Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

Lee, Jong-Hak; Yoon, Taekwan; Kwon, Sangil

doi:10.3390/app10010129

Cited by 55 publications

(22 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The activation function is responsible for making a neural network non-linear [19]. The tangent, hyperbolic, sigmoid, and linear functions are commonly chosen activation functions [20].…”

Section: Methodsmentioning

confidence: 99%

PSO-ANN in preventing traffic collisions: a comparative study

Ashikuzzaman

Akram

Anik

et al. 2021

IJEECS

View full text Add to dashboard Cite

Traffic accident is a global threat which causes health and economic casualties all around the world. Due to the expansion of transportation systems, congestion can lead to spike road accident. Every year thousands of people have died due to traffic accidents. Various technologies have been adopted by modern cities to minimize traffic accidents. Therefore, to ensure people’s safety, the concept of the smart city has been introduced. In a smart city, factors like road, light, and weather conditions are important to consider to predict traffic mishap. Several machine learning models have been implemented in the existing literature to determine and predict traffic collision. But the accuracy is not enough and there exist a lot of challenges in determining the accident. In this paper, an approach of particle swarm optimization with artificial neural network (PSO-ANN) has been proposed to determine traffic collision using the dataset of the transport department of United Kingdom. The performance of PSO-ANN outperforms the existing machine learning model. PSO-ANN model can be adopted in the transportation system to counter traffic accident issues. Random Forest, Naıve Bayes, Nearest Centroid, K-Nearest Neighbor classification have been used to compare with the proposed PSO-ANN model.

show abstract

“…The activation function is responsible for making a neural network non-linear [19]. The tangent, hyperbolic, sigmoid, and linear functions are commonly chosen activation functions [20].…”

Section: Methodsmentioning

confidence: 99%

PSO-ANN in preventing traffic collisions: a comparative study

Ashikuzzaman

Akram

Anik

et al. 2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…The results of the study revealed that AdaBoost outperformed the other methods. Furthermore, in [25][26][27], the authors investigated road accidents using real-life data considering methods such as J48, LSSVM, and RF. Other studies used probabilistic reasoning models such as Bayesian networks, or BNs, [28][29][30][31][32], with [28] performing a comparison between BNs and regression models.…”

Section: Related Studiesmentioning

confidence: 99%

Comparative Study of Machine Learning Classifiers for Modelling Road Traffic Accidents

2022

View full text Add to dashboard Cite

Road traffic accidents (RTAs) are a major cause of injuries and fatalities worldwide. In recent years, there has been a growing global interest in analysing RTAs, specifically concerned with analysing and modelling accident data to better understand and assess the causes and effects of accidents. This study analysed the performance of widely used machine learning classifiers using a real-life RTA dataset from Gauteng, South Africa. The study aimed to assess prediction model designs for RTAs to assist transport authorities and policymakers. It considered classifiers such as naïve Bayes, logistic regression, k-nearest neighbour, AdaBoost, support vector machine, random forest, and five missing data methods. These classifiers were evaluated using five evaluation metrics: accuracy, root-mean-square error, precision, recall, and receiver operating characteristic curves. Furthermore, the assessment involved parameter adjustment and incorporated dimensionality reduction techniques. The empirical results and analyses show that the RF classifier, combined with multiple imputations by chained equations, yielded the best performance when compared with the other combinations.

show abstract

“…Farhangi et al [10] Accident-risk modeling and mapping Lee et al [25] Accident severity prediction Mestri et al [26] Identification of accident-prone locations Al-dogom et al [21] Spatio-temporal analysis for accidents prediction Fan et al [27] Identification of accident black spots and analyzing their characteristics…”

Section: Paper Machine Learning Applicationmentioning

confidence: 99%

Evaluation of Tree-Based Machine Learning Algorithms for Accident Risk Mapping Caused by Driver Lack of Alertness at a National Scale

et al. 2021

View full text Add to dashboard Cite

Drivers’ lack of alertness is one of the main reasons for fatal road traffic accidents (RTA) in Iran. Accident-risk mapping with machine learning algorithms in the geographic information system (GIS) platform is a suitable approach for investigating the occurrence risk of these accidents by analyzing the role of effective factors. This approach helps to identify the high-risk areas even in unnoticed and remote places and prioritizes accident-prone locations. This paper aimed to evaluate tuned machine learning algorithms of bagged decision trees (BDTs), extra trees (ETs), and random forest (RF) in accident-risk mapping caused by drivers’ lack of alertness (due to drowsiness, fatigue, and reduced attention) at a national scale of Iran roads. Accident points and eight effective criteria, namely distance to the city, distance to the gas station, land use/cover, road structure, road type, time of day, traffic direction, and slope, were applied in modeling, using GIS. The time factor was utilized to represent drivers’ varied alertness levels. The accident dataset included 4399 RTA records from March 2017 to March 2019. The performance of all models was cross-validated with five-folds and tree metrics of mean absolute error, mean squared error, and area under the curve of the receiver operating characteristic (ROC-AUC). The results of cross-validation showed that BDT and RF performance with an AUC of 0.846 were slightly more accurate than ET with an AUC of 0.827. The importance of modeling features was assessed by using the Gini index, and the results revealed that the road type, distance to the city, distance to the gas station, slope, and time of day were the most important, while land use/cover, traffic direction, and road structure were the least important. The proposed approach can be improved by applying the traffic volume in modeling and helps decision-makers take necessary actions by identifying important factors on road safety.

show abstract

Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

Cited by 55 publications

References 48 publications

PSO-ANN in preventing traffic collisions: a comparative study

PSO-ANN in preventing traffic collisions: a comparative study

Comparative Study of Machine Learning Classifiers for Modelling Road Traffic Accidents

Evaluation of Tree-Based Machine Learning Algorithms for Accident Risk Mapping Caused by Driver Lack of Alertness at a National Scale

Contact Info

Product

Resources

About