首页|Findings in Machine Learning Reported from University of Kashmir (Classifying Victim Degree of Injury In Road Traffic Accidents: a Novel Stacked Dcl-x Approach)
Findings in Machine Learning Reported from University of Kashmir (Classifying Victim Degree of Injury In Road Traffic Accidents: a Novel Stacked Dcl-x Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Springer Nature
Data detailed on Machine Learning have been presented. According to news reporting originating in Jammu Kashmir, India, by NewsRx journalists, research stated, “Road Traffic Injuries are one of the world’s leading cause of death, with greatest burden falling on nations with lower and moderate incomes. They are consistently ranked in top 10 leading causes of mortality worldwide for persons of all ages.” The news reporters obtained a quote from the research from the University of Kashmir, “The biggest advantage of classifying victim degree of injuries in road accidents can pave a way for safer roads and reduced accident rates. This article employs California based SWITRS dataset to propose a novel approach namely Stacked DCL-X model for classifying “victim_degree_of_injury “\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{ amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$“victim\_degree\_of\_injury”$$\end{document}. It classifies injuries that might take place due to collisions occurring between vehicles and near by pedestrians, obstacles etc. on roads. To verify the superiority of our proposed model, several Machine Learning algorithm-based classification models are stacked together to classify “victim_degree_of_injury “\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{- 69pt} \begin{document}$$“victim\_degree\_of\_injury”$$\end{document}. A total of 1 27 000 accidents are considered from SWITRS dataset when determining the “victim_ degree_of_injury “\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{ wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{ document}$$“victim\_degree\_of\_injury”$$\end{document}. Machine Learning classifiers implemented in this article includes XGBoost, CatBoost, LightGBM, Decision Tree, Random Forest, Gradient Boosting and Stacked DCL-X. In addition, the algorithm used at feature selection step is Harris Hawk Optimization algorithm, a Nature Inspired Algorithm to select the best features. Prediction results shows that the proposed Stacked DCL-X model provides good stability, fewer hyper-parameters, and highest accuracy under different levels of training data volume. The values of Accuracy, Mean Square Error, and ROC-Auc in Stacked DCL-X model are 87.52, 0.5677 and 97.43, respectively. Moreover, confusion matrix and evaluation metrics of the proposed model provides better results than state-of-the-art classifiers. Statistical analysis has also been performed using Friedman’s rank test on different datasets to ensure the superiority of our proposed Stacked DCL-X model. The findings of this study would be helpful in classifying the “victim_degree_of_injury “\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{ amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$“victim\_degree\_of\_injury”$$\end{document}.”
Jammu KashmirIndiaAsiaAlgorithmsCyborgsEmerging TechnologiesMachine LearningUniversity of Kashmir
NETL
NSTL
Springer Nature
