Page 56 - 2023-Vol19-Issue2
P. 56

52 |                                                                                                                         Hashim & Yassin

                                             Fig. 9. Performance results of soft voting classifier.

                                                                      TABLE V.
                       SIGNIFICANCE OF THE PROPOSED METHOD COMPARED WITH THE RELATED STUDIES

      Authors    Year  Balanced the dataset  Practical Application                     Feature selection method                                     Model                  Accuracy (%)
       Hazra     2016             NO                    NO                          Pearson correlation coefficient                                  SVM                        98.51
         [6]     2018             NO                    NO                        Univariate feature selection (chi2)                   VotingClassifier(ANN,LR)                98.50
                 2018             NO                    NO          Binary teaching learning-based optimisation (FS-BTLBO)                           SVM                        98.43
     Khuriwal    2019             NO                    NO                       Recursive feature elimination (RFE)                                 SVM                          99
         [7]     2019             NO                    NO                                                                                   Adaboost classifier                98.24
                 2021             NO                    NO                                  Genetic algorithm                                     Soft Voting                   99.00
       Allam     2021             NO                    NO            Correlation analysis and principal component analysis                          SVM                        97.45
         [8]     2021             NO                    NO                                                                   Hierarchical clustering random forest (HCRF)       97.05
                 2022             NO                    NO                           Principal component analysis                                    ANN                         98.3
      Memon                                                                 Variable importance measure method (VIM)                       Soft voting classifier
         [9]     2022            YES                   YES                                                                                     (LR, DT, SVM)                     99.3
                                                                                       Forward feature selection
       Dhahri
        [10]                                                        Pearson correlation and mutual information (PC-MI)

      Ibrahim
        [11]
        HAQ
        [12]

      HUANG
        [13]

      Jumanto
        [14]

Proposed Method

[6] A. Hazra, “Study and analysis of breast cancer cell de-               tion,” wireless communications and mobile computing,
     tection using naive bayes , svm study and analysis of                vol. 2019, pp. 1–19, 2019.
     breast cancer cell detection using naive bayes , svm and
     ensemble algorithms,” Int. J. Comput. Appl., vol. 145,         [10] H. Dhahri, E. Al Maghayreh, A. Mahmood, W. Elkilani,
     no. January 2017, pp. 39–45, 2016.                                   M. Faisal Nagi, et al., “Automated breast cancer diagno-
                                                                          sis based on machine learning algorithms,” Journal of
[7] N. Khuriwal, “Breast cancer diagnosis using adaptive                  healthcare engineering, vol. 2019, 2019.
    voting ensemble machine learning algorithm,” 2018
    IEEMA Eng. Infin. Conf., pp. 1–5, 2018.                         [11] S. Ibrahim and S. Nazir, “Feature selection using cor-
                                                                          relation analysis and principal component analysis for
[8] M. Allam and M. Nandhini, “Optimal feature selection                  accurate breast cancer diagnosis,” J. Imaging, vol. 225,
     using binary teaching learning based optimization algo-              pp. 1–7, 2021.
     rithm,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34,
     no. 2, pp. 329–341, 2022.                                      [12] A. U. Haq, J. P. Li, A. Saboor, J. Khan, S. Wali, S. Ah-
                                                                          mad, A. Ali, G. A. Khan, and W. Zhou, “Detection of
[9] M. H. Memon, J. P. Li, A. U. Haq, M. H. Memon,                        breast cancer through clinical data using supervised and
     and W. Zhou, “Breast cancer detection in the iot health              unsupervised feature selection techniques,” IEEE Access,
     environment using modified recursive feature selec-                  vol. 9, pp. 22090–22105, 2021.
   51   52   53   54   55   56   57   58   59   60   61