Computer Engineering Department, Yildiz Technical University, Davutpasa Street, 34220, Istanbul, Turkey.
Abstract: In this study, dimension reduction methods were applied to ECG signals and success of such dimension reduction techniques for the classification and segmentation of ECG signals were discussed. As classification method, such as bagging, boosting and random subspace, ensemble methods have been chosen. Because ensemble learning methods are powerful and popular classifiers. Also, segmentation of data through neighbourhood feature extraction (NFE) method were enabled by transiting from high dimensioned space to low dimension space by considering the longitudinal combination of ECG signals. Results classification results of NFE algorithm performed through longitudinal combination and as a newly developed method were compared with classification results of ECG signals obtained through dimension reduction by taking one ECG instance. Results of NFE dimension reduction technique performed by considering the neighbour ECG instances, advantage of effect on segmentation of ECG signals were presented at empirical results section and the success of suggested method was indicated. In addition, ensemble learning methods results were presented comparatively.Results obtained by performed study are promising for the studies to be conducted in further period.
Keywords: ensemble learning, ECG, classification.
Pages: 353 – 363 | Full PDF Paper