Designing of the Artificial Neural Network Model Trained by Using the Different Learning Algorithms to Classify the Electrocardiographic Signals (original) (raw)

PERFORMANCE EVALUATION OF ARTIFICIAL NEURAL NETWORKS FOR CARDIAC ARRHYTHMIA CLASSIFICATION

In this paper an effective and most reliable method for appropriate classification of cardiac arrhythmia using automatic Artificial Neural Network (ANN) has been proposed. The results are encouraging and are found to have produced a very confident and efficient arrhythmia classification, which is easily applicable in diagnostic decision support system. The authors have employed 3 neural network classifiers to classify three types of beats of ECG signal, namely Normal (N), and two abnormal beats Right Bundle Branch Block (RBBB) and Premature Ventricular Contraction (PVC). The classifiers used in this paper are K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC) and Multi-Class Support Vector Machine (MSVM). The performance of the classifiers is evaluated using 5 parametric measures namely Sensitivity (Se), Specificity (Sp), Precision (Pr), Bit Error Rate (BER) and Accuracy (A). Hence MSVM classifier using Crammers method is very effective for proper ECG beat classification.

An Approach of Neural Network For Electrocardiogram Classification

ECG is basically the graphical representation of the electrical activity of cardiac muscles during contraction and release stages. It helps in determination of the cardiac arrhythmias in a well manner. Due to this early detection of arrhythmias can be done properly. In other words we can say that the bio-potentials generated by the cardiac muscles results in an electrical signal called Electro-cardiogram (ECG). It acts as a vital physiological parameter, which is being used exclusively to know the state of the cardiac patients. Feature extraction of ECG plays a vital role in the manual as well as automatic analysis of ECG. In this paper the study of the concept of pattern recognition of ECG is done. It refers to the classification of data patterns and characterizing them into classes of predefined set. The analysis ECG signal falls under the application of pattern recognition. The ECG signal generated waveform gives almost all information about activity of the heart. The ECG signal feature extraction parameters such as spectral entropy, Poincare plot and Lyapunov exponent are used for study in this paper .This paper also includes artificial neural network as a classifier for identifying the abnormalities of heart disease. 1. Introduction Electrocardiography gives information of the electrical activity of the cardiac muscles. Bio-signals which are usually non-stationary signals may occur randomly in the timescale. Hence, for the effective diagnosis, the ECG signal pattern and heart rate variability should be observed over several hours. Because of the volume of the data being enormous due to long time recording, the analysis of it is tedious and also time consuming. Therefore, automatic computer-based examination and classification of cardiac diseases can be very helpful in diagnostic [1]. The frequency range of an ECG signal lies in between 0.05–100 Hz and its magnitude lies in the range of 1–10 mV. It is been characterized by five peaks and valleys labeled as P, Q, R, S and T as shown in Fig 1. The performance of any automatic ECG analyzer depends majorly on the accurate and reliable detection of the QRS segmentation part, as well as T and P waves. The detection of the QRS segmentation part is the crucial task in automatic ECG signal analysis. Because, once the QRS segmentation part has been acknowledged a more comprehensive assessment of ECG signal can be performed that includes the heart rate, the ST segment etc. The normal beats have the P-R interval usually in the range of 0.12-0.2 seconds whereas the QRS interval lies in the range of 0.04-0.12 seconds. The division of ECG is basically in two phases as depolarization of the cardiac muscles and repolarisation of the cardiac muscles. The depolarization phases include the P wave i.e, atrial depolarization and QRS-wave i.e, ventricles depolarization. The repolarisation phases include the T-wave and U-wave i.e, ventricular repolarisation [2-6]. Malfunction in the signaling in the myocardium results in the heart to pump blood less effectively and deteriorates proper conduction process of the heart [4]. Hence, the early detection of arrhythmias is very helpful for living a durable and reliable life as well as improves early detection of arrhythmias. Generally, the standard ECG signals are categorized into three different groups and shown in Figure 1. a. Waves – deviations from the isoelectric line i.e, the baseline voltage. They are named successively: P, Q, R, S, T, U. b. Segments-isoelectric lines time duration between waves. c. Intervals-time duration which include segments and waves.

Cardiac Arrhythmia Prediction Using Improved Multilayer Perceptron Neural Network

TJPRC, 2013

Electrocardiogram (ECG) has much diagnostic information to ensure proper clinical decisions in cardiac arrhythmia. Heart rate variations are signposts of current heart disease or imminent cardiac diseases.This study uses an ECG to determine bundle branch block (BBB), a form of heart block involving conduction delay/failure in the heart’s bundle branch. Machine learning and data mining methods are considered to improve ECG arrhythmia detection accuracy. Usually an automated classification of cardiac arrhythmias procedure is suggested on the basis of linear and non-linear HRV analysis. This paper presents an automated method for classification of cardiac arrhythmic based on ECG rhythm. RR intervals are extracted from ECG data using Symlet, and symmetric uncertainty is used for feature reduction. Extracted RR data is the classification feature with beats being classified through a Improved Neural Network and finally being evaluated through the use of MIT-BIH arrhythmia database.

Classification of ECG-signals using Artificial Neural Networks

An electrocardiogram (ECG) is a bio-electrical signal which is used to record the heart's electrical activity with respect to time. Early and accurate detection is important in detecting heart diseases and choosing appropriate treatment for a patient. ECG signals are used as the parameter for detection of Cardiac diseases and most of the data comes from PhysioDataNet and MIT-BIH database .The pre-processing of ECG signal is performed with help of Wavelet toolbox and also used for feature extraction of ECG signal. The complete project is implemented on MATLAB platform. The performance of the algorithm is evaluated on MIT-BIH Database. This paper presents the application of Probabilistic Neural Networks (PNN) for the classification and detection of Electrocardiogram (ECG).

Identification and Prediction of Heart Disease Based on the Analysis Electrocardiosignals Using a Neural Network

— At the same time image processing as well as the actual calculations combined with a large volume of incoming information in terms of distortion. Artificial Neural Networks has been selected on the basis of networks for research.In this article had heen given application technique of neural network technology.Radial base network was used for the analysis of cardiosignals. Defining of algorithms according to three groups of cardiosignalswere offered: norm signals, bradycardia and tachycardia.

Conception of intelligent classifiers for cardiac arrhythmias detection

Nowadays support systems for diagnosis constitute technical means which are necessary in the medical field, particularly in cardiology. In such field, traditional methods of classification such as the tree approach and the statistical one are inadequate. The introduction of emerging smart technologies such as neural networks is more efficient than other methods. The neural network approach is proved as an effective technique for solving the classification problem. The aim of this paper is to design a neural network classifier, able to reliably identify cases of pathological tachycardia family such as ventricular tachycardia (SVT) and supra ventricular tachycardia (SVT). To achieve this goal, we use several neuronal network algorithms namely the multilayer perceptron network (MLP), the Kohonen Self-Organizing Maps (SOM), the learning vector quantization (LVQ) and the probabilistic neural network (PNN). Test of performances are conducted to verify the reliability margin proposed neura...