ENHANCED TRAFFIC INCIDENT DETECTION USING FACTOR ANALYSIS AND WEIGHTED RANDOM FOREST ALGORITHM

MACHINE LEARNING

In order to reduce casualties and property damage, efficient and precise traffic incident detection is essential. In order to address the issue of unbalanced event data, this work offers a novel methodology known as FA-WRF (Factor Analysis and Weighted Random Forest). This approach combines dimensionality reduction through factor analysis with classification using weighted random forests, data preparation through the Synthetic Minority Over-sampling Technique (SMOTE), and data preparation with SMOTE. The included feature of severity detection is highlighted in this paper, as is the evaluation of the FA-WRF model using well-established metrics such as detection rate, false alarm rate, classification rate, and area under the receiver operating characteristic curve (AUC). The superiority of the FA-WRF model is illustrated using real-world expressway traffic data characterized by imbalanced incidents through thorough comparisons with various machine learning algorithms such as Support Vector machine, k-nearest neighbors, Logistic Regression, and decision trees. In addition to advancing incident detection, our technique has encouraging prospects for enhancing traffic management procedures and well-informed decision-making procedures in the context of transportation networks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.