| Titre : | Breast cancer diagnosis using gwo optimized features selection |
| Auteurs : | Feriel Debakla, Auteur ; Feriel Oumnia Boualem, Auteur ; Mohamed Salem, Directeur de thèse |
| Type de document : | texte manuscrit |
| Editeur : | Université mustapha stambouli de Mascara:Faculté des sciences exactes, 2023 |
| ISBN/ISSN/EAN : | SE02365T |
| Format : | 84P. / couv. ill. / 29cm. |
| Accompagnement : | disque optique numérique (CD-ROM) |
| Langues: | Anglais |
| Résumé : |
In conclusion, our research concentrated on the use of machine learning algorithms, particularly SVM and RND, for the classification of breast cancer. We also looked into how feature selection techniques could be used to improve classification performance. We specifically assessed the GWO algorithm's performance for feature selection in the classification of breast cancer. According to our research, feature selection is an important step in the breast cancer classification. The performance of both the SVM and RND algorithms were improved by the use of GWO for feature selection, which helped to find a subset of important and instructive features. Our research results demonstrated that, in terms of accuracy, recall, and F1-score, the GWO-SVM algorithm beat the GWO-RND method. Compared to other feature selection methods, the use of GWO for feature selection in breast cancer classification has a variety of advantages, including its capacity to handle high-dimensional and non-linear data. The significance of data pre-processing and hyperparameter modification for improving classification performance was also pointed out by our studies. We can argue that our study adds to the body of knowledge on feature selection and machine learning algorithms for breast cancer classification. Our research offers insights into the best algorithm and feature selection method for breast cancer diagnosis, and our results indicate that the GWO-SVM algorithm can be a useful strategy for classifying breast cancer. Our study has the potential to increase the efficacy and precision of breast cancer diagnosis and support medical professionals in making better clinical practice decisions. This work could be enhanced by developing other GWO variants that improve the optimization process by introducing new initialization strategies. Furthermore, we can evaluate our optimization approach on other Machine learning classifier or combine it with the existing breast cancer diagnosis based on medical imaging |
Exemplaires (1)
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| SE02365T | INF951 | Livre audio | Bibliothèque des Sciences Exactes | 7-Mémoires Master | Consultation sur place Exclu du prêt |
Aucun avis, veuillez vous identifier pour ajouter le vôtre !
Accueil
