Predicting Injury Severity of Road Traffic Accidents Using a Hybrid Extreme Gradient Boosting and Deep Neural Network Approach

Pradhan, Biswajeet; Sameen, Maher Ibrahim

doi:10.1007/978-3-030-10374-3_10

Cited by 18 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of potential predictors in this study was rather large at 26. Because it was necessary to preserve as much information contained in the predictors as possible and avoid removing any predictors completely, three machine learning techniques based on ensembles of regression trees were used: random forest (Krishnaveni and Hemalatha, 2011), gradient boosting machines (Pradhan and Sameen, 2020), and bagging regression trees (Sutton, 2005). A number of combinations of predictors were created to see how the various combinations of predictors performed.…”

Section: Methodsmentioning

confidence: 99%

Predicting the Segment-Based Effects of Heterogeneous Traffic and Road Geometric Features on Fatal Accidents

Siregar¹,

Tjahjono²,

Yusuf³

2022

IJTech

View full text Add to dashboard Cite

Inter-urban roads in Indonesia are characterized mainly by distinct road geometry and heterogeneous traffic features. The accident database from the Republic of Indonesia National Traffic Police recorded a substantial number of fatal accidents and fatalities along inter-urban roads. This study aimed to analyze the effects of traffic heterogeneity and road geometry features on fatal accidents along inter-urban roads in South Sulawesi, Indonesia. Segment-based accident analysis was adopted to minimize bias due to the large standard deviations of road lengths. Vehicle-specific speeds, speed standard deviations, and volumes of six vehicle categories, road surface condition, and road geometry were the classified predicting factors. A machine learning technique was adopted to produce predictions of the classification problem. A total of 1,068 road segment observations from 2013-2016 were used to build and validate the model. Model generalization was carried out using the out-of-sample 2019 data. With 26 potential predictors, three machine learning techniques based on the ensembles of regression trees were used to avoid removing potential predictors altogether. The results indicate that road-related features show the greatest importance in predicting the number of fatal accidents. Among the speed features, the average speed of angkots and speed standard deviation of motorcycles showed the greatest importance. The average daily traffic (ADT) of pickups had the greatest importance among other vehicle-specific ADTs.

show abstract

Section: Methodsmentioning

confidence: 99%

Predicting the Segment-Based Effects of Heterogeneous Traffic and Road Geometric Features on Fatal Accidents

Siregar¹,

Tjahjono²,

Yusuf³

2022

IJTech

View full text Add to dashboard Cite

show abstract

“…It has the computational efficiency, speed learning ability and capable processing of the Gradient tree boosting algorithm developed by [38]. The ensemble learning of decision three was applied in the XGB algorithms and can be used for both regression and classification [39]. However, since the pronouncement of this new algorithm to the best authors' knowledge there is no published research indicating the application of XGB in streamflow forecasting in general and as essential means of input section with a wavelet.…”

Section: Methods and Modeling Development A Extreme Gradient Boomentioning

confidence: 99%

Non-Linear Input Variable Selection Approach Integrated With Non-Tuned Data Intelligence Model for Streamflow Pattern Simulation

et al. 2019

View full text Add to dashboard Cite

Streamflow modeling is considered as an essential component for water resources planning and management. There are numerous challenges related to streamflow prediction that are facing water resources engineers. These challenges due to the complex processes associated with several natural variables such as non-stationarity, non-linearity, and randomness. In this study, a new model is proposed to predict long-term streamflow. Several lags that cover several years are abstracted using the potential of Extreme Gradient Boosting (XGB) then after the selected inputs variables are imposed into the predictive model (i.e., Extreme Learning Machine (ELM)). The proposed model is compared with the stand-alone schema in which the optimum lags of the variables are supplied into the XGB and ELM models. Hydrological variables including rainfall, temperature and evapotranspiration are used to build the model and predict the streamflow at Goksu-Himmeti basin in Turkey. The results showed that XGB model performed an excellent result in which can be used for predicting the streamflow pattern. Also, it is clear from the attained results that the accuracy of the streamflow prediction using XGB technique could be improved when the high number of lags was used. However, the implementation of the XGB is tree-based technique in which several issues could be raised such as overfitting problem. The proposed schema XGBELM in which XGB approach is selected the correlated inputs and ranking them according to their importance; then after, the selected inputs are supplied into the ELM model for the prediction process. The XGBELM model outperformed the stand-alone schema of both XGB and ELM models and the high-lagged schema of the XGB. It is important to indicate that the XGBELM model found to improve the prediction ability with minimum variables number.INDEX TERMS Correlated variables, non-linear XGB approach, extreme learning machine, streamflow simulation.

show abstract

“…To overcome the limitations of statistical models, ML approaches have been increasingly employed to model the potentially nonlinear relationships between crash severity outcomes and the contributing factors [ 51 , 52 , 53 , 54 , 55 , 56 , 57 ]. ML methods are more flexible with no or fewer model assumptions for input variables, and also have better fitting characteristics.…”

Section: Related Workmentioning

confidence: 99%

Exploring the Injury Severity Risk Factors in Fatal Crashes with Neural Network

Jamal

Umer

2020

IJERPH

View full text Add to dashboard Cite

A better understanding of circumstances contributing to the severity outcome of traffic crashes is an important goal of road safety studies. An in-depth crash injury severity analysis is vital for the proactive implementation of appropriate mitigation strategies. This study proposes an improved feed-forward neural network (FFNN) model for predicting injury severity associated with individual crashes using three years (2017–2019) of crash data collected along 15 rural highways in the Kingdom of Saudi Arabia (KSA). A total of 12,566 crashes were recorded during the study period with a binary injury severity outcome (fatal or non-fatal injury) for the variable to be predicted. FFNN architecture with back-propagation (BP) as a training algorithm, logistic as activation function, and six number of hidden neurons in the hidden layer yielded the best model performance. Results of model prediction for the test data were analyzed using different evaluation metrics such as overall accuracy, sensitivity, and specificity. Prediction results showed the adequacy and robust performance of the proposed method. A detailed sensitivity analysis of the optimized NN was also performed to show the impact and relative influence of different predictor variables on resulting crash injury severity. The sensitivity analysis results indicated that factors such as traffic volume, average travel speeds, weather conditions, on-site damage conditions, road and vehicle type, and involvement of pedestrians are the most sensitive variables. The methods applied in this study could be used in big data analysis of crash data, which can serve as a rapid-useful tool for policymakers to improve highway safety.

show abstract

Predicting Injury Severity of Road Traffic Accidents Using a Hybrid Extreme Gradient Boosting and Deep Neural Network Approach

Cited by 18 publications

References 19 publications

Predicting the Segment-Based Effects of Heterogeneous Traffic and Road Geometric Features on Fatal Accidents

Predicting the Segment-Based Effects of Heterogeneous Traffic and Road Geometric Features on Fatal Accidents

Non-Linear Input Variable Selection Approach Integrated With Non-Tuned Data Intelligence Model for Streamflow Pattern Simulation

Exploring the Injury Severity Risk Factors in Fatal Crashes with Neural Network

Contact Info

Product

Resources

About