ECG Classification using SVM
Download as PPTX, PDF0 likes929 views
This document outlines a study that used support vector machines (SVM) and artificial neural networks (ANN) to classify electrocardiogram (ECG) data. ECG data from 100 subjects across 4 databases was preprocessed and 12 morphological features were extracted. SVM was trained on 80% of the data and achieved 87% accuracy on the test set. ANN was trained with different numbers of hidden neurons and achieved highest accuracy of 93% with 24 neurons. While results were promising, limitations included inability to work with raw data and need for more accuracy. Future work proposed using more advanced neural networks and identifying most important features.
More Related Content
Similar to ECG Classification using SVM (20)
More from Md Kafiul Islam (20)
ECG Classification using SVM
- 1. 1 Supervised by: Dr. Md. Kafiul Islam, Assistant Professor, EEE, IUB
- 2. OUTLINE Introduction Motivation Electrocardiogram (ECG) Support vector machine (SVM) How SVM works (Linear) How SVM works (non-linear) Artificial Neural Network (ANN) Materials Method Pre-processing Morphological features Result and discussion (SVM) Comparison with related work Result and discussion (ANN) Conclusion Limitation Future work 2
- 3. INTRODUCTION ECG is a simple test to visualize the electrical activity of the heart over a period of time. ECG classification is done by machine learning algorithm. The machine learning algorithm are SVM and ANN 3
- 4. MOTIVATION Number 1 cause of death is cardio vascular diseases Gain knowledge and work with machine learning Create effective and easier classifier 4
- 5. ELECTROCARDIOGRAM (ECG) Another name EKG. Measured using sensors (electrodes). Heart rate, heart rhythm, indication of heart diseases or heart attack etc. 3 main components- 1. P wave 2. QRS complex 3. T wave 5
- 6. ELECTROCARDIOGRAM (ECG) There are mainly 3 types of ECG 1.Resting ECG 2.Stress or exercise ECG 3.Ambulatory ECG 6
- 7. SUPPORT VECTOR MACHINE (SVM) Supervised machine learning algorithm. Commonly use in classification and regression analysis. Other applications - Image classification, Text classification, Biological science etc. 7
- 8. HOW SVM WORKS (LINEAR) Original dataset Getting optimal hyperplane 8
- 9. HOW SVM WORKS (NON-LINEAR) Original dataset Data with separator 9
- 10. HOW SVM WORKS (NON-LINEAR) Transformed data 10
- 11. ARTIFICIAL NEURAL NETWORK (ANN) Important subset of machine learning. It contains input, output and hidden layer. 11
- 12. MATERIALS 100 subjects (50 normal and 50 arrhythmia) Downloaded from physionet website 4 different types of database- 1. Fantasia Database 2. MIT-BIH Normal Sinus Rhythm Database 3. MIT-BIH Arrhythmia Database 4. Sudden Cardiac Death Holter Database 12
- 13. METHOD 13
- 14. PRE-PROCESSING power line interference remover • Notch filter • 50 HZ and harmonics • 2nd order Low pass filter • 80 Hz • 128th order 14
- 15. MORPHOLOGICAL FEATURES Maximum heart rate Average heart rate Minimum heart rate Total number of QRS Number of irregular beats Percentage of irregular beats Number of episodes with consecutive beats Average PR interval Average QRS interval Average QTc interval Number of P absence Number of consecutive P absence 15
- 16. RESULT AND DISCUSSION (SVM) Dataset divided into 2 set Training set (80%) Test set (20%) Accuracy is 87% 16
- 17. COMPARISON WITH RELATED WORK Related Project Database Method Accuracy ECG feature extraction and classification using wavelet transform and support vector machines MIT-BIH arrhythmia 2 different feature extraction methods-The wavelet transform and autoregressive modeling (AR) 99.68% Domain adaptation methods for ECG classification MIT-BIH arrhythmia (divided in 2 set) Two kinds of features: 1) ECG morphology features and 2) ECG wavelet features with QRS width. 97% and 91% ECG beat classification method for ECG printout with Principle components analysis and support vector machines MIT-BIH arrhythmia Discrete wavelet transform (DWT) and principle components analysis (PCA) 99.6367% with LIBSVM This project Fantasia, MIT- BIH normal sinus rhythm, MIT-BIH Morphology Feature extraction method (12 features) 87% 17
- 18. RESULT AND DISCUSSION (ANN) Dataset divided into 3 set- Training set (70%) Validation set (15%) Test set (15%) Accuracy is 93% (number of neurons 24) 18
- 19. RESULT AND DISCUSSION (ANN) Performance changes with the number of hidden neurons For 10 hidden neurons 19
- 20. RESULT AND DISCUSSION (ANN) For 22 hidden neurons 20
- 21. RESULT AND DISCUSSION (ANN) For 30 hidden neurons 21
- 22. CONCLUSION Pre-processing and feature extraction done successfully Successfully train SVM and ANN. The accuracy is good but nor promising 22
- 23. LIMITATION Can not work with raw data. Choosing SVM parameter. Problem with big data. New area. 23
- 24. FUTURE WORK Aim for more accuracy More work with these features. Finding most dominate features to work with. Work with advance neural network (DNN and CNN) 24
- 25. Thank you 25