Analysis and Comparison for Innovative Prediction Technique of Breast Cancer Tumor using k Nearest Neighbor Algorithm over Support Vector Machine Algorithm with Improved Accuracy
Aim: The main objective of this study is to compare the efficiency of the k-Nearest Neighbor (KNN) and Support vector machine (SVM) algorithms in detecting breast cancer tumors and to examine their improved accuracy, sensitivity, and precision. Materials and Methods: The data for the research of Innovative breast cancer prediction using machine learning algorithms is taken from UCI Machine Learning Repository. The sample size of the innovative technique involves two groups KNN (N=20) and SVM (N=20) according to clincalc.com by keeping alpha error-threshold at 0.05, confidence interval at 95%, enrollment ratio as 0:1, and power at 80%. The accuracy, sensitivity, and precision are calculated using MATLAB software. Result: Accuracy (%), sensitivity (%), precision (%) are compared using SPSS software using an independent sample t-test tool. The accuracy of the k-Nearest Neighbor is 93.38% (p<0.001) while the accuracy of the Support vector machine is 97.50%. The sensitivity rate is 90.85% (p<0.001) for k-Nearest Neighbor whereas the results of Support vector machine sensitivity is 95.83%. The precision of k-Nearest Neighbor is 98.48% (p<0.001) whereas the results of Support vector machine precision is 100%. Conclusion: The support vector machine algorithm appears to have performed better than the k-Nearest Neighbor with improved accuracy in Innovative breast cancer prediction.
Srinivasulureddy Ch,, Neelam Sanjeev Kumar. Analysis and Comparison for Innovative Prediction Technique of Breast Cancer Tumor using k Nearest Neighbor Algorithm over Support Vector Machine Algorithm with Improved Accuracy. Cardiometry; Issue 25; December 2022; p.878-884; DOI: 10.18137/cardiometry.2022.25.878884; Available from: https://www.cardiometry.net/issues/no25-december-2022/nearest-neighbor-algorithm