Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor.
Li KuangHan YanYujia ZhuShenmei TuXiaoliang FanPublished in: J. Intell. Transp. Syst. (2019)
Keyphrases
- cost sensitive
- k nearest neighbor
- traffic accidents
- knn
- bayesian networks
- naive bayes
- support vector machine
- nearest neighbor
- text categorization
- multi class
- cost sensitive learning
- k nearest neighbour
- misclassification costs
- text classification
- cost sensitive classification
- binary classification
- class distribution
- active learning
- countermeasures
- support vector machine svm
- neural network
- probability estimates
- classification algorithm
- nearest neighbour
- training data
- classification accuracy
- traffic flow
- class imbalance
- probability estimation
- feature selection
- machine learning
- text mining
- feature vectors
- shortest path
- class probabilities
- data mining