An entropy-based initialization method of K-means clustering on the optimal number of clusters.
Kuntal ChowdhuryDebasis ChaudhuriArup Kumar PalPublished in: Neural Comput. Appl. (2021)
Keyphrases
- computational complexity
- dynamic programming
- clustering method
- k means
- high accuracy
- high precision
- experimental evaluation
- computational cost
- clustering algorithm
- cluster centers
- pairwise
- threshold values
- scaling factors
- initial set
- cluster analysis
- synthetic data
- small number
- significant improvement
- model selection
- segmentation method
- prior knowledge
- optimal solution
- objective function
- reinforcement learning
- learning algorithm
- neural network