A SVM based ship collision risk assessment algorithm

Zheng, Kai; Chen, Yabo; Jiang, Yi; Qiao, Shuanghu

doi:10.1016/j.oceaneng.2020.107062

Cited by 52 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, various machine learning methods and spatial regression models have been increasingly used in traffic accident research due to their capacity for superfitting to nonlinear problems. Among them, support vector machine (SVM) methods use kernel functions for nonlinear classification [58][59][60]; hierarchical clustering algorithms divide traffic impacts into layers based on data distribution [61]; K-means clustering algorithms and GWR both perform cluster analysis based on the collection distance of sample points [62]; and deep learning is often applied to general graph models or hypergraph models without massive constraints [62], such as image recognition of traffic accidents in social media and black spot recognition in urban traffic safety [63][64][65]. However, the earlier studies present a lack of accuracy due to the errors and unobserved variances.…”

Section: Methodological Reviewmentioning

confidence: 99%

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Yang

Chung

Kim

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

In cities, road traffic accidents are critical endangerment to people’s safety. A vast number of studies which are designed to understand these accidents’ leading causes and mechanisms exist. The widely held view is that emerging analysis methods can be a critical tool for understanding the complex interactions between land use and urban transportation. Using a case study of Suzhou Industrial Park (SIP) in Suzhou, China, this paper examines the relationship between different land use types and traffic accidents using a gradient boosting model (GBM) machine learning method. The results show that the GBM can be used as an effective accident model for a variety of research and analysis methods by (1) ranking the influential factors, (2) testing the degree of interpretation of each variable as the complexity of iterations changes, and (3) obtaining partial dependence plots, among other methods. The findings of this study also suggest that land use types—including facility points—demonstrate differing degrees of influence at two geographical scales: local level and neighborhood level. In the ranking of relative importance at both scales, the variables of education institutions, traffic lights, and service institutions are all ranked high—with a more significant influence on the occurrence of accidents. However, residential land and land use mix variables differed significantly in both scales and showed a significant deviation compared to the other results. When adjusting the complexity of the decision tree, the local level is more suitable for measuring variables such as residential areas and green parks where pedestrians and vehicles have fixed mobility periods and moderate flows. On the contrary, the nearest neighborhood level is more suitable to a small number of variables related to public service facilities at fixed locations, such as traffic lights and bus stops. In the partial dependence plots, all variables, except educational institutions and residences, show a positive correlation for accidents in the fitting process. The results of this study can ideally help inform transportation planners to reconsider transport accident occurrence rates in the context of the proximity to various land use types and public service facilities.

show abstract

Section: Methodological Reviewmentioning

confidence: 99%

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Yang

Chung

Kim

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Due to its advanced properties, compared to other techniques, SVM considers the best algorithm for classification and regression (Ping & Yongheng, 2011). As such, a lot of recent studies also developed models based on robust classifier SVM (Al-Hadeethi et al, 2020;Jalal et al, 2020;Kouziokas, 2020;Luo et al, 2020;Yu et al, 2018;Zheng et al, 2020). This paper also used industry-standard LR (Ohlson, 1980) and CART (Breiman et al, 1984) to compare with the above-mentioned trendy classifiers.…”

Section: Literature Reviewmentioning

confidence: 99%

Feature selection in credit risk modeling: an international evidence

Zhou

Uddin

Habib

et al. 2021

Economic Research-Ekonomska Istraživanja

View full text Add to dashboard Cite

This paper aims to discover a suitable combination of contemporary feature selection techniques and robust prediction classifiers. As such, to examine the impact of the feature selection method on classifier performance, we use two Chinese and three other real-world credit scoring datasets. The utilized feature selection methods are the least absolute shrinkage and selection operator (LASSO), multivariate adaptive regression splines (MARS). In contrast, the examined classifiers are the classification and regression trees (CART), logistic regression (LR), artificial neural network (ANN), and support vector machines (SVM). Empirical findings confirm that LASSO's feature selection method, followed by robust classifier SVM, demonstrates remarkable improvement and outperforms other competitive classifiers. Moreover, ANN also offers improved accuracy with feature selection methods; LR only can improve classification efficiency through performing feature selection via LASSO. Nonetheless, CART does not provide any indication of improvement in any combination. The proposed credit scoring modeling strategy may use to develop policy, progressive ideas, operational guidelines for effective credit risk management of lending, and other financial institutions. The finding of this study has practical value, as to date, there is no consensus about the combination of feature selection method and prediction classifiers.

show abstract

“…After decades of development, ship's domain is widely used in the marine field, including the ship's collision avoidance (Szlapczynski et al, 2018;Mou et al, 2020), the risk assessment of ship's traffic (Chai et al, 2020;Zheng et al, 2020;Rawson and Brito, 2021) and the waterway traffic capacity (Zhang et al, 2017;Weng et al, 2020). More importantly, different domain theories have been proposed continuously.…”

Section: Overview Of Ship Domainmentioning

confidence: 99%

Dynamic risk prewarning in ship encounter process considering domain violation

Qin

Guo-liang

et al. 2021

J. Navigation

View full text Add to dashboard Cite

A ship's perception of risk is an important basis for collision avoidance. To improve such perception, several risk measurement parameters on the ship domain are determined, including the approach factor, the time to domain violation (TDV) and the possible collision domain. Then, a risk hierarchy prewarning (RHP) model based on the violation detection of a ship domain is proposed, in which a two-level alarm scheme is adopted accordingly. A low-intensity alarm will be activated by reaching the minimum approach factor and the TDV threshold, and a high-intensity alarm will be activated by the factor of the possible collision domain and the TDV threshold. Subsequently, a novel guard zone in ARPA radar utilising the RHP model has been developed to establish a ship's risk perception system for officers on watch at sea. The model proposed in this paper can not only enhance the veracity of risk assessment around our own ship, but also be used as a decision support system for collision avoidance.

show abstract

A SVM based ship collision risk assessment algorithm

Cited by 52 publications

References 24 publications

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Feature selection in credit risk modeling: an international evidence

Dynamic risk prewarning in ship encounter process considering domain violation

Contact Info

Product

Resources

About