Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer

Breast cancer is a considerable problem among the women and causes death around the world. This disease can be detected by distinguishing malignant and benign tumors. Hence, doctors require trustworthy diagnosing process in order to differentiate between malignant and benign tumors. Therefore, the a...

Full description

Bibliographic Details
Main Authors: Obaid, Omar Ibrahim, Mohammed, Mazin Abed, Abd Ghani, Mohd Khanapi, A. Mostafa, Salama, AL-Dhief, Fahad Taha
Format: Article
Published: Science Publishing Corporation 2018
Subjects:
_version_ 1796869150051663872
author Obaid, Omar Ibrahim
Mohammed, Mazin Abed
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
AL-Dhief, Fahad Taha
author_facet Obaid, Omar Ibrahim
Mohammed, Mazin Abed
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
AL-Dhief, Fahad Taha
author_sort Obaid, Omar Ibrahim
collection UTHM
description Breast cancer is a considerable problem among the women and causes death around the world. This disease can be detected by distinguishing malignant and benign tumors. Hence, doctors require trustworthy diagnosing process in order to differentiate between malignant and benign tumors. Therefore, the automation of this process is required to recognize tumors. Numerous research works have tried to apply the algorithms of machine learning for classifying breast cancer and it was proven by many researchers that machine learning algorithms act preferable in the diagnosing process. In this paper, three machine-learning algorithms (Support Vector Machine, K-nearest neighbors, and Decision tree) have been used and the performance of these classifiers has been compared in order to detect which classifier works better in the classification of breast cancer. Furthermore, the dataset of Wisconsin Breast Cancer (Diagnostic) has been used in this study. The main aim of this work is to make comparison among several classifiers and find the best classifier which gives better accuracy. The outcomes of this study have revealed that quadratic support vector machine grants the largest accuracy of (98.1%) with lowest false discovery rates. The experiments of this study have been carried out and managed in Matlab which has a special toolbox for machine learning algorithms.
first_indexed 2024-03-05T21:50:32Z
format Article
id uthm.eprints-5144
institution Universiti Tun Hussein Onn Malaysia
last_indexed 2024-03-05T21:50:32Z
publishDate 2018
publisher Science Publishing Corporation
record_format dspace
spelling uthm.eprints-51442022-01-06T02:35:24Z http://eprints.uthm.edu.my/5144/ Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer Obaid, Omar Ibrahim Mohammed, Mazin Abed Abd Ghani, Mohd Khanapi A. Mostafa, Salama AL-Dhief, Fahad Taha QA76 Computer software RC Internal medicine T Technology (General) T58.6-58.62 Management information systems Breast cancer is a considerable problem among the women and causes death around the world. This disease can be detected by distinguishing malignant and benign tumors. Hence, doctors require trustworthy diagnosing process in order to differentiate between malignant and benign tumors. Therefore, the automation of this process is required to recognize tumors. Numerous research works have tried to apply the algorithms of machine learning for classifying breast cancer and it was proven by many researchers that machine learning algorithms act preferable in the diagnosing process. In this paper, three machine-learning algorithms (Support Vector Machine, K-nearest neighbors, and Decision tree) have been used and the performance of these classifiers has been compared in order to detect which classifier works better in the classification of breast cancer. Furthermore, the dataset of Wisconsin Breast Cancer (Diagnostic) has been used in this study. The main aim of this work is to make comparison among several classifiers and find the best classifier which gives better accuracy. The outcomes of this study have revealed that quadratic support vector machine grants the largest accuracy of (98.1%) with lowest false discovery rates. The experiments of this study have been carried out and managed in Matlab which has a special toolbox for machine learning algorithms. Science Publishing Corporation 2018 Article PeerReviewed Obaid, Omar Ibrahim and Mohammed, Mazin Abed and Abd Ghani, Mohd Khanapi and A. Mostafa, Salama and AL-Dhief, Fahad Taha (2018) Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer. International Journal of Engineering & Technology, 7 (4.36). pp. 160-166. ISSN 2227-524X
spellingShingle QA76 Computer software
RC Internal medicine
T Technology (General)
T58.6-58.62 Management information systems
Obaid, Omar Ibrahim
Mohammed, Mazin Abed
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
AL-Dhief, Fahad Taha
Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title_full Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title_fullStr Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title_full_unstemmed Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title_short Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer
title_sort evaluating the performance of machine learning techniques in the classification of wisconsin breast cancer
topic QA76 Computer software
RC Internal medicine
T Technology (General)
T58.6-58.62 Management information systems
work_keys_str_mv AT obaidomaribrahim evaluatingtheperformanceofmachinelearningtechniquesintheclassificationofwisconsinbreastcancer
AT mohammedmazinabed evaluatingtheperformanceofmachinelearningtechniquesintheclassificationofwisconsinbreastcancer
AT abdghanimohdkhanapi evaluatingtheperformanceofmachinelearningtechniquesintheclassificationofwisconsinbreastcancer
AT amostafasalama evaluatingtheperformanceofmachinelearningtechniquesintheclassificationofwisconsinbreastcancer
AT aldhieffahadtaha evaluatingtheperformanceofmachinelearningtechniquesintheclassificationofwisconsinbreastcancer