Abstract
Within Testor Theory, typical testors are irreducible subsets of attributes preserving the object discernibility ability of the original set of attributes. Computing all typical testors from a dataset has exponential complexity regarding its number of attributes, however there are other properties of a dataset that have some influence on the performance of different algorithms. Previous studies have determined that a significant runtime reduction can be obtained from selecting the appropriate algorithm for a given dataset. In this work, we present an experimental study evaluating the effect of basic matrix dimensionality on the performance of the algorithms for typical testor computation. Our experiments are carried out over synthetic and real–world datasets. Finally, some guidelines obtained from the experiments, for helping to select the best algorithm for a given dataset, are summarised.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ayaquica, I.O.: A new external scale algorithm for typical testor computation. Memories of the II Iberoamerican Worshop on Pattern Recognition, pp. 141–148 (1997). (in Spanish)
Bache, K., Lichman, M.: UCI machine learning repository (2013)
Cheguis, I.A., Yablonskii, S.V.: About testors for electrical outlines. Uspieji Matematicheskij Nauk 4(66), 182–184 (1955). (in Russian)
Chikalov, I., Lozin, V.V., Lozina, I., Moshkov, M., Nguyen, H.S., Slowron, A., Zielosko, B.: Three Approaches to Data Analysis. Springer Science & Business Media, Heidelberg (2013). https://doi.org/10.1007/978-3-642-28667-4
Dmitriev, A., Zhuravlev, I., Krendeliev, F.: About mathematical principles and phenomena classification. Diskretni Analiz 7, 3–15 (1966). (in Russian)
González-Guevara, V.I., Godoy-Calderon, S., Alba-Cabrera, E., Ibarra-Fiallo, J.: A mixed learning strategy for finding typical testors in large datasets. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. LNCS, vol. 9423, pp. 716–723. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25751-8_86
Lazo-Cortés, M., Ruiz-Shulcloper, J., Alba-Cabrera, E.: An overview of the evolution of the concept of testor. Pattern Recogn. 34(4), 753–762 (2001)
Lazo-Cortés, M.S., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Sánchez-Díaz, G.: On the relation between rough set reducts and typical testors. Inf. Sci. 294, 152–163 (2015)
Lias-Rodríguez, A., Pons-Porrata, A.: BR: a new method for computing all typical testors. In: Bayro-Corrochano, E., Eklundh, J.-O. (eds.) CIARP 2009. LNCS, vol. 5856, pp. 433–440. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-10268-4_50
Lias-Rodríguez, A., Sánchez-Díaz, G.: An algorithm for computing typical testors based on elimination of gaps and reduction of columns. Int. J. Pattern Recogn. Artif. Intell. 27(08), 1350022 (2013)
Pawlak, Z.: Classification of objects by means of attributes. Institute of Computer Science, Polish Academy of Sciences [PAS] (1981)
Piza-Davila, I., Sanchez-Diaz, G., Lazo-Cortes, M.S., Rizo-Dominguez, L.: A CUDA-based hill-climbing algorithm to find irreducible testors from a training matrix. Pattern Recogn. Lett. 95, 22–28 (2017). https://doi.org/10.1016/j.patrec.2017.05.026
Rodríguez-Diez, V., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Lazo-Cortés, M.S.: Fast-BR vs. Fast-CT_EXT: an empirical performance study. In: Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera-López, J.A. (eds.) MCPR 2017. LNCS, vol. 10267, pp. 127–136. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59226-8_13
Rodríguez-Diez, V., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Lazo-Cortés, M.S.: A new algorithm for reduct computation based on gap elimination and attribute contribution. Inf. Sci. 435, 111–123 (2018)
Rodríguez-Diez, V., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Lazo-Cortés, M., Feregrino-Uribe, C., Cumplido, R.: A fast hardware software platform for computing irreducible testors. Expert Syst. Appl. 42(24), 9612–9619 (2015)
Ruiz-Shulcloper, J.: Pattern recognition with mixed and incomplete data. Pattern Recogn. Image Anal. 18(4), 563–576 (2008)
Ruiz-Shulcloper, J., Aguila, L., Bravo, A.: BT and TB algorithms for computing all irreducible testors. Rev.cienc. matemáticas 2, 11–18 (1985). (in Spanish)
Ruiz-Shulcloper, J., Alba-Cabrera, E., Lazo-Cortés, M.: Introduction to typical testor theory. Green Series No. 50. CINVESTAV-IPN, México (1995). (in Spanish)
Sanchez-Díaz, G., Lazo-Cortés, M.: CT-EXT: an algorithm for computing typical testor set. In: Rueda, L., Mery, D., Kittler, J. (eds.) CIARP 2007. LNCS, vol. 4756, pp. 506–514. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76725-1_53
Sánchez-Díaz, G., Lazo-Cortés, M.: Modifications to the BT algorithm for reducing its runtime. Rev. cienc. matemáticas 20(2), 129–136 (2002). (in Spanish)
Sanchez-Diaz, G., Piza-Davila, I., Lazo-Cortes, M., Mora-Gonzalez, M., Salinas-Luna, J.: A fast implementation of the CT-EXT algorithm for the testor property. In: Sidorov, G., Hernández Aguirre, A., Reyes García, C.A. (eds.) MICAI 2010. LNCS (LNAI), vol. 6438, pp. 92–103. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16773-7_8
Santiesteban, Y., Pons-Porrata, A.: LEX: a new algorithm for the calculus of typical testors. Rev. cienc. matemáticas 21(1), 85–95 (2003). (in Spanish)
Torres, M.D., Torres, A., Cuellar, F., Torres, M.D.L.L., Ponce De León, E., Pinales, F.: Evolutionary computation in the identification of risk factors. Case of TRALI. Expert Syst. Appl. 41(3), 831–840 (2014)
Acknowledgments
This work was partly supported by National Council of Science and Technology of Mexico under the scholarship grant 399547.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Rodríguez-Diez, V., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Lazo-Cortés, M.S. (2018). The Impact of Basic Matrix Dimension on the Performance of Algorithms for Computing Typical Testors. In: Martínez-Trinidad, J., Carrasco-Ochoa, J., Olvera-López, J., Sarkar, S. (eds) Pattern Recognition. MCPR 2018. Lecture Notes in Computer Science(), vol 10880. Springer, Cham. https://doi.org/10.1007/978-3-319-92198-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-92198-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92197-6
Online ISBN: 978-3-319-92198-3
eBook Packages: Computer ScienceComputer Science (R0)
