Browsing by Author "Sarvan, Cagla"

Now showing 1 - 5 of 5

Citation - Scopus: 1
ECG Arrhythmia Detector with Custom Designed Wavelet-Based Convolutional Autoencoder for Unbalanced Data
(Institute of Electrical and Electronics Engineers Inc., 2025) Eravci, Oyku; Sarvan, Cagla; Ozkurt, Nalan
Citation - WoS: 4
Citation - Scopus: 14
ECG beat arrhythmia classification by using 1-d CNN in case of class imbalance
(Institute of Electrical and Electronics Engineers Inc., 2019) Çağla Sarvan; Nalan Ǒzkurt; Sarvan, Cagla; Ozkurt, Nalan
In this study ECG arrhythmia types of non-ectopic (N) ventricular ectopic (V) unknown (Q) supraventricular ectopic (S) and fusion (F) were classified by using the convolutional neural network (CNN) architecture. QRS detection was performed on these ECG arrhythmias that downloaded from MIT-BIH database. An imbalanced number of beats was obtained for 5 different arrhythmia types. In order to reduce the effect of imbalance in statistical performance metrics data mining techniques such as recall of data were applied. It was aimed to increase the positive predictive value (PPV) rates of the classes which consist of a few instances. © 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 2
Citation - Scopus: 2
Feature Selection for ECG Beat Classification using Genetic Algorithms with A Multi-objective Approach
(IEEE, 2018) Cagla Sarvan; Nalan Ozkurt; Sarvan, Cagla; Ozkurt, Nalan
To identify appropriate features in classification studies is a common problem in many areas. In this study a genetic algorithm method with multi-objective approach is proposed for selecting the features that give high performance ratio in classifying cardiac arrhythmia. Discrete Wavelet Transform (DWT) were used for extracting features from Normal right bundle branch block left bundle branch block and paced rhythm recordings of electrocardiography (ECG) signals which were taken from the MIT-BIH cardiac arrhythmia database. Using 13 different wavelet types 208 features were obtained by the DWT method. Among these features a minimum number of feature sets were chosen to provide high performance in classification. Then the classification results were compared with the results of the classical genetic algorithm which aims to improve accuracy.
Citation - Scopus: 1
Implementation of ANN Training Module on Field Programmable Gate Arrays
(IEEE, 2019) Cagla Sarvan; Mustafa Gunduzalp; Gunduzalp, Mustafa; Sarvan, Cagla
This study provides an application-specific integrated circuit (ASIC) diagram of Artificial Neural Networks (ANN) with module design for 32-bit floating point operations on Field Programmable Gate Array (FPGA). It is aimed that ANNs train operations are moved from software to hardware and calculations are made by using IEEE 754 single precision floating point number format. The proposed architecture is designed with combination of Verilog and Very High Speed Integrated Circuits Hardware Description Language (VHDL). Sigmoidal non-linear function was used as the activation function of the train and look-up table (LUT) was created for process efficiency of the designed circuit. Natural parallelisms were used in the calculation of the operations which are implemented on FPGA thus the system operations was accelerated by performing independent operations during the same clock cycle. The results obtained from FPGA were compared with the results obtained from MATLAB R2016b.
Citation - Scopus: 5
Wavelet Feature Extraction for ECG Beat Classification
(IEEE, 2014) Sani Saminu; Nalan Ozkurt; Ibrahim Abdullahi Karaye; Karaye, Ibrahim Abdullahi; Sarvan, Cagla; Ozkurt, Nalan; Saminu, Sani; S Misra; C Ayo; N Omoregbe; B Odusote; A Adewumi
Electrocardiography (ECG) signal is a bioelectrical signal which depicts the cardiac activity of the heart. It is a technique used primarily as a diagnostic tool for various cardiac diseases. ECG provides necessary information on the electrophysiology and changes that may occur in the heart. Due to the increase in mortality rate associated with cardiac diseases worldwide despite recent technological advancement early detection of these diseases is of paramount importance. This paper has proposed a robust ECG feature extraction technique suitable for mobile devices by extracting only 200 samples between R-R intervals as equivalent R-T interval using Pan Tompkins algorithm at preprocessing stage. The discrete wavelet transform (DWT) of R-T interval samples are calculated and the statistical parameters of wavelet coefficients such as mean median standard deviation maximum minimum energy and entropy are used as a time-frequency domain feature. The proposed hybrid technique has been tested by classifying three ECG beats as normal right bundle branch block (Rbbb) and paced beat using the signals from Massachusetts Institute of Technology Beth Israel Hospital (MIT-BIH) arrhythmia database and processed using Matlab 2013 environment. Classification has been performed using neural network backpropagation algorithm because of its simplicity. While equivalent R-T interval features gives average accuracy of 98.22% the proposed hybrid method gives a promising result with average accuracy of 99.84% with reduced classifier computational complexity.