Traffic Incident Detection Method Based on Factor Analysis and Weighted Random Forest

Abstract

Timely and accurate detection of traffic incidents can effectively reduce personal casualties and property losses, and improve the ability of macro-control and scientific decisionmaking of traffic. The unbalance of traffic incident data has a great influence on the detection effect. Therefore, a traffic incident detection method based on factor analysis and weighted random forest (FA-WRF) is designed. Through the analysis of the change rule of traffic flow parameters to build the initial incident variable. The factor analysis (FA) method is used to reduce the dimension of the initial incident variables. Using Bootstrap improved algorithm to predetermine the data extraction standard of the training set. The MCC coefficient value is calculated for the classification effect of the decision tree after training, and is assigned to each tree as a weight value, so as to ensure that the trees with better classification ability have more voting power in the voting process, thus improve the overall classification performance of the random forest (RF) algorithm for unbalanced data. The detection performance is evaluated by the common criteria including the detection rate, the false alarm rate, the classification rate and the area under the curve of the receiver operating characteristic (AUC). Based on the location detector data from expressway, the incident data in which accounts for 6.5%, showing a typical unbalance. The experimental results indicate that the model based on FA-WRF has the better classification effect. Meanwhile it is competitive in processing unbalanced data classification compared with Support Vector Machine.

Automated Traffic Incident Detection: Coping With Imbalanced and Small Datasets

“…Random forest (RF) was used to train the data set, and Matthews correlation coefficient (MCC) is calculated for the classification results as a new weight value to test data, so as to improve the overall classification performance of random forest algorithm for unbalanced data. The experimental results demonstrate that the model based on FA-WRF has better classification effect and is more competitive in dealing with imbalanced data classification [22]. In 2020, a hybrid AID method using Random Forest-Recursive Feature Elimination (RF-RFE) algorithm and Long-Short Term Memory (LSTM) network optimized by Bayesian Optimization Algorithm (BOA) was proposed.…”

“…For Problem 1: for the scarcity of samples, there are three common strategies: 1) improve the algorithm itself to apply to the dataset [22], 2) cost-sensitive learning approaches, 3) change the size of the sample. In contrast, because the third strategy is more simple to use, the application scope is more widely and popular.…”

Expressway Traffic Flow Missing Data Repair Method Based on Coupled Matrix-Tensor Factorizations

“…2 are the Lagrangian multipliers [31], ρ is the penalty coefficient ( > 0), and tr is the trace of the matrix, that is, the sum of the diagonal elements in the matrix. e iterative calculation formula of ( 9) is…”

An Improved Distribution Cost Model Considering Various Temperatures and Random Demands: A Case Study of Harbin Cold-Chain Logistics

“…In recent years, research on cold chain logistics distribution has concentrated on solving the VRP [10][11][12][13][14]. However, considering the spoilage of fresh food and the complex traffic environment, researchers found that the shortest paths may not necessarily lead to the lowest distribution cost.…”