Geetika Srivastava

Review: Comparison of QRS detection algorithms

An Electrocardiogram (ECG) is graphical representation of the electrical movement of human heart and used in diagnosis of various heart diseases. The primary function of ECG analysis is correct detection of QRS complex and other ECG characteristics [1]. In this review paper, researchers provide a comparative study between four popular algorithms: namely Window pair algorithm, Dynamic Plosion Index algorithm, KNN algorithm, Slope vector waveform algorithm [2-5] against three assessment criteria 1) Cross Validation, 2) Threshold and 3) Robustness to noise in order to obtain a fast, robust and highly accurate QRS detection algorithm which helps in the development of a more robust clinical instrument by making the front end signal processing more effective [6].

Decomposition of ECG Signals Using Discrete Wavelet Transform for Wolff Parkinson White Syndrome Patients

Todays biggest problem in front of healthcare professionals is to achieve a highest accuracy while classifying ECG signals. This paper explores diverse possibilities of the decomposition using DWT method in order to classify Wolff Parkinson White Syndrome ECG signals. In this work, ECG signals are discretely sampled till 5th resolution level of decomposition tree using DWT with daubechies wavelet of order 4 (db4), which helps in smoothing the feature more appropriate for detecting changes in signals. The MIT-BIH database were used for some experimental results.

Effect of technology scale-down on power reduction strategies

This paper presents limiting effect analysis of voltage scaling on Static Random Access Memory (SRAM) with process technology. The power reduction strategy utilize the property of standby circuit power reduction by reducing voltage swing available to cell by replacing ground and supply nodes by virtual ground and virtual supply nodes respectively. Important precaution to be taken in this method is complete charge removal from virtual nodes before next operation. Focus of this work is on the SRAM cell in 45nm and 32nm technology. Relative reduction in power is evaluated in context of process technology scale down. Cell behavior indicates process technology based design application of virtual supply and ground node technique. Power reduction by virtual ground node gives excellent response in 65nm and higher process technology but it ceases its impact as technology scales down beyond 45nm and 32nm. A detail comparative analysis of these two types of circuit arrangements for standby power reduction of SRAM with changing operating condition has been carried out in 32nm, 45nm.65nm, 90nm and 120nm.

Classification of ECG Signals Related to Paroxysmal Atrial Fibrillation

Paroxysmal atrial fibrillation is a life threatening arrhythmia which leads to sudden cardiac death. Cardiac professionals are always looking to obtain a maximum accuracy in identifying and treating heart disorders. The new method of automatic feature extraction and classification of paroxysmal atrial fibrillation is proposed in this paper. The first step toward classifying paroxysmal disorder is to decompose the ECG signals (healthy and unhealthy) using wavelet transformation techniques. Corresponding to these decomposed levels, the values of ECG signals are computed on the basis of entropy by using the method of cross recurrence quantification analysis. The classification was implemented by probabilistic neural network (PNN) concept. Overall gained accuracy by using PNN classifier is 86.6%. The purpose of this work is to develop a smart method for the proper classification of paroxysmal AF arrhythmias. Long-Term AF Database (Itafdb) and MIT-BIH Fantasia Database (fantasia) have been chosen from Physio Bank ATM for carrying out this work.

Classification of ECG signals using cross-recurrence quantification analysis and probabilistic neural network classifier for ventricular tachycardia patients

Ventricular Tachycardia (VT) is one of the leading causes of sudden cardiac death in the world. Prediction of VT is usually diagnosed by using Electrocardiogram (ECG) and requires expeditious treatment which reduces the mortality rate. The cross recurrence plot (CRP) toolbox is used for computing the recurrence rate values for both (healthy and unhealthy) subjects and artificial neural network (ANN) toolbox in Matlab is used for generating the accurate results. Radial basis function neural network (RBFNN) is used for designing the probabilistic neural network classifier for discriminating the normal from abnormal (VT) signals based on the recurrence rate values. This paper illustrates the cross recurrence quantification analysis (CRQA) of ECG signals followed by the decomposition method using discrete wavelet transform (DWT) for the analysis of cardiac disorders with sensitivity, specificity of 98.5% and 97.6% respectively and overall accuracy achieved is 98.7%. This paper is useful in adopting automated approach for detecting the cardiac arrhythmias efficiently.

Wavelet Transform Based Feature Extraction and Classification of Atrial Fibrillation Arrhythmia

A new approach of automatic classification of atrial fibrillation (AF) arrhythmia is proposed in this paper. Our approach is based on discrete wavelet transform method followed by cross recurrence quantification analysis (CRQA) for extracting the features of experimental ECG signals. The features like laminarity, determinism, entropy, trapping time and transitivity are used for measuring the RQA measures. After that, the classification process has been performed using the concept of probabilistic neural network (PNN) approach. This method is applied to make a differentiation between normal persons and the persons having atrial fibrillation arrhythmia. For testing our approach PHYSIOBANK database of ECG signals have been used. The significance of this classification method has been shown in our Matlab generated results. The outcome of this paper will be very beneficial in treating AF patients. We achieved 100% accuracy by using this method.

Diagnosis of narcolepsy sleep disorder for different stages of sleep using Short Time Frequency analysis of PSD approach applied on EEG signal

Narcolepsy is a sleep disorder in which the subjects brain is chronically unable to regulate sleep-wake cycles. This study aims at identifying narcoleptics from normal individuals. Our approach involves implementation of Short Time Frequency analysis of PSD approach applied on EEG signals, post filtering ROC-LOC channels. In this research article, a comprehensive analysis of EEG signals for S0, S2 and S3 stages of sleep has been performed. The analysis and calculation is performed in all stages of sleep and a comparative database, with Power Spectral Density comparisons between healthy and affected individuals, been prepared. Hence segregation of narcoleptic occurrence events based on delta and alpha segments, of EEG signals, has been successfully performed herein.

Diagnosis of insomnia sleep disorder using short time frequency analysis of PSD approach applied on EEG signal using channel ROC-LOC

Insomnia is a sleep disorder in which the subject encounters problems in sleeping. The aim of this study is to identify insomnia events from normal or effected person using time frequency analysis of PSD approach applied on EEG signals using channel ROC-LOC. In this research article, attributes and waveform of EEG signals of Human being are examined. The aim of this study is to draw the result in the form of signal spectral analysis of the changes in the domain of different stages of sleep. The analysis and calculation is performed in all stages of sleep of PSD of each EEG segment. Results indicate the possibility of recognizing insomnia events based on delta, theta, alpha and beta segments of EEG signals.

Detection of Sleep Disorder Breathing (SDB) Using Short Time Frequency Analysis of PSD Approach Applied on EEG Signal

Sleep disorders may be one of the reasons for concerned sleep. Distressed sleep involves many inabilities such as to fall asleep, to go back to sleep and common waking up during the night. Sleep disorders can be classified under primary and secondary sleep disorders. By the improved recognition of sleep disorders, the variety of treatments now available. In this analysis of several patients of sleep disordered breathing (SDB) and standard people we have calculated an accurate PSD estimate After the analysis of normalized power of standard person a range is defined by which the comparison of normalized power of patients of sleep disordered breathing (SDB) is done. The result of comparison gives the accurate estimate of PSD for sleep disordered breathing. The analysis of patients can be done on a large scale, the more we analyze patients the more accurate results we will get. Working on all channels, with different PSD estimation methods can be very productive.

ECG signal decomposition using PCA and ICA

This paper covers the fundamental concepts involved in Independent Component analysis (ICA) and Principle Component Analysis (PCA) techniques and review its applications. ICA is used Separation of source signal from mixture signals. These mixture of signals may consists of source signals, sensor signals, surface signals etc. ICA consists a higher order statistics which performs its function by making the signal components independent to each other but for the lower order statistics there is also a technique called as PCA (Principle Component Analysis) that performs uncorrelation in signal components. In this Paper, we describe the working of PCA with flowcharts and tried find out principle components of an ECG signal with its Kurtosis value.