Modeling Traffic Accident Severity Using Neural Networks and Support Vector Machines

Pradhan, Biswajeet; Sameen, Maher Ibrahim

doi:10.1007/978-3-030-10374-3_9

Cited by 11 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given a training set, SVM builds a model that assigns new examples to one category or the other. It also works efficiently in a non-linear classification [6].…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Landslide Prediction using Machine Learning on the Edge Node in Pervasive Internet of Things

Zahoor

Mir

2021

Proceedings of the 2nd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2020, 27-28 Feb

View full text Add to dashboard Cite

In today's world, everything is connected via internet, but Internet of Things will change our life in the future. For, this to happen, large amount of data has to be generated, processed and captured by IoT and are considered to be highly useful and contain valuable information. The critical role in making things smart is through Machine Learning techniques. Machine Learning will play important role in extracting data and knowledge from the connected things after that constructing smart system that provides convenient services. The data aggregated from the IoT nodes in an IoT environment has to be analyzed in a time bound manner by using different mining algorithms such as KNN, Naïve Bayes, LDA, SVM, C4.5. So, in this paper we focus on comparative analysis of data mining algorithm on internet of things data using MATLAB. We are using various data mining software because there are resource constraints in an IoT environment, and due to resource constraints we cannot use them at device level. In order to use them at edge level, we will analyze the data using MATLAB software tools as if they are to be used at the edge level. At last our preliminary results on real IoT datasets shows that C4.5 has better accuracy and have relatively higher processing speeds in all tools we used.

show abstract

“…Given a training set, SVM builds a model that assigns new examples to one category or the other. It also works efficiently in a non-linear classification [6].…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Landslide Prediction using Machine Learning on the Edge Node in Pervasive Internet of Things

Zahoor

Mir

2021

Proceedings of the 2nd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2020, 27-28 Feb

View full text Add to dashboard Cite

show abstract

“…RF, a commonly employed tree-based ensemble ML technique, has been found to be popular in different crash injury severity studies [20] [21]. In addition to RF, other techniques that are prominently used to predict crash injury severity include decision trees [19] [21], support vector machines (SVMs) [22], and XGBoost [19] [23]. Various studies used DL techniques to predict road crash severity [22] [24] [25].…”

Section: Introductionmentioning

confidence: 99%

“…In addition to RF, other techniques that are prominently used to predict crash injury severity include decision trees [19] [21], support vector machines (SVMs) [22], and XGBoost [19] [23]. Various studies used DL techniques to predict road crash severity [22] [24] [25].…”

Section: Introductionmentioning

confidence: 99%

Road Crash Injury Severity Prediction Using a Graph Neural Network Framework

Sattar,

Ishak,

Affendey

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Crash severity prediction is a challenging research area, where the objective is to accurately assess the extent of severity of an injury resulting from road traffic accidents. The main aim of existing studies is to precisely assess the potential severity of crashes under diverse circumstances, such as weather conditions, vehicle attributes, road characteristics and layout, and traffic control factors. This effort aids authorities in establishing effective emergency response systems. The novelty and objective of our work involve contributing to this research area by employing a graph architecture to capture relationships among various crash records to uncover any hidden patterns that traditional ML models might overlook. The current study extends existing knowledge by leveraging Graph Neural Networks (GNN) and comparing their performance to popular ensemble-based models, which include Extreme Gradient Boosting (XGBoost) and Random Forest (RF) and Artificial Neural Networks (ANNs). Real data from the United Kingdom (UK) was employed to achieve our goal. All models underwent training using the training dataset, followed by performance evaluation using diverse metrics such as the accuracy, precision, recall, f1-score, Matthews Correlation Coefficient (MCC), confusion matrix, and computational cost on the test dataset. Overall, our proposed GNN-based model demonstrated better performance when compared to other models. Specifically, the GNN model outperformed all other models across all metrics. For instance, the accuracy stood at 85.55% for GNN as compared to 83.36%, 83.18%, and 83.27% for XGBoost, RF, and ANNs models, respectively. The GNN model assisted in identifying hidden patterns by considering non-linear relationships among crash records. Thus, the model had the potential to improve its ability to predict severe accidents, which could in turn significantly improve emergency response efforts and reduce the likelihood of severe accidents resulting in fatalities.

show abstract

“…Pedestrian and driver deaths and injuries due to road traffic accidents considerably affect society and can lead to substantial burdens on the national economy and healthcare system [2]. Therefore, it is necessary to investigate various aspects of traffic accidents in different geographic regions [3][4][5]. In this context, urban sustainable transportation aims to address the development of urban transport networks for supporting effective and safe mobility in urban environments.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, the accident datasets gathered from the traffic police in the form of tables and charts are complicated and not suitable for communication with planners and the public [21]. Therefore, it is essential to use effective spatial-temporal analysis techniques for better analysis of accident datasets [5,22].…”

Section: Introductionmentioning

confidence: 99%

A GIS-Based Spatiotemporal Modelling of Urban Traffic Accidents in Tabriz City during the COVID-19 Pandemic

et al. 2022

View full text Add to dashboard Cite

The main aim of the present study was to investigate the spatiotemporal trends of urban traffic accident hotspots during the COVID-19 pandemic. The severity index was used to determine high-risk areas, and the kernel density estimation method was used to identify risk of traffic accident hotspots. Accident data for the time period of April 2018 to November 2020 were obtained from the traffic police of Tabriz (Iran) and analyzed using GIS spatial and network analysis procedures. To evaluate the impacts of COVID-19, we used the seasonal variation in car accidents to analyze the change in the total number or urban traffic accidents. Eventually, the sustainability of urban transport was analyzed based on the demographic and land use data to identify the areas with a high number of accidents and its respective impacts for the local residences. Based on the results, the lockdown measures in response to the pandemic have led to significant reductions in road traffic accidents. From the perspective of urban planning, the spatiotemporal urban traffic accident analysis indicated that areas with high numbers of elderly people and children were most affected by car accidents. As we identified the hotspots of urban traffic accidents and evaluated their spatiotemporal correlation with land use and demography characteristics, we conclude that the results of this study can be used by urban managers and support decision making to improve the situation, so that fewer accidents will happen in the future.

show abstract

Modeling Traffic Accident Severity Using Neural Networks and Support Vector Machines

Cited by 11 publications

References 27 publications

Landslide Prediction using Machine Learning on the Edge Node in Pervasive Internet of Things

Landslide Prediction using Machine Learning on the Edge Node in Pervasive Internet of Things

Road Crash Injury Severity Prediction Using a Graph Neural Network Framework

A GIS-Based Spatiotemporal Modelling of Urban Traffic Accidents in Tabriz City during the COVID-19 Pandemic

Contact Info

Product

Resources

About