Breast Cancer becomes the life-threatening disease in the female. Breast Cancer can start in breast and spread to different parts of the body. Early detection and diagnosis of Breast Cancer have been pointed at as the most reliable approach to reducing the number of deaths. There are different machine learning techniques available that are widely used in various domains such as classification and prediction process. In the present study, we employed one of the most popular used machine learning technique K-Nearest Neighbor(KNN) for Wisconsin Diagnostic Breast Cancer dataset in R environment. The dataset has been taken from the UCI Machine Learning Repository containing 32 attributes, 569 instances, and 2 classes. We analyzed classification results of KNN with and without Dimensionality Reduction Techniques. We employed two most important Dimensionality Reduction techniques namely Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) respectively. The objective of the present study is to analyze the performance of KNN technique in Wisconsin Diagnostic Breast Cancer Dataset based on the confusion matrix. The results show that to classify benign or a malignant using KNN with Linear Discriminant Analysis technique outperforms 97.06% accuracy as compared to KNN and KNN with PCA.
