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

Bhuiyan, Hanif; Ara, Jinat; Hasib, Khan Md.; Sourav, Md Imran Hossain; Karim, Faria Benta; Sik-Lányi, Cecília; Governatori, Guido; Rakotonirainy, Andry; Yasmin, Shamsunnahar

doi:10.1038/s41598-022-25361-5

Cited by 20 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 summarizes the results obtained from the first set of experiments, including overall mean precision, recall, F1 score, and weighted F1 score values. The approach with the highest F1 score, which is the harmonic mean of precision and recall 25 , was considered the most accurate. The weighted F1 score was also provided to evaluate the proposed methods, considering class imbalance 26 .…”

Section: Resultsmentioning

confidence: 99%

Automated hand-marked semantic text recognition from photographs

Suh,

Lee,

Gil

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Automated text recognition techniques have made significant advancements; however, certain tasks still present challenges. This study is motivated by the need to automatically recognize hand-marked text on construction defect tags among millions of photographs. To address this challenge, we investigated three methods for automating hand-marked semantic text recognition (HMSTR)—a modified scene text recognition-based (STR) approach, a two-step HMSTR approach, and a lumped approach. The STR approach involves locating marked text using an object detection model and recognizing it using a competition-winning STR model. Similarly, the two-step HMSTR approach first localizes the marked text and then recognizes the semantic text using an image classification model. By contrast, the lumped approach performs both localization and identification of marked semantic text in a single step using object detection. Among these approaches, the two-step HMSTR approach achieved the highest F1 score (0.92) for recognizing circled text, followed by the STR approach (0.87) and the lumped approach (0.78). To validate the generalizability of the two-step HMSTR approach, subsequent experiments were conducted using check-marked text, resulting in an F1 score of 0.88. Although the proposed methods have been tested specifically with tags, they can be extended to recognize marked text in reports or books.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated hand-marked semantic text recognition from photographs

Suh,

Lee,

Gil

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Wu et al (2014) [2], Rezapour et al (2018) [24], Ma et al (2023) [25] Road barrier [26], Russo & Savolainen (2018) [27], Molan et al (2020) [28] The following six factors have been identified as potential influential factors [29].…”

Section: Comparisonmentioning

confidence: 99%

Impact Analysis of Road Infrastructure and Traffic Control on Injury Severity of Single- and Multi-vehicle Crashes

Tanishita¹,

Sekiguchi²

2023

Preprint

View full text Add to dashboard Cite

Single and multi-vehicle crashes are a significant issue that causes economic and social costs and has therefore gained attention. This study explored the factors associated with injury severity for both single- and multi-vehicle crashes using over 550,000 crash data points in Japan between 2019 and 2021. We identified the determinants of road infrastructure and traffic control while controlling for driver, vehicle, environmental, and accident characteristics by applying ordered logit and bias-reduced binomial regression models. Our findings are as follows. 1) Traffic control variables did not affect single-vehicle crashes. 2) Guardrails had a higher severity in both single-vehicle crashes and multi-vehicle crashes at intersections. 3) The impact of the centerline differed between intersections and non-intersections for multi-vehicle crashes. These results of this study provide transportation agencies with important guidance as to the road infrastructure and transport control.

show abstract

“…These methods prove to be particularly advantageous in cases where the connection between predictor attributes and the targeted levels of injury severity remains poorly understood or exhibits a highly nonlinear relationship [18] [19]. 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].…”

Section: Introductionmentioning

confidence: 99%

“…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%

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

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

Cited by 20 publications

References 26 publications

Automated hand-marked semantic text recognition from photographs

Automated hand-marked semantic text recognition from photographs

Impact Analysis of Road Infrastructure and Traffic Control on Injury Severity of Single- and Multi-vehicle Crashes

Road Crash Injury Severity Prediction Using a Graph Neural Network Framework

Contact Info

Product

Resources

About