Severity analysis of crashes on express lane facilities using support vector machine model trained by firefly algorithm

Kitali, Angela E.; Mokhtarimousavi, Seyedmirsajad; Kadeha, Cecilia; Alluri, Priyanka

doi:10.1080/15389588.2020.1840563

Cited by 15 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the support vector machine algorithm, RBF kernel function is selected. This kernel function has the characteristics of wide convergence domain and can handle a variety of samples, which is widely used [21][22][23]. RBF kernel function only involves one parameter, so its performance is more stable and easy to apply.…”

Section: Journal Of Function Spacesmentioning

confidence: 99%

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Xin

2022

Journal of Function Spaces

View full text Add to dashboard Cite

Tax forecast has an important impact on financial budget and tax plan. The amount of tax data is greatly increased, the difficulty of tax forecast is improved, and the accuracy is always difficult to keep up with the development demand. Analyze the application of optimized support vector machine model in tax prediction system. Based on the simple analysis of the research situation of tax prediction and the research status of data mining algorithm in tax data classification and prediction, this paper constructs a tax prediction model. Aiming at the problem of too many influencing factors of tax prediction, this paper puts forward the use of principal component analysis to extract the main factors, reduce the dimension of tax data, and reduce the difficulty of analysis. Support vector machine is used to realize tax prediction, aiming at the problem of parameter optimization proposed to optimize the parameters. Finally, the prediction accuracy is evaluated by comparing the error between tax prediction value and real value. The results show that the algorithm used in this paper can optimize the parameters of support vector machine. The tax prediction results show that the predicted value is similar to the real value curve. After grid search optimization, the introduction of principal component analysis reduces the redundancy and improves the prediction accuracy.

show abstract

Section: Journal Of Function Spacesmentioning

confidence: 99%

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Xin

2022

Journal of Function Spaces

View full text Add to dashboard Cite

show abstract

“…Random Forest (RF), Support Vector Machine (SVM), and Back-Propagation Neural Network (BPNN) had all been widely and successfully used in predicting the possibility of injury-severity outcome [ 25 , 26 , 27 , 28 ]. Choosing a suitable method for the crash prediction is critical.…”

Section: Methodsmentioning

confidence: 99%

Determinants and Prediction of Injury Severities in Multi-Vehicle-Involved Crashes

Song

et al. 2021

IJERPH

View full text Add to dashboard Cite

Multi-vehicle (MV) crashes, which can lead to great damages to society, have always been a serious issue for traffic safety. A further understanding of crash severity can help transportation engineers identify the critical reasons and find effective countermeasures to improve transportation safety. However, studies involving methods of machine learning to predict the possibility of injury-severity of MV crashes are rarely seen. Besides that, previous studies have rarely taken temporal stability into consideration in MV crashes. To bridge these knowledge gaps, two kinds of models: random parameters logit model (RPL), with heterogeneities in the means and variances, and Random Forest (RF) were employed in this research to identify the critical contributing factors and to predict the possibility of MV injury-severity. Three-year (2016–2018) MV data from Washington, United States, extracted from the Highway Safety Information System (HSIS), were applied for crash injury-severity analysis. In addition, a series of likelihood ratio tests were conducted for temporal stability between different years. Four indicators were employed to measure the prediction performance of the selected models, and four categories of crash-related characteristics were specifically investigated based on the RPL model. The results showed that the machine learning-based models performed better than the statistical models did when taking the overall accuracy as an evaluation indicator. However, the statistical models had a better prediction performance than the machine learning models had considering crash costs. Temporal instabilities were present between 2016 and 2017 MV data. The effect of significant factors was elaborated based on the RPL model with heterogeneities in the means and variances.

show abstract

“…Some studies adopted other machine learning models, namely Support Vector Machine 1,9,13,22 , k-nearest neighbor 19,23 , and Naïve Bayes 18,24 to analyze a wide range of crash factors such as vehicle characteristics (i.e., vehicle age, condition of vehicle, weight of the vehicle, group of light trucks and vans, occupants involved, the body type of the vehicle), road infrastructure (road function, lane width, shoulder type, accident location), environmental condition (i.e., sight distance, lighting condition, weather, crash time, month/season) and temporal characteristics (i.e., crash type, time of day, day of the week, annual average daily traffic, type of separator, roadway terrain, left shoulder width, and right shoulder width, number of vehicles). Delen et al 13 revealed that Support Vector Machine performs better in low or high injury clarification and prediction with 90.41% accuracy.…”

Section: Background Studymentioning

confidence: 99%

“…Our preliminary observation from these studies is that the Decision Tree, Random Forest, and Naïve Bayes approaches are frequently applied machine learning algorithms www.nature.com/scientificreports/ in road safety research for their regularization parameter. These algorithms are important in avoiding over-fitting, better performance with imbalanced data, and non-linearity for input and target variables 22 . Among several feature selection techniques, chi-square, two-way ANOVA, and regression analysis have also been considered for their less complexity, effectiveness, and cost-sensitive properties.…”

Section: Analytical Context Of Current Studymentioning

confidence: 99%

Crash severity analysis and risk factors identification based on an alternate data source: a case study of developing country

Bhuiyan

Ara

Hasib

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Road traffic injuries are one of the primary reasons for death, especially in developing countries like Bangladesh. Safety in land transport is one of the major concerns for road safety authorities and other policymakers. For this reason, contributory factors identification associated with crashes is necessary for reducing road crashes and ensuring transportation safety. This paper presents an analytical approach to identifying significant contributing factors of Bangladesh road crashes by evaluating the road crash data, considering three different severity levels (non-fetal, severe, and extremely severe). Generally, official crash databases are compiled from police-reported crash records. Though the official datasets are focusing on compiling a wide array of attributes, an assorted number of unreported issues can be observed that demands an alternative source of crash data. Therefore, this proposed approach considers compiling crash data from newspapers in Bangladesh which could be complimentary to the official crash database. To conduct the analysis, first, we filtered the useful features from compiled crash data using three popular feature selection techniques: chi-square, Two-way ANOVA, and Regression analysis. Then, we employed three machine learning classifiers: Decision Tree, Random Forest, and Naïve Bayes over the extracted features. A confusion matrix was considered to evaluate the proposed model, including classification accuracy, sensitivity, and specificity. The predictive machine learning model, namely, Random Forest using Label Encoder with chi-square and Two-way ANOVA feature selection process, seems the best option for crash severity prediction that provides high prediction accuracy. The resulting model highlights nine out of fourteen independent features as responsible factors. Significant features associated with crash severities include driver characteristics (gender, license type, seat belts), vehicle characteristics (vehicle type), road characteristics (road surface type, road classification), environmental conditions (day of crash occurred, time of crash), and injury localization. This outcome may contribute to improving traffic safety of Bangladesh.

show abstract

Severity analysis of crashes on express lane facilities using support vector machine model trained by firefly algorithm

Cited by 15 publications

References 11 publications

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Determinants and Prediction of Injury Severities in Multi-Vehicle-Involved Crashes

Crash severity analysis and risk factors identification based on an alternate data source: a case study of developing country

Contact Info

Product

Resources

About