A hybrid reciprocal model of PCA and K-means with an innovative approach of considering sub-datasets for the improvement of K-means initialization and step-by-step labeling to create clusters with high interpretability.
Seyed Alireza Mousavian AnarakiAbdorrahman HaeriFateme MoslehiPublished in: Pattern Anal. Appl. (2021)
Keyphrases
- k means
- clustering algorithm
- data clustering
- hierarchical clustering
- cluster analysis
- computational model
- probabilistic model
- agglomerative hierarchical clustering
- clustering framework
- clustering approaches
- spectral clustering
- expectation maximization
- probability distribution
- feature extraction
- high level
- prediction accuracy
- clustering method
- mathematical model
- principal component analysis
- high dimensional
- clustering analysis
- unsupervised clustering
- fuzzy clustering algorithm
- image segmentation