Human Error Analysis in Maritime Accidents: A Hybrid Machine Learning Approach for Enhanced Predictive Modeling
TL;DR
An advanced classification model that combines Random Forest, Gradient Boosting, XGBoost, LightGBM, and neural networks through a soft voting ensemble mechanism is developed, indicating that specific human element factors have significant correlations with particular accident types.
Abstract
This study presents a novel hybrid machine learning approach for analyzing human error factors in maritime accidents using HELCOM accident data. We developed an advanced classification model that combines Random Forest, Gradient Boosting, XGBoost, LightGBM, and neural networks through a soft voting ensemble mechanism. Our methodology includes enhanced data preprocessing techniques, sophisticated feature engineering, and class imbalance correction through SMOTE resampling. The visualizations produced meet publication-quality standards with optimized color schemes, typography, and statistical representations suitable for high-impact journals. The hybrid model achieved 84% accuracy with macro-averaged F1-score of 0.58 across eight accident classes, identifying key human factors contributing to maritime incidents. Our findings indicate that specific human element factors have significant correlations with particular accident types, offering valuable insights for maritime safety policy development and accident prevention strategies. This research contributes to the growing field of data-driven maritime risk assessment by providing a robust methodological framework for human error analysis in the maritime domain.