A machine vision method for the evaluation of ship-to-ship collision risk

Predicting types of human-related maritime accidents with explanations using selective ensemble learning and SHAP method

“…The results indicated that ship type and poor visibility would increase the likelihood of ship accidents. In addition, a novel research area is the development of anomaly detection models using ship traffic data and machine learning for real-time monitoring of ship risks [ 26 ]. Rawson et al [ 27 ] developed extreme gradient boosting (XGBoost) model, random forest (RF) model, support vector machines (SVM) model, and logistic regression ( ) model to monitor the risk of maritime navigation under adverse weather conditions.…”