TY  - JOUR
TI  - A TRANSFER LEARNING APPROACH BY USING 2-D CONVOLUTIONAL NEURAL NETWORK FEATURES TO DETECT UNSEEN ARRHYTHMIA CLASSES
AB  - Arrhythmia is an irregular heartbeat and can be diagnosed via electrocardiography (ECG). Since arrhythmia can be a fatalhealth problem, developing automatic detection and diagnosis systems is vital. Although there are accurate machine learningmodels in the literature to solve this problem, most models assume all arrhythmia types present in training. However, somearrhythmia types are not seen frequently, and there are not enough heartbeat samples from these rare arrhythmia classes to usethem for training a classifier. In this study, the arrhythmia classification problem is defined as an anomaly detection problem.We use ECG signals as inputs of the model and represent them with 2-D images. Then, by using a transfer learning approach,we extract deep image features from a Convolutional Neural Network model (VGG16). In this way, it is aimed to get benefitfrom a pre-trained deep learning model. Then, we train a ν-Support Vector Machines model with only normal heartbeats andpredict if a test sample is normal or arrhythmic. The test performance on rare arrhythmia classes is presented in comparisonwith binary SVM trained with normal and frequent arrhythmia classes. The proposed model outperforms the binaryclassification with 90.42 % accuracy.
AU  - Cimen, Emre
DO  - 10.18038/estubtda.755500
PY  - 2021
JO  - Eskişehir Technical University Journal of Science and and Technology A- Applied Sciences and Engineering
VL  - 22
IS  - 1
SN  - 2667-4211
SP  - 1
EP  - 9
DB  - TRDizin
UR  - http://search/yayin/detay/433795
ER  -