Swati Banerjee

Application of Cross Wavelet Transform for ECG Pattern Analysis and Classification

In this paper, we use cross wavelet transform (XWT) for the analysis and classification of electrocardiogram (ECG) signals. The cross-correlation between two time-domain signals gives a measure of similarity between two waveforms. The application of the continuous wavelet transform to two time series and the cross examination of the two decompositions reveal localized similarities in time and frequency. Application of the XWT to a pair of data yields wavelet cross spectrum (WCS) and wavelet coherence (WCOH). The proposed algorithm analyzes ECG data utilizing XWT and explores the resulting spectral differences. A pathologically varying pattern from the normal pattern in the QT zone of the inferior leads shows the presence of inferior myocardial infarction. A normal beat ensemble is selected as the absolute normal ECG pattern template, and the coherence between various other normal and abnormal subjects is computed. The WCS and WCOH of various ECG patterns show distinguishing characteristics over two specific regions R1 and R2, where R1 is the QRS complex area and R2 is the T-wave region. The Physikalisch-Technische Bundesanstalt diagnostic ECG database is used for evaluation of the methods. A heuristically determined mathematical formula extracts the parameter(s) from the WCS and WCOH. Empirical tests establish that the parameter(s) are relevant for classification of normal and abnormal cardiac patterns. The overall accuracy, sensitivity, and specificity after combining the three leads are obtained as 97.6%, 97.3%, and 98.8%, respectively.

ECG feature extraction and classification of anteroseptal myocardial infarction and normal subjects using discrete wavelet transform

In this paper, a novel methodology, based on discrete wavelet transform (DWT) is developed for extraction of characteristic features from twelve - lead Electrocardiogram recordings. The first step of this method is to denoise the signal using DWT technique. A multiresolution approach along with thresholding is used for the detection of R - Peaks in each cardiac beats. Followed, by this other fiducial points (Q and S) are detected and QRS onset and offset points are identified. Baseline is also detected and heights of R, Q, S waves are calculated. This, algorithm was validated using PTB diagnostic database giving a sensitivity of 99.6% and MITDB Arrhythmia, giving a sensitivity of 99.8%. The QRS vectors are calculated for normal and patients with Anteroseptal MI and a comparative study is presented. Accordingly, it has been found that classification of normal and AS MI is possible by computing the QRS vector. And a simple classification rule is established for this purpose.

A classification approach for myocardial infarction using voltage features extracted from four standard ECG leads

This paper, deals with classification of Anteroseptal Myocardial Infarction and normal subjects. Multiresolution approach based extraction of diagnostic pathological features from V1–V4 chest leads is proposed. Mahalanobish distance based classification is used for classification and generation of discriminant function.The digitized ECG signals is subjected to DWT based denoising before applying feature extraction technique. A multiresolution approach along with an adaptive thresholding is used for the detection of R - peaks. Then Q, S peak, QRS onset and offset points are identified. Finally, the T wave is detected. By detecting the baseline of the ECG data, height of R, Q, S and T wave are calculated. Computed QRS vector and T wave amplitude are used for classification of the two classes. Mahalanobish distance based classification method is used for finding discrimant functions for leads V1–V4 and analysis is made accordingly. For R-peak detection, proposed algorithm yields sensitivity and positive predictivity of 99.8% and 99.7% respectively with MIT BIH Arrhythmia database, 99.84% and 99.98% respectively with PTB diagnostic ECG database. For time plane features, an average coefficient of variation of 3.21 is obtained over 150 leads tested from PTB data, each with 10000 samples. Classification accuracy for this method is 96.4%.

A cross wavelet transform based approach for ECG feature extraction and classification without denoising

Automatic classification of cardiac patterns has become a challenging problem as the morphological and temporal characteristics of the ECG signal shows significant variations for different subjects. Most of the classification methods use explicit time-plane features information like presence of abnormal Q wave, QS complexes, ST segment, R height, QT segment measurement etc. Also ECG signals gets corrupted by various forms of noises. Before any feature extraction technique ECG requires to be preprocessed for removal of artifacts and other high frequency noises. This paper presents an ECG based feature extraction and classification technique which does not require conventionally used time plane features also the features in use are extracted from noisy data. The developed method also extracts parameters which have sufficient distinguishing characteristic to classify normal and abnormal cardiac patterns. The proposed algorithm analyses ECG data through the scope of cross-wavelet transform (XWT) and explores the resulting spectral differences. R peaks are detected for beat segmentation and extraction of any other explicit time plane features is not required. The cross-correlation between two time domain signals gives the measure of similarity between two waveforms. The application of the Continuous Wavelet Transform to two time series and the cross examination of the two decomposition reveals localized similarities in time and frequency. Application of Cross Wavelet Transform to a pair of signals yields wavelet cross spectrum (WCS) and wavelet coherence (WCOH). A heuristically determined mathematical formula extracts parameter(s) from the wavelet cross spectrum and coherence. Empirical tests establish that the two parameter(s) are relevant for classification of normal and abnormal Cardiac patterns. Advantage of this method is: i) It efficiently works in noisy environment ii). Explicit time plane feature extraction is not required and eliminates the use of rule mining procedure thus reducing the computational complexity of the classifier.

ECG beat classification based on discrete wavelet transformation and nearest neighbour classifier

Abstract Myocardial infarction (MI) is a coronary artery disease acquired due to the lack of blood supply in one or more sections of the myocardium, resulting in necrosis in that region. It has different types based on the region of necrosis. In this paper, a statistical approach for classification of Anteroseptal MI (ASMI) is proposed. The first step of the method involves noise elimination and feature extraction from the Electrocardiogram (ECG) signals, using multi-resolution wavelet analysis and thresholding-based techniques. In the next step a classification scheme is developed using the nearest neighbour classification rule (NN rule). Both temporal and amplitude features relevant for automatic ASMI diagnosis are extracted from four chest leads v1–v4. The distance metric for NN classifier is calculated using both Euclidian distance and Mahalanobis distance. A relative comparison between these two techniques reveals that the later is superior to the former, as evident from the classification accuracy. The proposed method is tested and validated using the PTB diagnostic database. Classification accuracy for Mahalanobis distance and Euclidean distance-based NN rule are 95.14% and 81.83%, respectively.

Application of crosswavelet transform and Wavelet Coherence for classification of ECG patterns

This paper presents a method for classification of ECG patterns using Cross Wavelet Transform (XWT) and Wavelet Coherence (WC) techniques. The cross-correlation is the measure of similarity between two waveforms. The application of the Continuous Wavelet Transform to two time series and the cross examination of the two decomposition reveals localized similarities in time and scale. A pathologically varying pattern in QT zone of inferior lead III, shows the presence of Inferior Myocardial Infarction (IMI). In this work classification of normal and IMI is studied. The Cross Wavelet Transform and Wavelet Coherence is used for the cross examination of a single normal and abnormal (IMI) beats. A normal beat template is selected as the absolute normal pattern and the coherence between various other normal and abnormal is computed. A parameter pa, equal to the summation of the coherence values over the QT zone distinguishes normal and abnormal clusters. From this cluster a threshold value is determined, which is used for classification of the subjects. All data for the purpose of analysis is considered from PTB diagnostic ECG database. The classification accuracy and sensitivity is obtained as 90% respectively.

Optimal design approach towards standard electromyography (EMG) controlled hand prosthesis system

Prosthesis is an artificial device that is the substitute of a missing body part like hand and Dexterity is the grace and ease of using the hands. Invention of the myoelectric prosthesis was the most exciting development in prosthetics in recent times. Myoelectric controlled Prosthetic Hand is very significant for handicapped person. This paper deals with an approach to achieve optimum condition of a standard myoelectric hand prosthesis system. The standard transfer function of the system is chosen to achieve the optimized response by increasing the system stability and minimizing the system error. The optimal condition has been gained by using an appropriate PI controller. Computational approach towards stability is involved here with proper and accurate optimization. Particle Swarm Optimization (PSO) technique is also introduced to eliminate the system error further.

An approach for ECG based cardiac abnormality detection through the scope of Cross Wavelet Transform

The analysis of standard clinical electrocardiogram signal is one of the basic routine tests for preliminary screening of cardiac abnormalities. This work deals with classification of normal and IMI (Inferior Myocardial Infaction) and presents a method for analysis of ECG patterns using Cross Wavelet Transform (XWT). The cross-correlation between two time domain signals gives the measure of similarity between two waveforms. The application of the Continuous Wavelet Transform to two time series and the cross examination of the two decomposition reveals localized similarities in time and scale. A pathologically varying pattern in QT zone of inferior lead III, shows the presence of Inferior Myocardial Infarction (IMI). Application of Cross Wavelet Transform to a pair of data gives wavelet cross spectrum and wavelet coherence. A normal beat template is selected as the absolute normal ECG pattern and the coherence between various other normal and abnormal subjects is computed. The Wavelet cross spectrum and Wavelet coherence of various ECG patterns show distinguishing characteristics over two specific regions R1 and R2, where R1 is the QRS complex area and R2 is the T wave region. PTB diagnostic ECG database is used for evaluation of the methods. A heuristically determined mathematical formula extracts parameter(s) from the wavelet cross spectrum and coherence. Empirical tests establish that the parameter is relevant for classification of normal and abnormal Cardiac patterns. The classification accuracy is obtained as 92.5% respectively.