Predicting and analyzing injury severity: A machine learning-based approach using class-imbalanced proactive and reactive data

Sarkar, Sobhan; Pramanik, Anima; Maiti, J.; Reniers, Genserik

doi:10.1016/j.ssci.2020.104616

Cited by 101 publications

(52 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, Reiman and Pietikäinen [4] showed that using both reactive and proactive data can be more useful for the organizations and decision makers. This premise is confirmed by Sarkar et al [5] in a study that demonstrated the effectiveness of using a combination of reactive and proactive data in predicting the injury severity of accidents in the workplace.…”

Section: Introductionmentioning

confidence: 55%

Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

et al. 2022

View full text Add to dashboard Cite

Highway crashes, along with the property damage, personal injuries, and fatalities that they cause, continue to present one of the most significant and critical transportation problems. At the same time, provision of safe travel is one of the main goals of any transportation system. For this reason, both in transportation research and practice much attention has been given to the analysis and modeling of traffic crashes, including the development of models that can be applied to predict crash occurrence and crash severity. In general, such models assess short-term crash risks at a given highway facility, thus providing intelligence that can be used to identify and implement traffic operations strategies for crash mitigation and prevention. This paper presents several crash risk and injury severity assessment models applied at a highway segment level, considering the input data that is typically collected or readily available to most transportation agencies in real-time and at a regional network scale, which would render them readily applicable in practice. The input data included roadway geometry characteristics, traffic flow characteristics, and weather condition data. The paper develops, tests, and compares the performance of models that employ Random effects Bayesian Logistics Regression, Gaussian Naïve Bayes, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine methods. The paper applies random oversampling examples (ROSE) method to deal with the problem of data imbalance associated with the injury severity analysis. The models were trained and tested using a dataset of 10,155 crashes that occurred on two interstate highways in New Jersey over a two-year period. The paper also analyzes the potential improvement in the prediction abilities of the tested models by adding reactive data to the analysis. To that end, traffic crashes were classified in multiple classes based on the driver age and the vehicle age to assess the impact of these attributes on driver injury severity outcomes. The results of this analysis are promising, showing that the simultaneous use of reactive and proactive data can improve the prediction performance of the presented models.

show abstract

Section: Introductionmentioning

confidence: 55%

Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

et al. 2022

View full text Add to dashboard Cite

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

“…[ Sarkar et al, (2020)] experimented with SMOTE, borderline SMOTE (BLSMOTE), majority weighted minority oversampling technique (MWMOTE), and k-means SMOTE (KMSMOTE) to handle the class imbalance issue in the prediction of injury severity using machine learning techniques. [Nnamoko and Korkontzelos ,(2020)] tackled class imbalance with SMOTE for predicting diabetes.…”

Section: Related Workmentioning

confidence: 99%

Untitled

2020

INDJCSE

View full text Add to dashboard Cite

The objective of this paper is to build a CKD prediction model using machine learning techniques that can predict the risk of chronic kidney disease (CKD) in patients with Cardiovascular Disease (CVD) or at high risk of CVD. CVD is associated with worsening of renal functions. But patients with CVD remains often underdiagnosed and undertreated for CKD because mostly the clinical diagnosis and treatment are single organ centered in earlier stages. Machine learning algorithms have been widely used to predict and classify diseases in healthcare. Healthcare data is often imbalanced. In this analysis, the CKD prediction model is built using CVD data with imbalanced distribution of positive and negative cases. The analysis involves three stages: Stage I involves selecting the best model based on performance metrics that support imbalanced class distribution without applying any resampling techniques. Stage II involves oversampling the training data of the minority class using Synthetic Minority Oversampling Technique (SMOTE) and stage III involves randomly under-sampling the training data of the majority class to solve the class imbalance. The experimental results show that the MLP (Multi-Layer Perceptron)-SMOTE model performs better in predicting CKD with a better F-score, recall, precision, G-mean, balanced accuracy and RUC-AUC when compared to other models.

show abstract

Predicting and analyzing injury severity: A machine learning-based approach using class-imbalanced proactive and reactive data

Cited by 101 publications

References 97 publications

Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

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

Untitled

Contact Info

Product

Resources

About