Abstract
This is a summary of the author’s PhD thesis, supervised by Prof. Domenico Conforti and defended on 26-02-2010 at the Universitá della Calabria, Cosenza. The thesis is written in Italian and a copy is available from the author upon request. This work deals with the development of a high-level classification framework which combines parameters optimization of a single classifier with classifiers ensemble optimization, through meta-heuristics. Support Vector Machines (SVM) is used for learning while the meta-heuristics adopted and compared are Genetic-Algorithms (GA), Tabu-Search (TS) and Ant Colony Optimization (ACO). Single SVM optimization usually concerns two approaches: searching for optimal set up of a SVM with fixed kernel (Model Selection) or with linear combination of basic kernels (Multiple Kernel Learning), both issues were considered. Meta-heuristics were used in order to avoid time consuming grid-approach for testing several classifiers configurations and some ad-hoc variations to GA were proposed. Finally, different frameworks were developed and then tested on 8 datasets providing reliable solutions.
Similar content being viewed by others
References
Valentini G, Masulli F (2002) Ensemble methods, in Neural Nets. 2486 of lecture notes in computer science, pp 3–20
Scholkopf B, Smola AJ (2002) Learning with kernels. Support Vector Machines, regularization, optimization and beyond. Massachussetts Institute of Technology, USA
Conforti D, Guido R (2009) Kernel based support vector machine via semidefinite programing: application to medical diagnosis. Comput Oper Res, in printing
Huang CL, Wang CJ (2006) A GA-based feature selection and parameters optimization for Support Vector Machines. Experts Syst Appl 31: 231–240
He LM, Yang XB, Kong FS (2006) Support Vector Machines ensemble with optimizing weights by genetic algorithm. In: Proceedings of the fifth international conference on machine learning and cybernetics
Lebrun G, Charrier C, Lezoray O (2008) Tabu search model selection for SVM. Int J Neural Syst 18(1): 19–31
Ji J, Huang Z, Liu C, Liu X, Zhong N (2007) An ant colony optimization algorithm for solving the multidimensional Knapsack problems. In: Proceedigns of IEEE/WIC/ACM international conference on intelligent agent technology, pp 10–16
Xiong W, Wang C (2008) Feature selection: A hybrid approach based on self-adaptive ant colony and support vector machine. In: Proceedings of international conference on computer science and software engineering, pp 751–754
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Candelieri, A. A hyper-solution framework for classification problems via metaheuristic approaches. 4OR-Q J Oper Res 9, 425–428 (2011). https://doi.org/10.1007/s10288-011-0166-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10288-011-0166-8