Initializing Partition-Optimization Algorithms

• Published in: IEEE/ACM transactions on computational biology and bioinformatics Vol. 6; no. 1; pp. 144 - 157
• Main Author: Maitra, R.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2009; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; and association rules; Arabidopsis - genetics; Arabidopsis - metabolism; Arrays; Assessments; Bioinformatics; Biology; Chemical Hazard Release - statistics & numerical data; Circadian Rhythm - genetics; classification; Cluster Analysis; Clustering; Clustering algorithms; Computational Biology - methods; Data Interpretation, Statistical; Degradation; Escherichia coli Proteins - genetics; Gene expression; Humans; Industrial Waste - statistics & numerical data; Iterative algorithms; Mercury; Methylmercury Compounds; Minimization methods; Multivariate statistics; Normal Distribution; Oligonucleotide Array Sequence Analysis; Partitioning algorithms; Pattern Recognition, Automated - methods; Proteins; Public healthcare; Singular value decomposition; Staged; Starch - biosynthesis; Starch - genetics; Statistical methods; Testing; Statistical methods; Multivariate statistics; Clustering; classification; and association rules; Singular value decomposition
• ISSN: 1545-5963; 1557-9964; 1557-9964
• DOI: 10.1109/TCBB.2007.70244

Clustering datasets is a challenging problem needed in a wide array of applications. Partition-optimization approaches, such as k-means or expectation-maximization (EM) algorithms, are sub-optimal and find solutions in the vicinity of their initialization. This paper proposes a staged approach to specifying initial values by finding a large number of local modes and then obtaining representatives from the most separated ones. Results on test experiments are excellent. We also provide a detailed comparative assessment of the suggested algorithm with many commonly-used initialization approaches in the literature. Finally, the methodology is applied to two datasets on diurnal microarray gene expressions and industrial releases of mercury.