Two-level clustering approach to training data instance selection: A case study for the steel industry.
Heli KoskimäkiIlmari JuutilainenPerttu LaurinenJuha RöningPublished in: IJCNN (2008)
Keyphrases
- instance selection
- steel industry
- training data
- supervised learning
- classification accuracy
- data reduction
- clustering algorithm
- feature and instance selection
- unsupervised learning
- nearest neighbor
- semi supervised learning
- text classification
- multiple instance learning
- training set
- feature selection
- unlabeled data
- listed companies
- training process
- data sets
- information retrieval
- prior knowledge
- labeled data
- support vector machine
- data points
- multi class
- decision trees
- co training
- neural network
- high dimensional data
- empirical analysis
- high dimensionality
- k nearest neighbor
- semi supervised