ebook img

CALIFORNIA STATE UNIVERSITY, NORTHRIDGE ARRHYTHMIA CLASSIFICATION USING ... PDF

36 Pages·2013·0.66 MB·English
by  
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview CALIFORNIA STATE UNIVERSITY, NORTHRIDGE ARRHYTHMIA CLASSIFICATION USING ...

CALIFORNIA STATE UNIVERSITY, NORTHRIDGE ARRHYTHMIA CLASSIFICATION USING SUPPORT VECTOR MACHINE A graduate project submitted in partial fulfillment of the requirements For the degree of Master of Science in Electrical Engineering By Alexis Pena August 2013 The graduate project of Alexis Pena is approved: __________________________________ _________________________ Benjamin F Mallard Date __________________________________ _________________________ Dr. Ali Amini Date __________________________________ _________________________ Dr. Xiyi Hang, Chair Date California State University, Northridge ii TABLE OF CONTENTS Signature page………………………………………………………………………….…ii Abstract…………………………………………………………………………………...iv Introduction……………………………………………………………………………..…1 Support Vector Machine ………………………………………………………………….8 Feature extraction ……………………...……………….……………………………......12 Numerical Experiment...……………………………………………….………………...14 Discussion.…………………………………………………………………………….....22 Bibliography .…………………………………………………………………………....23 Appendix…..……………………………………………………………………………..24 iii ABSTRACT ARRHYTHMIA CLASSIFICATION USING SUPPORT VECTOR MACHINE By Alexis Pena Master of Science in Electrical Engineering The number one cause of death in the United States is heart disease (1). 67% of heart disease death is brought on by sudden cardiac death. Most of these cases are due to an abnormal electrical triggering of the heart which disrupts blood circulation that lead to immediate death if electrical shock therapy is not applied. Automatic arrhythmia analysis helps speed up the defibrillation therapy to correct the disruption in the electrical system. Implantable defibrillators analyze every heart beat and proper classification is the key to saving thousands of lives every year. In my project, I approached automatic arrhythmia analysis through support vector machine classification (SVMs). I analyze time series ECG heartbeat files from multiple subjects with various arrhythmias, as well as normal heartbeats with no arrhythmias. The heartbeat signals are extracted into individual beats and classified using SVM. The performance of the SVM is evaluate through multiple kernel modification, including higher order dimension analysis and compared to achieve the best classification accuracy rate. Finally, the wavelet transform is taken of the individual signals to maintain enough features while compressing and reducing the sample size to classify each signal with a high accuracy rate. Through my numerical experiments I conclude that SVM provides fast and accurate arrhythmia classification allowing automatic analysis without human oversight. iv INTRODUCTION A healthy human heart pumps about 2,000 gallons of blood through all of our veins and arteries every single day. It carries oxygen and nutrients to every cell in our body. With an average of 100,000 heart beats per day, (2) it is one of the hardest working organs in a human body. The heart beats because of the small electrical current generated by the cardiac conduction system. An electrocardiogram, ECG is a noninvasive procedure that records the electrical activity of the heart over a period of time. The morphology of a heartbeat can provide many detail of a patient. We can determine the cause of symptoms of heart disease, such as dizziness, fainting or shortness of breath. We can check the health of the heart when other conditions are present, such as diabetes, high cholesterol, high blood pressure, or cigarette smoking. And we can check the maintenance of mechanical devices, such as a pacemaker working in combination with other organs throughout the rest of the body. An ideal heart beat has five deflections. Figure 1. QRS complex wave with P and T wave. The ECG will record the electrical activity that comes from depolarization and repolarization of the heart muscle cells when the atria and ventricles contract. The P wave results from atrial depolarization which spreads from the SA node throughout the atria and pumps blood through the open valves from the atria into both ventricles. The time 1 between the P and Q wave is when the signal arrives at the atrioventricular (AV) node and allows the heart’s left and right ventricles to fill with blood. The Q wave results from when the signal arrives at the bundle of His and is divided into left and right bundle branches. The signal leaves the bundle branches through the Purkinje fibers and spreads across the heart’s ventricles causing them to contract which pushes the blood though the pulmonary value into the lungs and through the aortic valve to the rest of the body . The left ventricles contracts first immediately followed by the right, this is marked by the R wave and S wave respectively. After the signal passes, the ventricles relax and await the next signal. The T wave marks the point when the ventricles are relaxing. Any changes from a normal heart beat may indicate a problem with the patient. A patient with atrial premature complexes, APC will have a reduced p wave. In this paper, the following arrhythmia groups have been considered: Normal Sinus Rhythm (NOR), Atrial Premature Contractions (APC), Ventricular premature complexes (VPC), Left Bundle Branch Block (LBBB) and Right Bundle Branch Block (RBBB). An atrial premature contraction (APC) is a heart rhythm disorder that involves a premature firing of the atrium (3), its feels like an extra heartbeat. On an ECG, APC will have a reduce P wave. 2 Figure 2. ECG of a heart beat with APC A ventricular premature complex (VPC) is perceived as a skipped beat, with a sensation feeling of palpitations in the chest. On an ECG, VPC is identifiable when the P wave is closer to the QRS complex. You will also see a longer duration from the T wave to the next QRS complex (4). Figure 3. ECG of a heart beat with VPC 3 In Left bundle branch block, (LBBB) the left ventricle contracts later than the right ventricle. On an ECG, the T wave is deflected opposite compared to a normal sinus rhythm. Figure 4. ECG of a heart beat with LBBB Right bundle branch block, (RBBB) is the result when the right ventricle is not activated by the current charge traveling through the right bundle branch. During this time, the left ventricle is operating normal. On an ECG graph we can see a slurred S wave as well as a widen QRS complex (5). 4 Figure 5. ECG graph showing a heartbeat with RBBB In a normal heart beat we can see the P wave, QRS complex and the S wave. Figure 6. ECG of a normal heart beat. Comparing the 4 arrhythmias to the normal heart beat, we can clearly distinguish the features that give the ECG its unique characteristics for each arrhythmia. A trained cardiologist can diagnose various arrhythmias just by looking at the ECG of a patient. This method is not very practical since the cardiologist cannot monitor the patient at all 5 times. A holter monitor is used to record the heart’s activities for at least 24 hours and later analyzed. In 24 hours, the holter monitor will record about 100,000 heartbeats making it a tedious task to do without computer help. The computational analysis of the ECG signals gives an output with a tally of the unique recorded heart beats. The field of arrhythmia classification is continuously evolving. There are several techniques for providing classification. Shape based matching algorithms using Fourier transform are used for classification from ECG printouts (6). In pattern recognition, k-nearest neighbor and neural networks provide similar approaches to that of SVM. Morphological pattern recognition is the leading method for accurate classification among ECG signals. I propose using the integrated software for support vector classification, libsvm to do multiclass classification with a multi-order polynomial kernel to provide a high accuracy rate of 99.6% in arrhythmia classification. I take advantage of SVM’s simplicity. Through minimal code and lack of computational expenses, I incorporated arrhythmia analysis that could be used in implantable devices to save thousands of lives each year. In this paper I explain the mathematical background and methods of support vector machine and feature extractions to bring an understanding of classification. I explain the method of gaining the ECG signals and how training and testing of the datasets was completed using matlab. In chapter 5, procedure i go into detail of how each heartbeat was separated, grouped and label into a single matrix file. A 10-fold cross validation was performed to achieve the best kernel function for a high accuracy rate within classification. A feature extraction process was performed with wavelet transform in matlab to reduce the signal data while maintaining enough features to perform classification without a drop in accuracy. In the proceeding chapter, I clarify the results of 6

Description:
Dr. Xiyi Hang, Chair. Date. California State University, Northridge .. forming through early detection. My paper brought forth the ease of arrhythmia detection through SVM classification. The feature reduction ability will allow low memory usage to incorporate such SVM algorithms into mobile device
See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.