Arşiv ve Dokümantasyon Merkezi
Dijital Arşivi

Intelligent arrhythmia classification based on support vector machines

Basit öğe kaydını göster

dc.contributor Graduate Program in Computer Engineering.
dc.contributor.advisor Gürgen, Fikret.
dc.contributor.author Özkaya, Aslı Uyar.
dc.date.accessioned 2023-03-16T10:04:46Z
dc.date.available 2023-03-16T10:04:46Z
dc.date.issued 2006.
dc.identifier.other CMPE 2006 O85
dc.identifier.uri http://digitalarchive.boun.edu.tr/handle/123456789/12434
dc.description.abstract The main objective of this study is to provide automatic recognition of arrhythmiccardiac pathologies from the classification of ECG recordings. ECG is a graphical signalwhich is the result of electrical tension of heart and is the most important biosignal used by cardiologists for diagnostic purposes. The difficulty faced in interpretation of ECG signalsforced researchers to study about automatic detection of cardiac arrhythmia disorders.Using intelligent data analysis techniques, computer programs could easily interpretcomplex ECG signals, predict presence or absence of cardiac arrhythmia and provide realtime analysis and diagnosis. In this study Support Vector Machines (SVM) technique hasbeen applied to ECG dataset for intelligent arrhythmia classification. The dataset used inthis study have been obtained from UCI repository. PCA and ICA methods have been usedfor dimensionality reduction of high dimensional ECG data. Parameter selection is very critical for SVM since its performance is greatly influenced by the model parameters. Theresults of the standard SVM classifier improved by parameter selection, dimensionreduction and a threshold based rejection method to avoid false predictions for ambiguouspatterns. The proposed threshold method provides uncertainty management and could be used for suppressing false alarms. As a comparison, k-Nearest Neighbor and Decision Treealgorithms have been tested on the arrhythmia dataset. According to experimental resultsimproved SVM results shown to outperform competing classification results.
dc.format.extent 30cm.
dc.publisher Thesis (M.S.)-Bogazici University. Institute for Graduate Studies in Science and Engineering, 2006.
dc.relation Includes appendices.
dc.relation Includes appendices.
dc.subject.lcsh Machine learning.
dc.subject.lcsh Electrocardiography.
dc.subject.lcsh Arrhythmia.
dc.title Intelligent arrhythmia classification based on support vector machines
dc.format.pages xi, 63 leaves;


Bu öğenin dosyaları

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

Dijital Arşivde Ara


Göz at

Hesabım