Browsing by Subject "ECG"

Now showing 1 - 3 of 3

Open Access
An analog neuromorphic classifier chip for ECG arrhythmia detection
(2019-09) Güngen, Murat Alp
Following Moore's Law, the increase in the availability of more processing power alongside the development of algorithms that can use this power, electrocardiogram (ECG) systems are now becoming a part of our daily lives. The analytical detection of irregularities within the ECG scan, arrhythmias, is tricky due to the variations in the signals that di er from people to people due to physiological reasons. In order to overcome this problem, a two stage machine-learning based time-domain algorithm is first developed and tested on MatLab using datasets from the MIT - BIH Arrhythmia Database. The algorithm begins with the preprocessing stage where seven features are extracted from the input ECG waveform. These features are then moved onto the second classification stage where a perceptron classifies the features as arrhythmic or normal. The algorithm was then converted into an analog CMOS circuit using the XFAB XC06M3 fabrication process on Cadence Virtuoso. Most of the operations in the preprocessing stage were completed using operational transconductance amplifiers (OTAs). For the classifier, the circuit uses analog oating gate metal oxide semiconductor transistors (FGMOS) to store the weights of the perceptron and a winner-take-all current comparator for the activation function. Simulation results show that the circuit works as intended with a power consumption of 290 W.
Open Access
Detection of acute myocardial ischemia based on support vector machines
(IEEE, 2018) Terzi, Merve Begüm; Arıkan, Orhan
In patients with acute myocardial ischemia, chest pains together with changes in ST/T sections of ECG signal occur before the start of myocardial infarction. In this study, in order to diagnose acute myocardial ischemia, a technique which automatically detects changes in ST/T sections of ECG is developed. For this purpose, by using ECG recordings of STAFF III database, ECG features that are critical in the detection of acute myocardial ischemia are identified. By using support vector machines (SVM) operating with linear and radial basis function (RBF) kernels, classifiers that use two and four most discriminating features of ST/T sections of ECG signal are designed. As a result of implementing the developed technique on ECG recordings of STAFF III database, obtained results over a considerable number of patients indicate that the proposed technique provides highly reliable detection of acute myocardial ischemia. Therefore, by using the developed technique, early and accurate diagnosis of acute myocardial ischemia can be performed, which can lead to a significant decrease in morbidity and mortality rates.
Open Access
Koroner arter hastalığının destek vektör makineleri ve Gauss karışım modeli ile tespiti
(IEEE, 2019-04) Terzi, Merve Begüm; Arıkan, Orhan
Bu çalışmada, koroner arter hastalığının (KAH) gürbüz tespitini gerçekleştirmek amacıyla EKG’deki anomalileri güncel sinyal işleme ve makine ögrenmesi yöntemlerini kullanarak tespit eden bir teknik geliştirilmiştir. Bu amaçla, European ST-T veri tabanındaki geniş bantlı kayıtlar kullanılarak, KAH’ın güvenilir tespiti için kritik olan EKG özniteliklerini elde eden özgün bir öznitelik çıkarım tekniği geliştirilmiştir. Elde edilen öznitelikleri kullanarak, KAH’ın gürbüz tespitini gerçekleştiren destek vektör makinelerine (DVM) ve çekirdek fonksiyonlarına dayalı bir gözetimli öğrenme tekniği geliştirilmiştir. İskemik EKG verilerinin eksik olduğu durumlarda, sadece bazal EKG verilerini kullanarak KAH’ın gürbüz tespitini gerçekleştiren Gauss karışım modeline (GKM) dayalı bir gözetimsiz ögrenme tekniği geliştirilmiştir. KAH’ı temsil eden aykırı değerlerin gürbüz tespitini gerçekleştirmek için Neyman-Pearson tipi bir yaklaşım geliştirilmiştir. Önerilen tekniğin European ST-T veri tabanı üzerindeki başarım sonuçları, tekniğin oldukça güvenilir KAH tespiti sağladığını göstermektedir.