In this paper, we present a methodology for classifying normal, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy recordings by analysing single lead ECG signal of short duration.In two layer binary cascaded approach proposed in our methodology, an unlabelled recording is initially classified into one the intermediate classes ('normal+others' 'AF+noisy') at first before actual classification second layer.The Physionet Challenge 2017 dataset containing more than...

This paper presents a novel approach of generating synthetic Photoplethysmogram (PPG) data using physical model the cardiovascular system to improve classifier performance with combination and real data. The is an in-silico cardiac computational model, consisting four-chambered heart electrophysiology, hemodynamic, blood pressure auto-regulation functionality. Starting small number measured PPG data, used synthesize healthy as well time-series pertaining coronary artery disease (CAD) by...

Objective: Atrial fibrillation (AF) and other types of abnormal heart rhythm are related to multiple fatal cardiovascular diseases that affect the quality human life. Hence development an automated robust method can reliably detect AF, in addition non-sinus sinus rhythms, would be a valuable medicine. The present study focuses on developing algorithm for classification short, single-lead electrocardiogram (ECG) recordings into normal, rhythms noisy classes. Approach: proposed framework...

Photoplethysmography (PPG) signals, captured using smart phones are generally noisy in nature. Although they have been successfully used to determine heart rate from frequency domain analysis, further indirect markers like blood pressure (BP) require time analysis for which the signal needs be substantially cleaned. In this paper we propose a methodology clean such PPG signals. Apart filtering, proposed approach reduces baseline drift of near zero. Furthermore it models each cycle as sum 2...

This paper presents a simple method to indirectly estimate the range of certain important electrocardiogram (ECG) parameters using photoplethysmography (PPG). The proposed method, termed as PhotoECG, extracts set time and frequency domain features from fingertip PPG signal. A feature selection algorithm utilizing concept Maximal Information Coefficient (MIC) is presented rank according their relevance create training models for different ECG parameters. yields above 90% accuracy in...

Mobile smartphones have revolutionized the concept of mobile phones as different apps are built to offer various interesting applications in healthcare, gaming, etc. rather than using phone only for voice services. The application developers take advantage onboard sensors, web connectivity and powerful processing units develop such apps. In this paper, we present an approach where direct acoustic coupling technique is employed quickly conveniently convert into high quality digital...

Coronary Artery Disease (CAD) causes significant global mortality. The recent development in artificial intelligence shows the feasibility of early non-invasive screening several life- threatening cardiovascular diseases. However, such approaches have been less prolific diagnosis CAD due to lack clinically known definite bio-marker. In this paper, we propose a novel neural network architecture that effectively combines two non-specific markers, 1) anomalous morphology Electrocardiogram (ECG)...

Analysis of heart sounds is a popular research area for non invasive identification several diseases.This paper proposes set 88 time-frequency features along with five different methodologies classifying normal and abnormal sounds.State the art approach was applied segregating fundamental sounds.Apart from baseline two class classifier, separate classifiers long short were also explored in order to get rid dependency on duration recordings.Finally, three classifier deal noisy data present...

In this paper we propose a feature extraction algorithm for classifying Coronary Artery Disease (CAD) patients from Photoplethysmogram (PPG) signals. Several domain-independent features, representing inherent properties of time series are explored in our study. These combined with Heart Rate Variability (HRV) and other popularly used morphological PPG features. A statistical selection algorithm, based on Maximal Information Coefficient (MIC) is applied MIMIC II dataset ranking choosing the...

Automatic classification of normal and abnormal heart sounds is a popular area research. However, building robust algorithm unaffected by signal quality patient demography challenge. In this paper we have analysed wide list Phonocardiogram (PCG) features in time frequency domain along with morphological statistical to construct discriminative feature set for dataset-agnostic cardiac patients. The large open access database, made available Physionet 2016 challenge was used selection, internal...

Abnormal heart sounds may have diverse frequency characteristics depending upon underlying pathological conditions. Designing a binary classifier for predicting normal and abnormal using supervised learning requires lot of training data, covering different types cardiac abnormalities. In this paper, we propose semi-supervised approach to solve the problem. A convolutional Variational Autoencoder (VAE) structure is defined probability distribution spectrogram properties sounds. The...

Atrial Fibrillation (AF) is a type of abnormal heart rhythm which may lead to stroke or cardiac arrest. In spite numerous research works, developing an automatic mechanism for accurate detection AF remains popular yet unsolved problem. this paper, we propose deep neural network architecture classification using single-lead Electrocardiogram (ECG) signals short duration. We define novel Recurrent Neural Network (RNN) structure, comprising two Long-Short Term Memory (LSTM) networks temporal...

Sleep arousal directly affects the quality of sleep.PhysioNet Challenge 2018 aims to correctly identify designated target (non-apnea arousal) and non-arousal regions from simultaneously recorded multiple biomedical signals.Our contribution lies in a feature extraction algorithm that extracts generic domain-specific features different signals available challenge provided dataset form composite vector.50 most significant are selected based on Minimum Redundancy Maximum Relevance scores for...

In recent days, computer-aided diagnosis systems powered by artificial intelligence and machine learning have become an important part of medicine for assisting the doctors in critical decision making. They are popularly deployed cardiology early automatic detection various life-threatening diseases. However, a algorithm requires large volume training data to create model which is empirical problem medical domain. Generating synthetic patient has emerged as area research solve issue. this...

Coronary Artery Disease (CAD) kills millions of people every year across the world. In this paper, we present a novel idea low cost, non-invasive screening system for early detection CAD patients by fusion phonocardiogram (PCG) and photoplethysmogram (PPG) signals. Two sets time frequency features are extracted from both Support Vector Machine (SVM) is used to classify each subject separately based on feature sets. Finally, outcomes two classifiers fused at decision level, depending upon...

In this paper we propose a novel process flow of low-cost, non-invasive screening system for identifying Coronary Artery Disease (CAD) patients using two-stage classification approach. A statistical rule engine is designed based on patient demography and medical history which applied at the first stage proposed system. The misclassification error reduced second numerical features extracted from multiple cardiovascular signals. Two sets are phonocardiogram (PCG) photoplethysmogram (PPG)...

Robust and accurate detection of vehicle horn along with the rate honking can estimate traffic state a street in an urban area. Participatory sensing using audio users' mobile phones is being used for monitoring environment. In this paper, we propose Spectral Based Mel-Frequency Cepstral Co-efficient (SBMFCC) feature which considers spectral characteristics sounds computation. The proposed approach modifies conventional Mel filter bank structure according to varying nature energy...

This paper presents a demo proposal of standalone smartphone application that can automatically analyse the signal quality PCG, as it is recorded on low-cost smartphone-based digital stethoscope. Features, related to inherent pattern autocorrelated envelope, have been used for classifying and discarding noisy portions from continuous PCG. Our has successfully deployed Nexus 5 tested several clean PCG signals with sensitivity 78.91% specificity 70.83%.

In this paper, a Wide Learning architecture is proposed that attempts to automate the feature engineering portion of machine learning (ML) pipeline. Feature widely considered as most time consuming and expert knowledge demanding any ML task. The recommendation approach tested on 3 healthcare datasets: a) PhysioNet Challenge 2016 dataset phonocardiogram (PCG) signals, b) MIMIC II blood pressure classification photoplethysmogram (PPG) signals c) an emotion PPG signals. While method beats state...

Phonocardiogram (PCG) or auscultation via a stethoscope forms the basis of preliminary medical screening. But PCG recorded in an uncontrolled environment is inherently noisy. In this paper we have derived novel features from spectral domain and autocorrelation waveforms. These are used to identify quality recording accepting only diagnosable recordings for further analysis. proved be robust irrespective variations devices data collection protocols employed ensure consistent quality. A freely...

Wearable cardioverter defibrillator (WCD) is a life saving, wearable, noninvasive therapeutic device that prevents fatal ventricular arrhythmic propagation leads to sudden cardiac death (SCD). WCD are frequently prescribed patients deemed be at high risk but the underlying pathology potentially reversible or those who awaiting an implantable cardioverter-defibrillator. programmed detect appropriate events and generate energy shock capable of depolarizing myocardium thus re-initiating sinus...