Parameters Tuning for Support Vector Machine Based on Cuckoo Optimization Algorithm

Support Vector Machine (SVM) is a well-known technique in data classification. The performance of Support Vector Machine (SVM) on a particular dataset is highly dependent on its parameters used for training them. Different approaches like grid search or meta-heuristic are frequently employed to find suitable parameter values for a given dataset. In this work, the tuning parameters are carried out using a recently developed advanced bio-inspired optimization algorithm, called the cuckoo optimization algorithm (COA). The obtained results are compared with previously published results available in the literature. It has been proven that the COA competes robustly with a wide range of optimization algorithms.