Improvements to an algorithm for equipartitioning

Modifications to a clustering algorithm in which objects are adaptively partitioned into clusters of equal size are described. The object migration automaton has the advantage of being conceptually simple and easy to implement. Unfortunately, the algorithm may exhibit slow convergence speed and in some cases may not converge at all. The algorithm is modified to provide remedies to these conditions. Through experimental results, the modifications are shown to yield a substantial speedup in convergence (while maintaining 100% accuracy), especially as the number of objects to be partitioned increases