One of the most top diseases nowadays is breast cancer that causes death for many women over the world. Breast cancer is a heterogeneous disease defined by molecular types and subtypes. Artificial intelligence has an effect role in detecting and classification the breast cancer. In this work 13 classification method are used like Support Vector Machine, AdaBoost, MLP classifier and others. This work is evaluated using three keys accuracy, cross validation score and execution time. The results detect that Linear SVC Support Vector Machine achieved high accuracy (98.25%) and Random Forest and AdaBoost achieved high cross validation score (97.01%) when compared with other classification methods. Whereas Gaussian NB classifier achieved minimum execution time (0.01 seconds). A data set with 31 feature and 570 records are used for testing the algorithms. 20% of data set will be used in testing and 80% for training. The proposed work achieves high accuracy when compared with the previous works.
shehab, S., & Keshk, A. (2022). Breast Cancer Classification Using Ml Algorithms. Kafrelsheikh Journal of Information Sciences, 3(1), 1-7. doi: 10.21608/kjis.2022.159008.1010
MLA
Sara shehab; Arabi Keshk. "Breast Cancer Classification Using Ml Algorithms". Kafrelsheikh Journal of Information Sciences, 3, 1, 2022, 1-7. doi: 10.21608/kjis.2022.159008.1010
HARVARD
shehab, S., Keshk, A. (2022). 'Breast Cancer Classification Using Ml Algorithms', Kafrelsheikh Journal of Information Sciences, 3(1), pp. 1-7. doi: 10.21608/kjis.2022.159008.1010
VANCOUVER
shehab, S., Keshk, A. Breast Cancer Classification Using Ml Algorithms. Kafrelsheikh Journal of Information Sciences, 2022; 3(1): 1-7. doi: 10.21608/kjis.2022.159008.1010