A Two-Dimensional Analysis of Resampling Techniques for Imbalanced Big Data Sets

Authors

  • Angélica Guzmán Ponce Facultad de Ingeniería, Universidad Autónoma del Estado de México. Cerro de Coatepec S/N, Ciudad Universitaria C.P. 50100. Toluca, Estado de México
  • J. Salvador Sanchéz Department of Computer Languages and Systems, Universitat Jaume I, CIF: Q-6250003-H Av. de Vicent Sos Baynat, s/n 12071 Castellón de la Plana, España
  • Rosa M. Valdovinos Rosas Facultad de Ingeniería, Universidad Autónoma del Estado de México. Cerro de Coatepec S/N, Ciudad Universitaria C.P. 50100. Toluca, Estado de México
  • J. Raymundo Marcial Romero Facultad de Ingeniería, Universidad Autónoma del Estado de México. Cerro de Coatepec S/N, Ciudad Universitaria C.P. 50100. Toluca, Estado de México

DOI:

https://doi.org/10.30973/progmat/2019.11.1/6

Keywords:

Big data, Inbalanced data, Over-sampling, under-samplig

Abstract

Big data applications are the central focus of current research in many fields because of the increasing production of huge amounts of data. One important difficulty of data, both in traditional and big data real-life problems, refers to class imbalance where one class is heavily under-represented compared to the other classes. In this paper, we explore the use of some resampling methods for handling the class imbalance in big data sets, analysing processing time and classification accuracy achieved by three classifiers of different nature. The experimental results show that the over-sampling approaches perform better than the under-sampling techniques irrespective of the classifier used, but they lead to much higher classification times. When comparing the over-sampling methods, it is observed that SMOTE outperforms the random over-sampling algorithms; in the case of under-sampling, the random approach is better than the condensed nearest neighbour rule

References

Se-Heon, K., Sun-Kyung, K., and Yong-Hee, L. Vertical beaming of wavelength-scale photonic crystal resonators. Physical Review, 2006, 73. https://doi.org/10.1103/PhysRevB.73.235117

Painter, O., Lee, R. K., Scherer, A., Yariv A., O'Brien, J. D., Dapkus, P. D., Kim, I. TwoDimensional Photonic Band-Gap Defect Mode Laser. Science, 1999, 284. https://doi.org/10.1126/science.284.5421.1819

Painter, O., and Srinivasan, K., Polarization properties of dipolelike defect modes in photonic crystal nanocavities. Optics Letters, 2001, 27, 339-341. https://doi.org/10.1364/OL.27.000339

Johnson, S. G., Fan, Sh., Villeneuve, P. R., Joannopoulos, J. D., and Kolodziejski, L. A. Guided modes in photonic crystal slabs. Phys. Rev. 1999, 60. https://doi.org/10.1103/PhysRevB.60.5751

Sakoda, K. Optical Properties of Photonic Crystals. Edition Springer Berlin Heidelberg New York, Third, 2005.

Joannopoulos, J.D, Meade, R. D., and Winn, J. N. Photonic crystal: modeling the flow of light. Princenton University Press., Princeton, NJ, 1995.

Russell, P. St. J., Atkin, D. M., Birks, T.A. and Roberts, P. J. Bound Modes of TwoDimensional Photonic Crystal Waveguides. Microcavities and Photonic Bandgaps: Physics and Applications. 1996. 1-10. https://doi.org/10.1007/978-94-009-0313-5_18

Cherenkov, P. A. Visible emission of clean liquids by action of ???? radiation, Dokl. Akad. Nauk, 2, 1934.

Afanasiev, G. N., Cherenkov Radiation in a Dispersive Medium, Vavilov-Cherenkov and Synchrotron Radiation, Fundamental Theories if Physics. Kluwer Academin Publishers, 2004.

Joannopoulos, J.D, Meade R. D., and Winn J. N, Photonic crystal: modeling the flow of light. Princenton University Press., Princeton, NJ, 1995.

Sakoda, K., Optical Properties of Photonic Crystals. Edition Springer Berlin Heidelberg New York, Third, 2005.

Garcia de Abajo, F. J., Pattantyus, A. G., Zabala, N., Rivacoba, A., Wolf, M. O., and Echenique, P. M. Cherenkov Effect as a Probe of Photonic Nanostructure. Phys. Rev. Lett. 2003, 91. https://doi.org/10.1103/PhysRevLett.91.143902

Xiang-Wei, Sh., Jin-Hui, Y., Xin-Zhu, S., ChongXiu, Y., Lan, R., Min, X., Ying, H., Chang-Ming, X. and Lan-Tian, H. Highly efficient Cherenkov radiation generation in the irregular point of hollow-core photonic crystal fiber. Chinese Physics B. 2012, 21. https://doi.org/10.1088/1674-1056/21/11/114102

Kremers, Ch., Dmitry, N., Chigrin and Kroha, J. Theory of Cherenkov Radiation in Periodic Dielectric Media: Emission Spectrum. Physical Review A. 2009, 79. https://doi.org/10.1103/PhysRevA.79.013829

Taflove, A., and Hagness, S. C. Computational Electrodynamics: The Finite-Difference TimeDomain Method. Artech House, Boston, Second, 2000.

Se Heon, K. Wavelength Scale Photonic Crystal Cavities Toward High Efficiency Unidirectional Photon Sources. Department of Physics. Korea Advances Institute of Science and Technology. 2006.

Martínez, E. Tesis: Aplicación de las Condiciones de Frontera Absorbentes para Problemas de Propagación de Ondas Electromagnéticas, Universidad Autónoma del Estado de Morelos. Centro de Investigación en Ingeniería y Ciencias Aplicadas, 2013.

Carusotto, I., Artoni M., La Rocca, G. C. and Bassani F., Slow Group Velocity and Cerenkov Radiation, Physical Review Letters. 2001, 87. https://doi.org/10.1103/PhysRevLett.87.064801

Painter O. and Srinivasan K. Polarization properties of dipolelike defect modes in photonic crystal nanocavities. Optics Letters. 2001, 27( 5). https://doi.org/10.1364/OL.27.000339

Jackson, J. D. Classical Electrodynamics. J. Willey Son Ink. New York London Sidney, Third, 1962.

Koshlyakov, N. S., Smirnov, M. M. , Gliner E. B. Differential Equations of Mathematical Physics. North-Holland Publishing Company, Amsterdam, 1964.

Published

2019-02-28

How to Cite

Guzmán Ponce, A., Sanchéz, J. S., Valdovinos Rosas, R. M., & Marcial Romero, J. R. (2019). A Two-Dimensional Analysis of Resampling Techniques for Imbalanced Big Data Sets . Programación Matemática Y Software, 11(1), 48–55. https://doi.org/10.30973/progmat/2019.11.1/6