have been developed.
ESP32 is a low-power, low-cost microcontroller which has integrated Wi-Fi along with dual-mode Bluetooth. It has a 32-bit LX6 microprocessor, that operates at 160 or 240 MHz. It supports Wi-Fi 802.11 b/g/n, and Bluetooth v4.2 BR/EDR, Bluetooth Low Energy protocols.
Electrocardiogram (ECG) provides the best way to monitor human health. An electrocardiogram is the electrical activity of the human heart. It consists of a P-wave, QRS- complex, T-wave, U-wave. Using the features of these waves, it is possible to calculate the heart rate or beats per minute, detect any heart diseases such as a myocardial infarction. The heart rate of a normal person is 60 to 100 beats per minute. Any heart rate less than 60 bpm, accounts to a condition known as bradycardia and if the heart rate is more than 100 bpm, the condition is known as tachycardia. Using the heart rate and some additional information, other states of the driver such as stress, anxiety, drowsiness, alcohol consumption, the adrenaline rush can be detected.
The proposed system intends to realize a continuous ECG monitoring system for automotive drivers using the AD8232 ECG sensor and ESP32 microcontroller. It continuously records the ECG signals of the driver, filters it, detects the R-peaks, to calculate the heart rate, and also detects any abnormalities in the ECG signal due to any heart-related diseases using a polynomial regression approach. Upon the detection of any abnormalities, it provides an emergency notification system.
The system will be mainly composed of a central unit that is responsible of receiving information, and detecting heart beat , data collecting and transferring to the central unit. It is implemented with as low cost as possible to render its replacement affordable in case of a sudden heart attack .Ecg sensors will in this case act as mentors to control the unit. This will guarantee a high reduction of risk on their lives.
Ultrasonic sensors unit will communicate with the central unit to send speed information as soon as collecting them. This will insure the receiving of all necessary data even in case of losing the unit. Information transferred is typically the location of each detected suspected object and images from that location.
Nowadays people are driving very fast, accidents are occurring frequently, we lose our valuable life by making small mistakes while driving . To develop a system that can prevent fatal motor vehicular accidents due to abnormal health condition of the driver, over-speeding and undetected obstacles. To measure ECG signals of the driver, store it in a cloud and use machine learning to analyze the driver’s heart rate patterns and detect stress and fatal health problems. To detect over speeding of the vehicle using Ultrasonic sensors.PROPOSED SYSTEM
The system continuously monitors the driver’s ECG signals using an ECG sensor which is then sent to the microcontroller. The recorded ECG signal is processed using MATLAB to determine whether the driver is fit or unfit for driving. Based on the decision, a notification will be sent to the driver if he is unfit for driving.
This segment surveys the related methods for each of the component of the system over the year which includes different models for and their advancements.
The lateral survey of various approaches to land mine detection has been presented.
G. Wolgast et al. In , body area network (BAN) with two electrodes for measuring an electrocardiogram (ECG) signal and one electrode for reference and transmitting it to a smartphone via Bluetooth for data analysis were described. The user’s own smartphone was utilized for data processing and can be used to generate an alert if an abnormal heart condition is detected. The system had three use cases: monitoring of ECGs of an individual, continuously, myocardial infarction and other fatal heart-related malfunctions could be detected hours before. During a myocardial infarction, the ECG readings of an individual have a distinct ST elevation, which can be used to detect heart attacks.
An arm-band based ECG sensor, which is easy to wear has also been described by Rachim & Chung , in which capacitive coupled electrodes were implanted in an armband. Silver coated polyester ECG electrodes were used which were all placed in a single arm-band. This armband sensed ECG signals and sent them to a smartphone via Bluetooth. Peak detection was done using Pan and Tompkins algorithm.
W. Von Rosenberg, et al. In , A smart helmet that can monitor ECG, EEG (electroencephalogram), respiration and neural and brain activity to detect seizures, drowsiness, stress, the anxiety of drivers. Sensors embedded in helmets provide a convenient way to monitor the signals without disrupting the driver. The smart helmet consists of multiple electrodes placed at the positions of the lower jaw, mastoids, and forehead within a standard helmet. A multi-variate R-peak detection algorithm is used which is suited for noisy environments E. Span?, S. D. Pascoli, and G. Iannaccone discuss a wearable system for long term monitoring of a user’s health without assistance that requires less power. It can also monitor several patients with the same infrastructure and thus also reduces the cost per patient. The system uses an ECG sensor consisting of a chest belt that is battery powered. The belt consists of two dry plastic electrodes and electronic Printed Circuit Board. The chest belt enables the recording and continuous transmission of the ECG signals during daily activities.
A system for a specific purpose such as detecting a driver’s drowsiness using EEG signals has been discussed by G. Li et al. in . An EEG system consisting of a Bluetooth-enabled wearable EEG headband and a wearable smartwatch was used for a simple, cheap and feasible solution for driver drowsiness detection. The system uses a probabilistic model based on Support Vector Machine to convert the drowsiness level to a value between 0 and 1 in place of discrete classes.
Another system for stress management has been discussed by U. Ha et al. in , that uses a wearable headband and earplugs to monitor EEG signals, hemoenceophalography (HEG), and heart rate variability (HRV) to observe and monitor the user’s mental health. It uses the multimodal measurement of brain activity such as neural, vascular and autonomic domain signals that are combined with canonical correlation analysis (CCA) and temporal kernel canonical correlation analysis (tkCCA) algorithm to find the neural-vascular-autonomic coupling. In each domain, that is, neural, vascular and autonomic, the patterns of change in a signal are varied in case of mental stress and relaxation.
The creators have exhibited EBM (Eye Blink Checking) procedure, which cautions the concentration amid languor state. An implanted framework relies upon the mental condition of center through observing head developments and eye developments are useful in alarming drivers at the rest cycle phase of sleepiness. A customary eye flicker minute has no impact on the framework results
Scientists have planned Automated Speed Recognition System that may recognize the vehicle’s speed also, in the event that overspeeding occurs, evacuate the specific vehicle’s permit number and send it through mail to Toll Plaza so as to arraign fine. Here, Doppler Effect noticeable reality is utilized for estimating the speed. In the case of overspeeding is recognized, at that point a camera catches the picture of a vehicle naturally; and DIP (Digital Image Processing) strategies are utilized to expel the permit number. The discoveries have uncovered that the created framework distinguishes overspeeding vehicle effectively, mines the permit number, has incredible execution and might be utilized on streets to try out for overspeeding vehicles.
The specialists , in , have structured and created a novel framework, which may proficiently distinguish speed infringement on streets and causes driver to regard traffic runs by keeping up speed alongside the recommended speed limit. The created framework contains RFID (Radio Frequency Identification), GSM (Global Framework for Mobile) and PIC (18F45K22). This framework has given solid, ease, powerful results and continuous warning.
In , the creators have proposed another Vibration Sensor Device that was determined to the vehicle. Assuming any mishap occurs, vibration is actuated and afterward vehicle’s area has been identified with the assistance of GPS locator. Quickly, the occurrence has been insinuated to Patrol and Life bolster so as to recover the mishap just as suspect is to be followed by methods for GPS locator. The analysts have assessed the speed of vehicles by joining the accelerometer readings for the duration of the time and decide the speeding up shortcomings.Across the board analyzes were completed with the goal that sensor speed is exact and solid on genuine driving airs.
The creators in  have introduced a framework to recognize rash driving on the roadways just as to alarm the traffic experts if there is any infringement. Numerous approaches require human concentration and connect with numerous endeavors that is unpredictable to execute. In this article, the scientists have intended to propose a gadget for the early recognition and gave alarm of dangerous vehicle amid examples connected to rash driving. The entirety usage needs IR transmitter and beneficiary, a bell and a control circuit. On the off chance that the vehicle surpasses as far as possible, at that point a bell flag sounds cautioning the police.
- G. Wolgast, C. Ehrenborg, A. Israelsson, J. Helander, E. Johansson, and H. Manefjord, ”Wireless body area network for heart attack detec- tion [education corner],” IEEE Antennas Propag. Mag., vol. 58, no. 5, pp. 84-92, Oct. 2016.
- V. P. Rachim and W.-Y. Chung, ”Wearable noncontact armband for mobile ECG monitoring system,” IEEE Trans. Biomed. Circuits Syst., vol. 10, no. 6, pp. 1112-1118, Dec. 2016.
- W. Von Rosenberg, T. Chanwimalueang, V. Goverdovsky, D. Looney, D. Sharp, and D. P. Mandic, ”Smart helmet: Wearable multichannel ECG and EEG,” IEEE J. Transl. Eng. Health Med., vol. 4, 2016, Art. no. 2700111.
- E. Span?, S. D. Pascoli, and G. Iannaccone, ”Low-power wearable ECG monitoring system for multiple-patient remote monitoring,” IEEE Sen- sors J., vol. 16, no. 13, pp. 5452-5462, May 2016.
- G. Li, B.-L. Lee, and W.-Y. Chung, ”Smartwatch-based wearable EEG system for driver drowsiness detection,” IEEE Sensors J., vol. 15, no. 12, pp. 7169-7180, Dec. 2015.
- U. Ha et al., ”A wearable EEG-HEG-HRV multimodal system with simultaneous monitoring of tES for mental health management,” IEEE Trans. Biomed. Circuits Syst., vol. 9, no. 6, pp. 758-766, Dec. 2015.
- Aishwarya et al. S. R. (2015), “An IoT Based Accident Prevention & Tracking System for Night Drivers”, International Journal of Innovative Research in Computerand Communication Engineering, 3 (4), pp. 3493-3499.
- Malik et al. (2014), “Automated Over Speeding Detection and Reporting System”, IEEE Xplore, pp. 1-7.
- Shabibi L. A., Jayaraman N. and Vrindavanam J. (2014), “Automobile Speed Violation Detection System using RFID and GSM Technologies”, International Journal of Applied Information Systems, Vol. 7, No. 6, pp. 24-29.
- Prasanth P. and Karthikeyan U. (2016), “Effective Tracking of Misbehaviorial Driver & Over Speed Monitoring With Emergency Support”, International Journal of Advanced Research in Computer Engineering & Technology, 5 (10),pp. 2527-2529.
- Rangan P. R. (2017), “Vehicle Speed Sensing and Smoke Detecting System”, International Journal of Computer Science and Engineering, pp. 27-33.
Cite this essay
Accident Prevention Equipment. (2019, Nov 24). Retrieved from https://studymoose.com/accident-prevention-equipment-essay