Back to Search
Start Over
Integrating Blockchain Technology with IoT and ML to Avoid Road Accidents Caused by Drunk Driving.
- Source :
- Wireless Personal Communications; Aug2022, Vol. 125 Issue 4, p3001-3018, 18p
- Publication Year :
- 2022
-
Abstract
- Road Accident is a significant concern in every county. According to WHO (World Health Organization) reports, 1.3 million people died in road traffic crashes, and in India, the total number of 449,002 accidents in the year 2019 led to 151,113 deaths and 451,361 injuries; this will be increasing by the day. Drunk and driving alcohol is the momentous root cause of the accidental tragedy. During the drunk and drive, there is a chance person will move very fast, so we have to check the acceleration speed of the vehicle. Sometimes a person has drowsiness during driving, whether the person is drunk or not, so we have to check the eye position of the person with the help of IoT (internet of Things) devices. This study offered a model and concept for preventing such human suffering by detecting, preventing, and informing the system using today's dominating technologies, such as IoT, Machine Learning, and Blockchain. In the proposed model on the embedded Blockchain, devices are smartly controlled. The system is built on an IoT sensor and associated sensors to detect the amount of alcohol in a driver's breath, gather data for accuracy, and make a judgment using machine learning. However, because IoT devices have a central server, attackers target the system, use Distributed Denial of Service, and temper exploit its flaws. Component-based Blockchain will also significantly boost the system's scalability and security. The suggested precise result and data received by IoT devices will not degrade, and all connected nodes will assist in resolving the issue. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09296212
- Volume :
- 125
- Issue :
- 4
- Database :
- Complementary Index
- Journal :
- Wireless Personal Communications
- Publication Type :
- Academic Journal
- Accession number :
- 158447111
- Full Text :
- https://doi.org/10.1007/s11277-022-09695-x