dc.contributor.author | Mert, Ahmet | |
dc.contributor.author | Kılıç, Niyazi | |
dc.contributor.author | Akan, Aydın | |
dc.date.accessioned | 2021-06-05T19:57:06Z | |
dc.date.available | 2021-06-05T19:57:06Z | |
dc.date.issued | 2011 | |
dc.identifier.isbn | 978-953-7044-12-1 | |
dc.identifier.issn | 1334-2630 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12960/435 | |
dc.description | 0000-0003-4236-3646 | en_US |
dc.description | 0000-0001-8894-5794 | en_US |
dc.description | WOS:000407010900009 | en_US |
dc.description.abstract | Correct and timely diagnosis of diseases is an essential matter in medical field. Limited human capability and limitations decrease the rate of correct diagnosis. Machine learning algorithms such as support vector machine (SVM) can help physicians to diagnose more correctly. In this study, Wisconsin diagnostic breast cancer (WDBC) data set is used to classify tumors as benign and malignant. Independent component analysis (ICA) is used to reduce the dimensionality of WDBC data into two feature vectors. The effect of using two reduced features to classify breast cancer with SVM and polynomial or radial basis function (RBF) kernels are investigated. Performances of these classifiers are evaluated to find out accuracy, sensitivity and specificity. In addition, the receiver operating characteristics (ROC) curves of SVM with these kernels are presented. Results show that SVM with quadratic kernel provides the most accurate diagnosis results (94.40%) and decreases the accuracy and sensitivity values slightly when the dimensionality is reduced into two feature vector computing two independent components. | en_US |
dc.description.sponsorship | EURASIP, IEEE Reg 8, IEEE Croatia Sect, IEEE Signal Proc Soc, Croatia Sect Chapter, IEEE AP MTT Soc, Croatia Sect Joint Chapter, Fdn Croatian Acad Sci & Arts, Minist Sci Educ & Sports Republ Croatia, Minist Sea Transport & Infrastructure Republ Croatia, Univ Zagreb, Fac Elect Engn & Comp, Univ Zadar | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Croatian Society Electronics Marine | en_US |
dc.relation.ispartof | 53Rd International Symposium Elmar-2011 | en_US |
dc.relation.ispartof | 53rd International ELMAR Symposium (ELMAR) -- SEP 14-16, 2011 -- Zadar, CROATIA | en_US |
dc.relation.ispartofseries | ELMAR Proceedings | |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Breast Cancer Classification | en_US |
dc.subject | Support Vector Machines | en_US |
dc.subject | Independent Component Analysis | en_US |
dc.subject | Roc Curve | en_US |
dc.title | Breast Cancer Classification by Using Support Vector Machines with Reduced Dimension | en_US |
dc.type | conferenceObject | en_US |
dc.department | Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü | en_US |
dc.department-temp | [Mert, Ahmet] Piri Reis Univ, Dept Nav Engn, TR-34940 Tuzla Istanbul, Turkey; [Kilic, Niyazi; Akan, Aydin] Istanbul Univ, Dept Elect & Elect Engn, TR-34320 Avcilar, Turkey | en_US |
dc.contributor.institutionauthor | Mert, Ahmet | |
dc.identifier.startpage | 37 | en_US |
dc.identifier.endpage | 40 | en_US |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |