Authors :
Kaaranki.HEMANTH KUMAR; Kathula. LAKSHMANUDU; Konda.ASHOK; P.Srinu Vasa Rao
Volume/Issue :
Volume 9 - 2024, Issue 2 - February
Google Scholar :
http://tinyurl.com/5e3bbsfw
Scribd :
http://tinyurl.com/4znm6jc8
DOI :
https://doi.org/10.5281/zenodo.10706890
Abstract :
The main aspect of the project is to indicate
accident possibility to the driver by using machine
learning algorithms. This is useful to reduce road
accidents pose significant threats to public safety, and
predicting the likelihood of accidents can play a crucial
role in implementing preventive measures. This project
focuses on developing a Road Accident Prediction
System using machine learning techniques.
By considering the road conditions, weather
conditions, speed, traffic density, time of day, junction
type, month, road quality, vehicle type, population
density, age of the driver, alcohol or drug influence, and
vehicle condition.
In addition, the system enables real-time
predictions through user interaction, allowing
individuals to input specific conditions and receive
instant assessments of accident risk. This interactive
feature enhances user engagement and awareness
regarding potential risks associated with varying road
scenarios.
The abstracted model serves as a foundation for
more advanced predictive systems, fostering the
development of proactive safety measures and
contributing to the overall enhancement of road safety.
The project emphasizes the importance of leveraging
machine learning for accident prediction and encourages
further exploration in the domain of intelligent
transportation systems.
Here we are using ml algorithms Decision tree,
Clustering, Regression Models, Anomaly Detection and
using readings of the Sensors to measure weather
conditions, vehicle speed,road conditions that are used to
detect the potholes on the roads and these data are
collected and train the dataset by using algorithms.
Keywords :
Road Accident Prediction, Prevention, Weather Conditions, Speed Detection, Population Density, Alocholor Drug Influence, Machine Learning Algorithms and IOT sensors.
The main aspect of the project is to indicate
accident possibility to the driver by using machine
learning algorithms. This is useful to reduce road
accidents pose significant threats to public safety, and
predicting the likelihood of accidents can play a crucial
role in implementing preventive measures. This project
focuses on developing a Road Accident Prediction
System using machine learning techniques.
By considering the road conditions, weather
conditions, speed, traffic density, time of day, junction
type, month, road quality, vehicle type, population
density, age of the driver, alcohol or drug influence, and
vehicle condition.
In addition, the system enables real-time
predictions through user interaction, allowing
individuals to input specific conditions and receive
instant assessments of accident risk. This interactive
feature enhances user engagement and awareness
regarding potential risks associated with varying road
scenarios.
The abstracted model serves as a foundation for
more advanced predictive systems, fostering the
development of proactive safety measures and
contributing to the overall enhancement of road safety.
The project emphasizes the importance of leveraging
machine learning for accident prediction and encourages
further exploration in the domain of intelligent
transportation systems.
Here we are using ml algorithms Decision tree,
Clustering, Regression Models, Anomaly Detection and
using readings of the Sensors to measure weather
conditions, vehicle speed,road conditions that are used to
detect the potholes on the roads and these data are
collected and train the dataset by using algorithms.
Keywords :
Road Accident Prediction, Prevention, Weather Conditions, Speed Detection, Population Density, Alocholor Drug Influence, Machine Learning Algorithms and IOT sensors.
