Texture classification of proteins using support vector machines and bio-inspired metaheuristics

Carlos Fernandez-Lozano*, Julian Dorado, Jose A. Seoane, Pablo Mesejo, Youssef S.G. Nashed, Stefano Cagnoni

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a novel classification method of two-dimensional polyacrylamide gel electrophoresis images is presented. Such a method uses textural features obtained by means of a feature selection process for whose implementation we compare Genetic Algorithms and Particle Swarm Optimization. Then, the selected features, among which the most decisive and representative ones appear to be those related to the second order co-occurrence matrix, are used as inputs for a Support Vector Machine. The accuracy of the proposed method is around 94 %, a statistically better performance than the classification based on the entire feature set. This classification step can be very useful for discarding over-segmented areas after a protein segmentation or identification process.

Original languageEnglish (US)
Title of host publicationBiomedical Engineering Systems and Technologies - 6th International Joint Conference, BIOSTEC 2013, Revised Selected Papers
EditorsAna Fred, Hugo Gamboa, Pedro L. Fernandes, Jordi Solé-Casals, Mireya Fernández-Chimeno, Sergio Alvarez, Deborah Stacey
PublisherSpringer Verlag
Pages117-130
Number of pages14
ISBN (Electronic)9783662444849
DOIs
StatePublished - 2014
Event6th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2013 - Barcelona, Spain
Duration: Feb 11 2013Feb 14 2013

Publication series

NameCommunications in Computer and Information Science
Volume452
ISSN (Print)1865-0929

Other

Other6th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2013
CountrySpain
CityBarcelona
Period2/11/132/14/13

Keywords

  • Electrophoresis
  • Feature Selection
  • Genetic Algorithm
  • Proteomic Imaging
  • Support
  • Texture Analysis
  • Vector Machines

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Texture classification of proteins using support vector machines and bio-inspired metaheuristics'. Together they form a unique fingerprint.

  • Cite this

    Fernandez-Lozano, C., Dorado, J., Seoane, J. A., Mesejo, P., Nashed, Y. S. G., & Cagnoni, S. (2014). Texture classification of proteins using support vector machines and bio-inspired metaheuristics. In A. Fred, H. Gamboa, P. L. Fernandes, J. Solé-Casals, M. Fernández-Chimeno, S. Alvarez, & D. Stacey (Eds.), Biomedical Engineering Systems and Technologies - 6th International Joint Conference, BIOSTEC 2013, Revised Selected Papers (pp. 117-130). (Communications in Computer and Information Science; Vol. 452). Springer Verlag. https://doi.org/10.1007/978-3-662-44485-6_9