Related Experiment Video
Updated: Jul 5, 2025
14:55
Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
Published on: January 20, 2023
3.3K
Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways
Humera Khanum1,2, Anshul Garg1, Mir Iqbal Faheem3
1School of Civil Engineering, Lovely Professional University, Phagwara, Punjab, 1444411, India.
F1000Research
|January 15, 2024
Summary
This study used a random forest model to predict traffic accident severity on Indian highways. The model achieved 67% accuracy on training data but only 41.47% on test data, indicating potential dataset issues.
Area of Science:
- Road safety research
- Artificial intelligence in transportation
- Machine learning for accident analysis
Background:
- Road accidents cause over 1.35 million global deaths annually, with India experiencing a significant burden.
- In 2019, India recorded 449,002 road accidents, resulting in 151,113 deaths and 451,361 injuries.
- Accident severity modeling is crucial for identifying risk factors and informing preventive measures.
Purpose of the Study:
- To develop a predictive model for traffic accident severity on Indian highways.
- To apply the random forest algorithm for enhanced prediction accuracy.
- To analyze contributing factors to accident severity using machine learning.
Main Methods:
- Data collection and preprocessing from MoRTH and NHAI.
- Feature selection and random forest model training.
- Hyperparameter tuning using grid search and model evaluation with accuracy and F1 score.
Main Results:
- The random forest model achieved 67% accuracy and a 0.64 weighted F1-score on the training set.
- The model's accuracy dropped to 41.47% on the test set, suggesting dataset imbalance or bias.
- No significant correlation was found between the day of the week and accident occurrence or severity.
Conclusions:
- The random forest model showed limitations in predicting accident severity on unseen data.
- Addressing dataset imbalance and refining hyperparameters are key to improving model performance.
- Enhanced data recording systems and machine learning integration are recommended for better road safety outcomes.
Related Concept Videos
01:19Survival Tree
86
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
86
01:08Determination of Expected Frequency
2.2K
Suppose one wants to test independence between the two variables of a contingency table. The values in the table constitute the observed frequencies of the dataset. But how does one determine the expected frequency of the dataset? One of the important assumptions is that the two variables are independent, which means the variables do not influence each other. For independent variables, the statistical probability of any event involving both variables is calculated by multiplying the individual...
2.2K
01:16Hypothesis Test for Test of Independence
3.6K
The test of independence is a chi-square-based test used to determine whether two variables or factors are independent or dependent. This hypothesis test is used to examine the independence of the variables. One can construct two qualitative survey questions or experiments based on the variables in a contingency table. The goal is to see if the two variables are unrelated (independent) or related (dependent). The null and alternative hypotheses for this test are:
H0: The two variables (factors)...
H0: The two variables (factors)...
3.6K
01:21Introduction to Test of Independence
2.3K
In statistics, the term independence means that one can directly obtain the probability of any event involving both variables by multiplying their individual probabilities. Tests of independence are chi-square tests involving the use of a contingency table of observed (data) values.
The test statistic for a test of independence is similar to that of a goodness-of-fit test:
The test statistic for a test of independence is similar to that of a goodness-of-fit test:
2.3K
01:03Prediction Intervals
2.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.3K
01:11Hazard Rate
112
The hazard rate, also known as the hazard function or failure rate, is a statistical measure used to describe the instantaneous rate at which an event occurs, given that the event has not yet happened. From a probabilistic perspective, it represents the likelihood that a subject will experience the event in a very small time interval, conditional on surviving up to the beginning of that interval. In terms of frequency, the hazard rate can be viewed as the ratio of the number of events to the...
112