Pivot-based k-means Algorithm for Numerous-class Data Sets.
Takashi HattoriKazuo AoyamaKazumi SaitoTetsuo IkedaEri KobayashiPublished in: SDM (2016)
Keyphrases
- k means
- data sets
- dynamic programming
- preprocessing
- detection algorithm
- optimization algorithm
- learning algorithm
- input data
- multi class classification
- computational complexity
- cost function
- optimal solution
- lower bound
- high accuracy
- matching algorithm
- significant improvement
- experimental evaluation
- hierarchical clustering
- objective function
- worst case
- feature selection algorithms
- data clustering
- times faster
- decision trees
- similarity measure
- multi class
- computational cost
- np hard
- evolutionary algorithm