Statistical Mechanics of Complex Systems for Pattern Identification

This paper presents a statistical mechanics concept for identification of behavioral patterns in complex systems based on measurements (e.g., time series data) of macroscopically observable parameters and their operational characteristics. The tools of statistical mechanics, which provide a link between the microscopic (i.e., detailed) and macroscopic (i.e., aggregated) properties of a complex system are used to capture the emerging information and to identify the quasi-stationary evolution of behavioral patterns. The underlying theory is built upon thermodynamic formalism of symbol sequences in the setting of a generalized Ising model (GIM) of lattice-spin systems. In this context, transfer matrix analysis facilitates construction of pattern vectors from observed sequences. The proposed concept is experimentally validated on a richly instrumented laboratory apparatus that is operated under oscillating load for identification of evolving microstructural changes in polycrystalline alloys.

[1]  M. Klesnil,et al.  Fatigue of metallic materials , 1980 .

[2]  D. Ruelle,et al.  Ergodic theory of chaos and strange attractors , 1985 .

[3]  Josef Kittler,et al.  Pattern Recognition Theory and Applications , 1987, NATO ASI Series.

[4]  Albert-László Barabási,et al.  Statistical mechanics of complex networks , 2001, ArXiv.

[5]  Order isomorphism under higher power shift and generic form of renormalization group equations in multimodal maps , 2005 .

[6]  Aravind K. Joshi,et al.  Computational linguistics: A new tool for exploring biopolymer structures and statistical mechanics , 2007 .

[7]  Matthew B Kennel,et al.  Statistically relaxing to generating partitions for observed time-series data. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Shalabh Gupta,et al.  Symbolic time series analysis of ultrasonic data for early detection of fatigue damage , 2007 .

[9]  L. Ahlfors.  Complex Analysis , 1979 .

[10]  Douglas Lind,et al.  An Introduction to Symbolic Dynamics and Coding , 1995 .

[11]  W. Lenz,et al.  Beitrag zum Verständnis der magnetischen Erscheinungen in festen Körpern , 1920 .

[12]  E. Ott.  Chaos in Dynamical Systems: Contents , 1993 .

[13]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[14]  Asok Ray,et al.  Symbolic time series analysis via wavelet-based partitioning , 2006, Signal Process..

[15]  F. Y. Wu.  The Potts model , 1982 .

[16]  R. Pathria.  CHAPTER 9 – STATISTICAL MECHANICS OF INTERACTING SYSTEMS: THE METHOD OF CLUSTER EXPANSIONS , 1996 .

[17]  A. Ray,et al.  Space partitioning via Hilbert transform for symbolic time series analysis , 2008 .

[18]  T. Raghavan,et al.  Nonnegative Matrices and Applications , 1997 .

[19]  Sergey N. Dorogovtsev,et al.  Critical phenomena in complex networks , 2007, ArXiv.

[20]  Liliana López Kleine.  Computational Biology: a Statistical Mechanics Perspective , 2010 .

[21]  Shalabh Gupta,et al.  Real-time fatigue life estimation in mechanical structures , 2007 .

[22]  Asok Ray,et al.  Symbolic dynamic analysis of complex systems for anomaly detection , 2004, Signal Process..

[23]  N. Goldenfeld.  Lectures On Phase Transitions And The Renormalization Group , 1972 .

[24]  David P. Feldman,et al.  Computational mechanics of classical spin systems , 1998 .

[25]  Asok Ray,et al.  Real-Time Health Monitoring of Mechanical Structures , 2003 .

[26]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[27]  Asok Ray,et al.  Symbolic time series analysis of ultrasonic signals for fatigue damage monitoring in polycrystalline alloys , 2006 .

[28]  A. Ray,et al.  Signed real measure of regular languages for discrete event supervisory control , 2005 .

[29]  Arch W. Naylor,et al.  Linear Operator Theory in Engineering and Science , 1971 .

[30]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[31]  David G. Stork,et al.  Pattern Classification , 1973 .

[32]  R. B. Potts.  Some generalized order-disorder transformations , 1952, Mathematical Proceedings of the Cambridge Philosophical Society.

[33]  R. Badii,et al.  Complexity: Hierarchical Structures and Scaling in Physics , 1997 .

[35]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[36]  H. Kantz,et al.  Nonlinear time series analysis , 1997 .

[37]  David Ruelle,et al.  Thermodynamic Formalism: Flows , 2004 .

[38]  Asok Ray,et al.  Pattern identification using lattice spin systems: A thermodynamic formalism , 2007 .

[39]  Paul Martin,et al.  POTTS MODELS AND RELATED PROBLEMS IN STATISTICAL MECHANICS , 1991 .

[40]  Walter Rudin,et al.  Real & Complex Analysis , 1987 .

[41]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[42]  Joseph D. Bryngelson,et al.  Thermodynamics of chaotic systems: An introduction , 1994 .

[43]  M. Marsili,et al.  TOPICAL REVIEW: Statistical mechanics of socio-economic systems with heterogeneous agents , 2006, physics/0606107.

[44]  J. Dobson.  Many‐Neighbored Ising Chain , 1969 .

[45]  A. Bellouquid,et al.  Mathematical Modeling of Complex Biological Systems: A Kinetic Theory Approach , 2006 .

[46]  C. Finney,et al.  A review of symbolic analysis of experimental data , 2003 .

[47]  Claude E. Shannon,et al.  A Mathematical Theory of Communications , 1948 .

[48]  Brian A. Maurer,et al.  Statistical mechanics of complex ecological aggregates , 2005 .