Yazar "Iswisi, Amal F. A." seçeneğine göre listele
Listeleniyor 1 - 2 / 2
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Data mining approach based on harris hawks optimization (HHO) algorithm for multiple sclerosis lesions segmentation on brain magnetic resonance images(Altınbaş Üniversitesi / Lisansüstü Eğitim Enstitüsü, 2022) Iswisi, Amal F. A.; Karan, OğuzSegmentation approaches, the majority of which are based on the combination of data mining and machine learning techniques, can be used to extract damaged sections of brain tissues. Clustering algorithms, such as the fuzzy C-means (FCM) cluster algorithm, are effective for segmentation since they are accurate yet not unduly sensitive to visually noise. As a consequence, while the optimum cluster center selection might impact segmentation, the FCM approach is acceptable for detecting Multiple Sclerosis. It's complicated to choose them since it's an NP-hard problem. Harris Hawks optimization (HHO) was utilized to determine the optimal cluster center for both segmentation and FCM methods. Other common methods that aren't as exact as HHO include the genetic algorithm and particle swarm optimization. In the suggested procedure, each membership matrix must either be a hawk or an HHO. To reduce Multiple Sclerosis clustering mistakes, the next step is to construct hawk populations or membership vectors, with the best one chosen to locate the optimal cluster centers. The suggested technique outperformed FCM clustering, as well as other methods like the support vector machine, k-NN algorithm, and hybrid data mining methods, in accuracy testing on a variety of brain MRIs.Öğe Diagnosis of multiple sclerosis disease in brain magnetic resonance ımaging based on the harris hawks optimization algorithm(Hindawi, 2021) Iswisi, Amal F. A.; Rahebi, JavadThe damaged areas of brain tissues can be extracted by using segmentation methods, most of which are based on the integration of machine learning and data mining techniques. An important segmentation method is to utilize clustering techniques, especially the fuzzy C-means (FCM) clustering technique, which is sufficiently accurate and not overly sensitive to imaging noise. Therefore, the FCM technique is appropriate for multiple sclerosis diagnosis, although the optimal selection of cluster centers can affect segmentation. They are difficult to select because this is an NP-hard problem. In this study, the Harris Hawks optimization (HHO) algorithm was used for the optimal selection of cluster centers in segmentation and FCM algorithms. The HHO is more accurate than other conventional algorithms such as the genetic algorithm and particle swarm optimization. In the proposed method, every membership matrix is assumed as a hawk or an HHO member. The next step is to generate a population of hawks or membership matrices, the most optimal of which is selected to find the optimal cluster centers to decrease the multiple sclerosis clustering error. According to the tests conducted on a number of brain MRIs, the proposed method outperformed the FCM clustering and other techniques such as the k-NN algorithm, support vector machine, and hybrid data mining methods in accuracy.