FIR rescales features according to dispersion to boost the correlation of validity indices with ground truth in noisy Gaussian mixture data.
An extensive empirical comparison of k-means initialization algorithms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2representative citing papers
citing papers explorer
-
Improving clustering quality evaluation in noisy Gaussian mixtures
FIR rescales features according to dispersion to boost the correlation of validity indices with ground truth in noisy Gaussian mixture data.
- Scalable unsupervised feature selection via weight stability