Bibliothèque centrale Université Mustapha Stambouli de Mascara

Lien vers la notice

Titre :	Medical image segmentation by FCM kernels algorithm and optimization by CHIO metaheuristics
Auteurs :	Assala Belhadj, Auteur ; Rochdi Bachir Bouiadjra, Directeur de thèse
Type de document :	texte manuscrit
Editeur :	Université mustapha stambouli de Mascara:Faculté des sciences exactes, 2022
ISBN/ISSN/EAN :	SE02222T
Format :	67P. / couv. ill. / 29cm.
Accompagnement :	disque optique numérique (CD-ROM)
Langues:	Anglais
Résumé :	Quite recently, CHIO was established as a human-based optimization algorithm that imitates the herd immunity strategy to stop the spread of the COVID-19 disease. In this paper, CHIO is adapted to address KFCM/FCM (CHIO_KFCM/CHIO_FCM) and achieve its objectives efficiently due to its ability in achieving the right balance of exploitation and exploration, thus finding the optimal/near-optimal solution(s). The proposed CHIO-KFCM is examined using a dataset. The main CHIO parameters, including RBr and MaxAge are tuned to find their best values. The results prove CHIO’s robust performance when the values of its control parameters RBr and MaxAge are 0.05 and 100, respectively. These best values are used in the evaluation of the proposed method by comparing its results with the other methods, including CHIO-KFCM_S1, CHIO-KFCM_S2, CHIO-FCM, CHIO-FCM_S1, and CHIO-FCM_S2. These methods are compared in terms to show the best method in optimizing the problem. Generally speaking, the proposed CHIO shows the high performance when addressing KFCM.