Exploring the Efficacy of Artificial Intelligence in Speed Prediction: Explainable Machine-Learning Approach

Journal of Computing in Civil Engineering, Год журнала: 2025, Номер 39(2)

Опубликована: Янв. 9, 2025

Язык: Английский

---

Ordinal Random Tree with Rank-Oriented Feature Selection (ORT-ROFS): A Novel Approach for the Prediction of Road Traffic Accident Severity

Mathematics, Год журнала: 2025, Номер 13(2), С. 310 - 310

Опубликована: Янв. 18, 2025

Road traffic accident severity prediction is crucial for implementing effective safety measures and proactive management strategies. Existing methods often treat this as a nominal classification problem use traditional feature selection techniques. However, ordinal that account the ordered nature of (e.g., slight < serious fatal injuries) in still need to be investigated thoroughly. In study, we propose novel approach, Ordinal Random Tree with Rank-Oriented Feature Selection (ORT-ROFS), which utilizes inherent ordering class labels both stages classification. The proposed approach enhances model performance by separately determining importance based on levels. experiments demonstrated effectiveness ORT-ROFS an accuracy 87.19%. According results, method improved 10.81% over state-of-the-art studies average different train–test split ratios. addition, it achieved improvement 4.58% methods. These findings suggest promising accurate prediction, supporting road planning intervention

Язык: Английский

---

Towards Safer Roads: Predicting the Severity of Traffic Accident in Montreal using Machine Learning

Опубликована: Май 13, 2024

Traffic accidents are among the most common causes of death worldwide. According to statistics from World Health Organization (WHO), 50 million people involved in traffic every year. Canada, particularly Montreal, is not immune this problem. Data Soci&eacute;t&eacute; de l&rsquo;Assurance Automobile du Qu&eacute;bec (SAAQ) shows that there were 392 deaths on roads 2022, 38 them related city Montreal. This value represents an increase 29.3% for Montreal compared average years 2017 2021. In context, it important take concrete measures improve safety article, we present a web-based solution based machine learning predicts severity uses dataset occurred between 2012 and Classification algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical (CatBoost), Random Forest (RF) (GB) used develop prediction model. When evaluating model, performance metrics precision, recall, F1 score, accuracy taken into account. The analysis excellent 96% model XGBoost classifier. other models (CatBoost, RF, GB) achieved 95%, 93% 89% accuracy, respectively. classifier was deployed using client-server web application managed by Swagger-UI Flask Python framework.

Язык: Английский

---

Towards Safer Roads: Predicting the Severity of Traffic Accident in Montreal Using Machine Learning

Опубликована: Июнь 13, 2024

Traffic accidents are among the most common causes of death worldwide. According to statistics from World Health Organization (WHO), 50 million people involved in traffic every year. Canada, particularly Montreal, is not immune this problem. Data Soci&eacute;t&eacute; de l&rsquo;Assurance Automobile du Qu&eacute;bec (SAAQ) shows that there were 392 deaths on roads 2022, 38 them related city Montreal. This value represents an increase 29.3% for Montreal compared average years 2017 2021. In context, it important take concrete measures improve safety article, we present a web-based solution based machine learning predicts severity uses dataset occurred between 2012 and Classification algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical (CatBoost), Random Forest (RF) (GB) used develop prediction model. When evaluating model, performance metrics precision, recall, F1 score, accuracy taken into account. The analysis excellent 96% model XGBoost classifier. other models (CatBoost, RF, GB) achieved 95%, 93% 89% accuracy, respectively. classifier was deployed using client-server web application managed by Swagger-UI Flask Python framework.

Язык: Английский

---

An injury severity-based methodology for assessing priority areas for shared micromobility accident risk mitigation

Travel Behaviour and Society, Год журнала: 2024, Номер 39, С. 100962 - 100962

Опубликована: Ноя. 21, 2024

Язык: Английский

---

URBAN TRAFFIC CRASH ANALYSIS USING DEEP LEARNING TECHNIQUES

Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska, Год журнала: 2023, Номер 13(3), С. 56 - 63

Опубликована: Сен. 30, 2023

Road accidents are concerningly increasing in Andhra Pradesh. In 2021, Pradesh experienced a 20 percent upsurge road accidents. The state's unfortunate position of being ranked eighth terms fatalities, with 8,946 lives lost 22,311 traffic accidents, underscores the urgent nature problem. significant financial impact on victims and their families stresses necessity for effective actions to reduce This study proposes framework that collects accident data from regions, namely Patamata, Penamaluru, Mylavaram, Krishnalanka, Ibrahimpatnam, Gandhinagar Vijayawada (India) 2019 2021. dataset comprises over 12,000 records data. Deep learning techniques applied classify severity into Fatal, Grievous, Severe Injuries. classification procedure leverages advanced neural network models, including Multilayer Perceptron, Long-Short Term Memory, Recurrent Neural Network, Gated Unit. These models trained collected accurately predict project make important contributions suggesting proactive measures policies frequency

Язык: Английский

---

Toward Safer Roads: Predicting the Severity of Traffic Accidents in Montreal Using Machine Learning

Electronics, Год журнала: 2024, Номер 13(15), С. 3036 - 3036

Опубликована: Авг. 1, 2024

Traffic accidents are among the most common causes of death worldwide. According to statistics from World Health Organization (WHO), 50 million people involved in traffic every year. Canada, particularly Montreal, is not immune this problem. Data Société de l’Assurance Automobile du Québec (SAAQ) show that there were 392 deaths on roads 2022, 38 them related city Montreal. This value represents an increase 29.3% for Montreal compared with average years 2017 2021. In context, it important take concrete measures improve safety article, we present a web-based solution based machine learning predicts severity uses dataset occurred between 2012 and By predicting accidents, our approach aims identify key factors influence whether accident serious or not. Understanding these can help authorities implement targeted interventions prevent severe allocate resources more effectively during emergency responses. Classification algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical (CatBoost), Random Forest (RF), (GB) used develop prediction model. Performance metrics precision, recall, F1 score, accuracy evaluate The performance analysis shows excellent 96% model XGBoost classifier. other models (CatBoost, RF, GB) achieved 95%, 93%, 89% accuracy, respectively. classifier was deployed using client–server web application managed by Swagger-UI, Angular, Flask Python framework. study makes significant contributions field employing ensemble supervised algorithms, achieving high developing real-time application. enables quicker effective responses services, potentially reducing impact improving overall safety.

Язык: Английский

---

A Multilayer Perceptron Artificial Neural Network Study of Fatal Road Traffic Crashes

Journal of Data Analysis and Information Processing, Год журнала: 2024, Номер 12(03), С. 419 - 431

Опубликована: Янв. 1, 2024

This paper examines the relationship between fatal road traffic accidents and potential predictors using multilayer perceptron artificial neural network (MLANN) models. The initial analysis employed twelve predictors, including volume, prevailing weather conditions, roadway characteristics features, drivers' age gender, number of lanes. Based on output model variables' importance factors, seven significant variables are identified used for further to improve performance is optimized by systematically changing parameters, hidden layers activation function both layers. performances MLANN models evaluated percentage achieved accuracy, R-squared, Sum Square Error (SSE) functions.

Язык: Английский

---

Online Traffic Crash Risk Inference Method Using Detection Transformer and Support Vector Machine Optimized by Biomimetic Algorithm

Biomimetics, Год журнала: 2024, Номер 9(11), С. 711 - 711

Опубликована: Ноя. 19, 2024

Despite the implementation of numerous interventions to enhance urban traffic safety, estimation risk crashes resulting in life-threatening and economic costs remains a significant challenge. In light above, an online inference method for crash based on self-developed TAR-DETR WOA-SA-SVM methods is proposed. The method's robust data capabilities can be applied autonomous mobile robots vehicle systems, enabling real-time road condition prediction, continuous monitoring, timely roadside assistance. First, dataset object detection, named TAR-1, created by extracting information from major roads around Hainan University China incorporating Russian car news. Secondly, we develop innovative Context-Guided Reconstruction Feature Network-based Urban Traffic Objects Detection Model (TAR-DETR). model demonstrates detection accuracy 76.8% objects, which exceeds performance other state-of-the-art models. employed TAR-1 extract features, feature was designated as TAR-2. TAR-2 comprises six features three categories. A new algorithm proposed optimize parameters (C, g) SVM, thereby enhancing robustness inference. developed combining Whale Optimization Algorithm (WOA) Simulated Annealing (SA), Hybrid Bionic Intelligent Algorithm. inputted into Support Vector Machine (SVM) optimized using hybrid used infer crashes. achieves average 80%

Язык: Английский

---

Trend analysis of traffic management based on literature data mining and graph analysis tools

IET Intelligent Transport Systems, Год журнала: 2023, Номер 17(11), С. 2115 - 2130

Опубликована: Авг. 14, 2023

Abstract Studites on traffic management is crucial for the development of intelligent transportation systems and smart cities. However, identifying stages field based bibliometric analysis still lacking. In this study, CiteSpace VOSviewer software are used to explore “traffic management” by summarizing process predicting future research trend. A total 3,028 relevant documents over past 40 years were collected from Web Science. Results show that (1) studies mainly published researchers USA (30.55%), China (20.90%), some European countries; (2) key contents can be classified into four categories, is, background requirements, problems, method models, control strategies; (3) evolution divided stages, budding stage (1990–1994), (1995–2003), calm (2004–2010), maturation (2011–); (4) machine learning, deep learning other algorithms have played more important roles in recent years, connected vehicle also a potential suggest cooperative vehicle‐infrastructure or learning‐based might hotspots studies.

Язык: Английский

---