<abstract xmlns="http://www.w3.org/1999/xhtml"><sec><h3>Purpose</h3><p>The aim of this research is to propose a modification of the ANOVA-SVM method that can increase accuracy when detecting benign and malignant breast cancer.</p></sec><sec><h3>Methodology</h3><p>We proposed a new method ANOVA-BOOTSTRAP-SVM. It involves applying the analysis of variance (ANOVA) to support vector machines (SVM) but we use the bootstrap instead of cross validation as a train/test splitting procedure. We have tuned the kernel and the C parameter and tested our algorithm on a set of breast cancer datasets.</p></sec><sec><h3>Findings</h3><p>By using the new method proposed, we succeeded in improving accuracy ranging from 4.5 percentage points to 8 percentage points depending on the dataset.</p></sec><sec><h3>Research limitations</h3><p>The algorithm is sensitive to the type of kernel and value of the optimization parameter C.</p></sec><sec><h3>Practical implications</h3><p>We believe that the ANOVA-BOOTSTRAP-SVM can be used not only to recognize the type of breast cancer but also for broader research in all types of cancer.</p></sec><sec><h3>Originality/value</h3><p>Our findings are important as the algorithm can detect various types of cancer with higher accuracy compared to standard versions of the Support Vector Machines.</p></sec></abstract>

PurposeThe aim of this research is to propose a modification of the ANOVA-SVM method that can increase accuracy when detecting benign and malignant breast cancer.MethodologyWe proposed a new method ANOVA-BOOTSTRAP-SVM. It involves applying the analysis of variance (ANOVA) to support vector machines (SVM) but we use the bootstrap instead of cross validation as a train/test splitting procedure. We have tuned the kernel and the C parameter and tested our algorithm on a set of breast cancer datasets.FindingsBy using the new method proposed, we succeeded in improving accuracy ranging from 4.5 percentage points to 8 percentage points depending on the dataset.Research limitationsThe algorithm is sensitive to the type of kernel and value of the optimization parameter C.Practical implicationsWe believe that the ANOVA-BOOTSTRAP-SVM can be used not only to recognize the type of breast cancer but also for broader research in all types of cancer.Originality/valueOur findings are important as the algorithm can detect various types of cancer with higher accuracy compared to standard versions of the Support Vector Machines.

Detection of Malignant and Benign Breast Cancer Using the ANOVA-BOOTSTRAP-SVM

Department of Statistics and Econometric, Faculty of Economics and Business Administration

Journal of Data and Information Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Detection of Malignant and Benign Breast Cancer Using the ANOVA-BOOTSTRAP-SVM"}

PurposeThe aim of this research is to propose a modification of the ANOVA-SVM method that can increase accuracy when detecting benign and malignant breast...

Detection of Malignant and Benign Breast Cancer Using the ANOVA-BOOTSTRAP-SVM

Article Category: Research Paper

Published Online: May 20, 2020

Page range: 62 - 75

Received: Dec 22, 2019

Accepted: Apr 07, 2020

DOI: https://doi.org/10.2478/jdis-2020-0012

Keywords
Breast cancer detection, ANOVA, Bootstrap, Support vector machines

© 2020 Borislava Petrova Vrigazova, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Detection of Malignant and Benign Breast Cancer Using the ANOVA-BOOTSTRAP-SVM

Article Category: Research Paper

Published Online: May 20, 2020

Page range: 62 - 75

Received: Dec 22, 2019

Accepted: Apr 07, 2020

DOI: https://doi.org/10.2478/jdis-2020-0012

KeywordsBreast cancer detection, ANOVA, Bootstrap, Support vector machines

© 2020 Borislava Petrova Vrigazova, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Keywords
Breast cancer detection, ANOVA, Bootstrap, Support vector machines