Charles Wessell, North Carolina State University


Applying Simon-Ando Theory to Data Clustering

Abstract: In 1961 Herbert Simon and Albert Ando published a classic paper describing the long-term behavior of dynamical systems that can be described by nearly completely decomposable matrices. This theory assumes that the structure of the system is known and the point of interest is the various states the system passes through on its way to some long-term equilibrium. In this new research the problem is approached from the other direction. We develop a technique for using the evolution of the system to tell us about its initial structure, and we use this technique to develop a new algorithm for data clustering. Results using well-known data sets will show the applicability of this new method.

Mentor: Carl Meyer (North Carolina State University).