Segmentation of Multivariate Mixed Data via Lossy Data Coding and Compression

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 29; no. 9; pp. 1546 - 1562
• Main Authors: Yi Ma, Derksen, H., Wei Hong, Wright, J.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.09.2007; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Asymptotic properties; Bioinformatics; Coding; Compressing; Computer science; control theory; systems; Computer Simulation; Data Clustering; Data compression; Data Compression - methods; Data Interpretation, Statistical; Data Segmentation; Distortion; Exact sciences and technology; Gaussian distribution; Image coding; Image segmentation; Lossy Coding; Lossy Compression; Maximum likelihood estimation; Microarray Data Clustering; Models, Statistical; Multivariate Analysis; Multivariate Mixed Data; Normal Distribution; Optimization; Parameter estimation; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Phase distortion; Rate Distortion; Segmentation; Segments; Signal processing algorithms; Studies; Cluster analysis; Parameter estimation; Multivariate mixed data; Image processing; Data compression; Degenerate system; DNA chip; data clustering; Modeling; Phase transitions; Outlier; lossy coding; Classification; System identification; Pattern analysis; Deterministic approach; Bioinformatics; microarray data clustering; Mixed distribution; lossy compression; Rate distortion theory; data segmentation; Image segmentation; rate distortion; Gaussian process; Optimal solution; Asymptotic approximation; Artificial intelligence

In this paper, based on ideas from lossy data coding and compression, we present a simple but effective technique for segmenting multivariate mixed data that are drawn from a mixture of Gaussian distributions, which are allowed to be almost degenerate. The goal is to find the optimal segmentation th...