5. Quantum inspired automatic clustering algorithms: A comparative study of Genetic algorithm and Bat algorithm

This article is intendant to present two automatic clustering techniques of image datasets, based on quantum inspired framework with two different metaheuristic algorithms, viz., Genetic Algorithm (GA) and Bat Algorithm (BA). This work provides two novel techniques to automatically find out the optimum clusters present in images and also provides a comparative study between the Quantum Inspired Genetic Algorithm (QIGA) and Quantum Inspired Bat Algorithm (QIBA). A comparison is also presented between these quantum inspired algorithms with their analogous classical counterparts. During the experiment, it was perceived that the quantum inspired techniques beat their classical techniques. The comparison was prepared based on the mean values of the fitness, standard deviation, standard error of the computed fitness of the cluster validity index and the optimal computational time. Finally, the supremacy of the algorithms was verified in terms of the p-value which was computed by t-test (statistical superiority test) and ranking of the proposed procedures was produced by the Friedman test. During the computation, the betterment of the fitness was judge by a well-known cluster validity index, named, DB index. The experiments were carried out on four Berkeley image and two real life grey scale images.