Data Probes, Vertical Trajectories and Classification: A Tentative Study

David Pearson

doi:10.2478/v10006-007-0010-7

.blurhash-client-img { display: none !important; }

Data Probes, Vertical Trajectories and Classification: A Tentative Study

International Journal of Applied Mathematics and Computer Science

Volume 17 (2007): Issue 1 (March 2007)

By: David Pearson

Open Access

|Apr 2007

Abstract

In this paper we introduce a method of classification based on data probes. Data points are considered as point masses in space and a probe is simply a particle that is launched into the space. As the probe passes by data clusters, its trajectory will be influenced by the point masses. We use this information to help us to find vertical trajectories. These are trajectories in the input space that are mapped onto the same value in the output space and correspond to the data classes.

References

Benton T.C. and Hand D.J. (2002): Segmentation into predictable classes. — IMA J. Manag. Math., Vol. 13, No. 4, pp. 245-259.10.1093/imaman/13.4.245
Search in Google Scholar
Chiu S.L. (1994): Fuzzy model identification based on cluster estimation. — J. Intell. Fuzzy Syst., Vol. 2, No. 3, pp. 267-278.10.3233/IFS-1994-2306
Search in Google Scholar
Hand D.J., Li H.G. and Adams H.G. (2001): Supervised classification with structured class definitions. — Comput. Stat. Data Anal., Vol. 36, No. 2, pp. 209-225.10.1016/S0167-9473(00)00037-2
Search in Google Scholar
Hermann R. (1964): Cartan connections and the equivalence problem for geometric structures, — Contrib. Diff. Eqns., Vol. III, No. 2, pp. 199-248.
Search in Google Scholar
Hermann T. and Ritter H. (1999): Listen to your Data: Model-Based Bonification for Data Analysis, In: Advances in Intelligent Computing and Mulimedia Systems, (M.R. Syed, Edi.), International Institute for Advanced Studies in System Research and Cybernetics, pp. 189-194.
Search in Google Scholar
Isidori A. (1995): Nonlinear Control Systems 3rd Ed. — London: Springer.10.1007/978-1-84628-615-5
Search in Google Scholar
Pearson D.W. (1996): Approximating vertical vector fields for feedforward neural networks. — Appl. Math. Lett., Vol. 9, No. 2, pp. 61-64.10.1016/0893-9659(96)00013-4
Search in Google Scholar
Pearson D.W. and Batton-Hubert M. (2005): Increasing confidence in atmospheric pollution forecasting via vertical vector fields. — Journal Européen des Systèmes Automatisés, Vol. 39, No. 4, pp. 553-569.10.3166/jesa.39.553-569
Search in Google Scholar