Resources Contact Us Home
Method for refining the initial conditions for clustering with applications to small and large database clustering

Image Number 5 for United States Patent #6115708.

As an optimization problem, clustering data (unsupervised learning) is known to be a difficult problem. Most practical approaches use a heuristic, typically gradient-descent, algorithm to search for a solution in the huge space of possible solutions. Such methods are by definition sensitive to starting points. It has been well-known that clustering algorithms are extremely sensitive to initial conditions. Most methods for guessing an initial solution simply make random guesses. In this paper we present a method that takes an initial condition and efficiently produces a refined starting condition. The method is applicable to a wide class of clustering algorithms for discrete and continuous data. In this paper we demonstrate how this method is applied to the popular K-means clustering algorithm and show that refined initial starting points indeed lead to improved solutions. The technique can be used as an initializer for other clustering solutions. The method is based on an efficient technique for estimating the modes of a distribution and runs in time guaranteed to be less than overall clustering time for large data sets. The method is also scalable and hence can be efficiently used on huge databases to refine starting points for scalable clustering algorithms in data mining applications.

  Recently Added Patents
Uplink spatial division multiple access (SDMA) user pairing and scheduling
Neurostimulation system for estimating desired stimulation amplitude for electrode configuration
Method and system for providing coordinated checkpointing to a group of independent computer applications
Image correction using individual manipulation of microlenses in a microlens array
Celestial body running vehicle wheel
User interfaces for facilitating merging and splitting of communication sessions
Level shifter circuit
  Randomly Featured Patents
Implementation of signature analysis for analog and mixed signal circuits
Insert having sinusoidal undulations for ball nose end mill
Polymerizable esters
System and method for adapting video decoding rate
NAND type flash memory and write method of the same
Handy notebook for addresses
Object-holding tray for motor vehicles
Column-parallel sigma-delta analog-to-digital conversion with gain and offset control
Secure cryptographic key exchange and verifiable digital signature