info presentación miembros líneas investigación publicaciones investigación tesis docencia

[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]


Autores
Categoria WoS
Area
Titulo: Texture Classification of Proteins using Support Vector Machines and Bio-Inspired Metaheuristics
Tipo: revista internacional
Fecha: 2014
Revista: Communications in Computer and Information Science
SCIMago SJR: 0.140
Volumen: Communications in Computer and Information Science (CCIS) 452. BIOSTEC 2013
Paginas: 1-14
ISSN: 1865-0929
Editorial: Springer-Verlang Berling Heidelberg
doi: 10.1007/978-3-662-44485-6_9

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.

SABIA
    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial