An algorithm for optimal partitioning of data on an interval

Many signal processing problems can be solved by maximizing the fitness of a segmented model over all possible partitions of the data interval. This letter describes a simple but powerful algorithm that searches the exponentially large space of partitions of N data points in time O(N/sup 2/). The algorithm is guaranteed to find the exact global optimum, automatically determines the model order (the number of segments), has a convenient real-time mode, can be extended to higher dimensional data spaces, and solves a surprising variety of problems in signal detection and characterization, density estimation, cluster analysis, and classification.

[1]  R. Bellman.  On the approximation of curves by line segments using dynamic programming , 1961, CACM.

[2]  R. Bellman.  Dynamic programming. , 1957, Science.

[3]  Alan F. Blackwell,et al.  Programming , 1973, CSC '73.

[4]  I E Auger,et al.  Algorithms for the optimal identification of segment neighborhoods. , 1989, Bulletin of mathematical biology.

[5]  J. Scargle.  Studies in astronomical time series analysis. III - Fourier transforms, autocorrelation functions, and cross-correlation functions of unevenly spaced data , 1989 .

[6]  J. Hartigan,et al.  Product Partition Models for Change Point Problems , 1992 .

[7]  R. Vidal.  Optimal Partition of an Interval — The Discrete Version , 1993 .

[8]  J. Hartigan,et al.  A Bayesian Analysis for Change Point Problems , 1993 .

[9]  S. Kay.  Fundamentals of statistical signal processing: estimation theory , 1993 .

[10]  Athanasios Kehagias,et al.  Time-Series Segmentation Using Predictive Modular Neural Networks , 1997, Neural Computation.

[11]  J. Scargle.  Bayesian Blocks, A New Method to Analyze Structure in Photon Counting Data , 1997, astro-ph/9711233.

[12]  P. Hubert.  Change points in meteorological time series , 1997 .

[13]  C. Alpert,et al.  Splitting an Ordering into a Partition to Minimize Diameter , 1997 .

[14]  Jeffrey D. Scargle.  Studies in Astronomical Time Series Analysis: V. Bayesian Blocks, A New Method to Analyze Structure in , 1998 .

[15]  Oskari Heinonen,et al.  Optimal Multi-Paragraph Text Segmentation by Dynamic Programming , 1998, ACL.

[16]  P. Hubert.  The segmentation procedure as a tool for discrete modeling of hydrometeorological regimes , 2000 .

[17]  Athanasios Kehagias.  Hidden Markov model segmentation of hydrological and enviromental time series , 2002, ArXiv.

[18]  Marc Coram.  Nonparametric Bayesian Classification , 2006, math/0603228.

[19]  S. Kay,et al.  Optimal Segmentation of Signals Based on Dynamic Programming and Its Application to Image Denoising and Edge Detection , 2002 .

[20]  F. Quintana,et al.  Bayesian clustering and product partition models , 2003 .

[21]  Athanasios Kehagias,et al.  Linear Text Segmentation using a Dynamic Programming Algorithm , 2003, EACL.

[22]  V. Petridis,et al.  Text Segmentation by Product Partition Models and Dynamic Programming , 2003 .

[23]  Athanasios Kehagias,et al.  A Dynamic Programming Algorithm for Linear Text Segmentation , 2004, Journal of Intelligent Information Systems.

[24]  Ath. Kehagias,et al.  A hidden Markov model segmentation procedure for hydrological and environmental time series , 2004 .

[25]  R. Lecerf,et al.  Monitoring land use and land cover changes in oceanic and fragmented landscapes with reconstructed MODIS time series , 2005, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005..