Classification of Normal and Murmur Heart Signals by using the CITFA Algorithm and Deep Learning
Classification of Normal and Murmur Heart Signals by using the CITFA Algorithm and Deep Learning
Mohammad Hasan Olyaei Torqabeh1 Hasan Jalali2 Ali Olyaei Torqabeh3
1) Faculty of Electrical Engineering, Sadjad University of Technology, Mashhad, Iran -
2) Faculty of Electrical Engineering, Sadjad University of Technology, Mashhad, Iran -
3) Department of Computer Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran -
Publication :
germanconf.com(germanconf.com/2nd)
Abstract :
This paper discusses a new method called CITFA to classify the heart signal into two normal class and murmur class. So far, several methods have been proposed for classifying the heart signal by scientists. This algorithm is based on deep learning and consists of two steps. Firstly, the heart signal is received and then converted to CITFA and used as training data. In the next step, these data are taught to the deep network. The simulation and definition of the deep network is done using Python software. The database used to train the deep network is selected from the “Classifying Heart Sounds Challenge†series. The simulation results show that the proposed method has a precision of 98.79% of the ability to classify the heart signals.
Keywords :
heart signal
normal
murmur
classification
deep learning
python