手法を比較

	スペクトラルクラスタリング	DBSCAN	主成分分析
分野	機械学習	機械学習	機械学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2002	1996	2002
提唱者	Ng, A. Y.; Jordan, M. I.; Weiss, Y.	Ester, M., Kriegel, H.-P., Sander, J. & Xu, X.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
種類	Graph-based clustering (spectral method)	Density-based clustering algorithm	Unsupervised dimensionality reduction
原典	Ng, A. Y., Jordan, M. I., & Weiss, Y. (2002). On Spectral Clustering: Analysis and an Algorithm. Advances in Neural Information Processing Systems, 14, 849–856.	Ester, M., Kriegel, H.-P., Sander, J. & Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of the 2nd KDD, 226–231.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
別名	NJW spectral clustering, graph Laplacian clustering, normalized spectral clustering, spectral graph clustering	DBSCAN Kümeleme, density-based clustering, density-based spatial clustering	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
関連	5	3	3
概要	Spectral Clustering is a graph-based unsupervised learning algorithm, formalized by Ng, Jordan, and Weiss in 2002, that maps data points into a low-dimensional eigenspace derived from the similarity graph's Laplacian before applying k-means. This spectral embedding makes it possible to recover clusters of arbitrary shape — rings, crescents, interleaved spirals — that Euclidean distance-based methods consistently fail to separate.	DBSCAN is a density-based clustering algorithm, introduced by Ester, Kriegel, Sander and Xu in 1996, that groups together points lying in dense regions and flags points in sparse regions as noise. It is effective on noisy data and on clusters of irregular, non-spherical shapes.	Principal Component Analysis (PCA) is an unsupervised dimensionality-reduction method — given its modern textbook treatment by Ian Jolliffe (2002) — that compresses high-dimensional data into fewer dimensions while preserving the maximum possible variance. It re-expresses correlated variables as a small set of uncorrelated principal components ordered by how much of the data's variation each one captures.