All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.

Information Report

Category:
## Health & Lifestyle

Published:

Views: 4 | Pages: 8

Extension: PDF | Download: 0

Share

Description

Condition Monitoring and Analysis for ECG Signal Using Fuzzy Advance Neural Networks (FANN) and Hypertext Preprocessor(PHP) Nalla. Srinivas 1, A. Vinay Babu 2, M. D. Rajak 3 1 Research Scholar,Department

Transcript

Condition Monitoring and Analysis for ECG Signal Using Fuzzy Advance Neural Networks (FANN) and Hypertext Preprocessor(PHP) Nalla. Srinivas 1, A. Vinay Babu 2, M. D. Rajak 3 1 Research Scholar,Department Computer Science, Acharya Nagarjuna University 2 Director of JNTU,Hyderabad 3 Acharya Nagarjuna University,Guntur Abstract- In this paper analysis of Electrocardiogram (ECG) PQRSTU-waveforms and prediction of particular disease infection or state of a patient is done using Fuzzy logic and Artificial Neural Network (FANN), Precise Electrocardiogram (ECG) classification to diagnose patient s condition is essential. For classification of such Difficult-to- Diagnose-Signals,i.e. ECG signal, classification is performed using various pulses, like v1, v2, v3, v4, v5, v6 etc corresponding hidden layer in ANN i.e., P-Wave, PR- Interval, QRS-Interval, ST-Interval, T-Wave etc analysis of each Input pulse used to train the neural network. Output of the neural network gives weight factors of each signal to create a data set. WebECG is designed using php software and implemented with Fourier series to find out ECG signals according to the parameters such as heart rate, amplitudes and durations, frequency. and we use in this work a Neuro-fuzzy approach to identify these abnormal beats. To achieve this objective we have developed a Neuro- Fuzzy Classifier (NFCL). Keywords- Electrocardiogram, Fuzzy logic and Artificial Neural Network, Premature Ventricular contraction, sinus tachycardia, sinus brady cardia, Hypertext Preprocessor I. INTRODUCTION Heart disease has become the most common disease that affects human beings worldwide. Each year millions of people die from heart attacks and an equal number undergo coronary artery bypass surgery or balloon angioplasty for advanced heart disease.early detection and timely treatment can prevent such events. This would improve the quality of life and slow the progression of heart failure [1]. The first step in the diagnosis is to record the ECG of the patient. An ECG record is a non-invasive diagnostic tool used for the assessment of a patient s heart condition [2]. The features of the ECG, when recognized by simple observations, and combined with heart rate, can lead to a fairly accurate and fast diagnosis. ANN has a significant advantage to solve problems that either do not have an algorithmic solution or solution that is too complex. These networks have been applied effectively with in medical domain for clinical diagnosis, image and signal analysis and interpretation of these signals.the conventional (Heart Attack perdition system) has been identified as one of the ANN structures that can accurately perform classification tasks. 474 Neural Network is one of the most used methods of ECG beat classification, Multi-Layer Perception (MLP) based on the Neural Networks has been chosen to be able to classify the ECG signals. they are trained with Supervision, using Back- Propagation which minimize the squared error between the actual outputs of the network and the desired outputs. Neural network structure consists of four layers (an input layer, two hidden layers, and output layer) using Feed-Forward, Backpropagation, the input is mapped onto each node like P,QRS,ST,T Intervals in the hidden layer weight factors of Sinus tachycardia,sinus Bradycardia,Atrial tachycardia and atrial flutter, Atrial fibrillation, Atroiventricular block and output layer is a linear combination of hidden layer outputs multiplied by their weights. II. REVIEW OF PREVIOUS WORK Numerous works in literature related with heart disease diagnosis using fuzzy and artificial intelligence techniques were demonstrated in [1],[2].In their work three classes of ECG signals selected viz, the normal sinus rhythm, malignant ventricular ectopic and atrial fibrillation were selected and the shape of the PQRST waveforms was demonstrated. Different classes of ECG signals were also reported in [3]. Nikon E.mastorakis have developed [4] an Expert system for ECG Analysis that works by hierarchically organizing the knowledge in a context free Environment. They have used Turbo C for analysis and Turbo prolog for diagnosis. Hamiltonp[5] has developed a software for ECG beat detection and classification and made available as an open source system for use by researchers. silipo R and marchesis[6] used neural networks for automatic ECG analysis for the classification of different cardiac abnormalities. The premature ventricular contraction (PVC) and the premature atrial contraction (PAC) are cardiac arrhythmias as shown in fig 1,2,3. which are widely encountered in the cardiologic field they can be detected using electrocardiogram signal parameter. Implemented Neuro-fuzzy approach to identify these abnormal beats. Classifier was also reported in [8],[9]. The electrocardiogram ECG is a physiological signal that represents the mechanical heart contraction and relaxation as shown healthy persons ECG signals in fig 1,2,3 from [10]. If p is upward and QRS is upward and T is Downward RR0 is Normal RR1 is Normal then type is Normal ECG Signal. P wave: is the contraction of the atria. QRS complex: equivalent to a contraction the ventricles. T wave: is the relaxation of ventricles. Fig 4: Structure of heart and various signals Fig1:ECG of a health person Fig 5: The activation cycle of the heart Fig 2: The premature ventricular contraction (PVC) Fig 6: v1, v2, v3, v4, v5, v6 pulses in heart Fig3:The premature atrial contraction(pac) III. HEART AND SIGNALS The heart is divided two right and left part. Each part has two chambers called atrium and ventricle. The heart has four valves as shown in Fig 4,5,6 from [10]. It produced by an electrocardiograph, which records the electrical activity of the heart over time. A. Reading the Interpreting the ECG The ECG signals must be interpreted and examined systematically. A convenient method is as follows Determine the cardiac rate and rhythm. Assess the P-R interval and the width of the QRS complex. Examine the P wave the QRS complex Examine the S-T segment and T wave. B. ECG Signal ECG signal is generated by rhythmic contractions of the heart measured by electrodes.this signal can be effectively used for heart disease diagnosis. The analysis problem can be divided into two parts, the feature extraction and classification. The feature extraction procedure is necessary to detect abnormality of the signal, while the classification procedure is used to distinguish disease type. 475 There are four major ECG intervals RR,QRS,QT,ST,T segments. The heart rate (beats per minute)can be readily computed from the inter beat(r-r) interval by dividing the number of large(0.20s ) time units between consecutive R waves into 300 or the number of small (0.04s) time units between consecutive R waves into 300 or the number of small(0.04s)units into 1500.The PR interval measures the time(normally 120 to 200 ms) between atrial and ventricular depolarization. Which includes the physiologic delay imposed by stimulation of cells in the AV junction area. The QRS interval normally 100ms or less) reflects the duration of ventricular depolarization.the QT interval includes both ventricular depolarization and repolarization times and A rate related QT interval, QTc can be calculated as QT/R-R and normally is =0.44 s. The QRS complex is subdivided into specific deflections or waves if the initial QRS deflection in a given lead is negative it is termed as Q wave[6]. The first positive deflection is termed an R wave, A negative deflection after an R wave is an S wave subsequent positive or negative wave are labeled R and s respectively.lowercase letter(qrs)are used for waves of relatively small amplitude. An entirely negative QRS complex is termed a QS wave.the ECG signal is made up of a group of repetitive PQRST signals. The normal class of PQRSTU is shown in fig 7. Fig 8: ECG Sinus arrhythmia signal B. Atrial Tachycardia And Atrial Flutter Atrial tachycardia and atrial flutter are due to the presence of an ectopic focus in the atrium which beats regularly at a rapid rate.the p waves are abnormal in shape, but the QRS complexes are usually normal as presented in fig 9. Fig 9: ECG Atrial Flutter signal C. Atrial Fibrillation There is no co-ordinate atrial activity (either electrical or mechanical in atrial fibrillation. The ECG (fig.10) illustrates f (fibrillation) waves representing the atrial activity instead of P waves especially in lead V1, The QRS complexes are normal but occur irregularly. Fig 10: ECG Atrial Fibrillation signal. Fig7: Normal PQRST waveform and its intervals. IV. SAMPLE ECG SIGNALS The cardiac impulse arises normally from the sinus node in sinus tachycardia and the ecg is Normal Form.The pulse rate is increases above 100 beats/min (adults).sinus tachycardia may result from emotion, exercise, fever, hyperthyroidism and anemia as shown in fig8-11 reference from[10]. A. Sinus bradycardia The heart rate is less than 60 beats/min. Sinus bradycardia occurs in trained athletes and in patients with increased intracranial pressure,myxoedema and jaundice are presented in fig 8. D. Atrioventricular Block(Heart Block) In first degree atrioventricular block The P-R interval exceeds 0.2 second and all atrial impulses reach the ventricles.when some impulses fail to reach the ventricles but others do reach it, then there is second-degree atrioventricular block. In third degree atrioventricular block(complete)the atria and ventricles beat independently,i.e,they are dissociated the ventricular rate is usually slow,20-40 beats for min, and often erratic and may fail completely ventricular stands stills as presented in fig 11. Fig 11 ECG Atrioventricular Block(Heart Block)Signal V. METHODOLOGY Five classes of ECG signals have been selected for the classification tasks. The normal sinus tachycardia, sinus bradycardia, Atrial tachycardia and a trial flutter, Atrial fibrillation, Atrioventricular Block(heart block). 476 From the web site of physionet the database provides 22 sinus rhythm type,23 atrial fibrillation type,20 Atrioventricular Block.The signals from the five classes are sampled at the rate of 128 samples for second. All signal input to neural network.these feature representations involve one set of PQRST-wave from a series of PQRST-waves in a period of one second. To extract accurate information from each set of ECG data, five sets of PQRST-wave from different locations in one ECG signal input to neural networks. For every ECG data. Five sets of PQRST-wave were extracted using wavelet decomposition technique. This technique would detect the location of maximum P-wave and P-R interval, QRS, S-T segment and T wave. Detection by mat lab provides valuable information found in the interval and amplitude of ECG signals. Input to train the neural network. Output of the neural network gives weight factors of each signal. Each weight factors input to a software program is written in visual basic result to be displays risk factors. Y NN = f ( w i x j ) When x i =input, and w IJ =weight VII. SIMULATON RESULTS The complete set of rules initially input to the system has been checked with matlab finding different intervals like P-Wave, PR-Interval, QRS-Interval, ST-Interval, T- Wave etc as shown in fig13.analysis of each Input pulse is Input to train the neural network. Output of the neural network gives weight factors of each signal to create a data set. Corresponding output-datasets indicates related disease and predict the causes. a Neuro-fuzzy approach to identify these abnormal beats. To achieve this objective we have developed a Neuro-Fuzzy Classifier (NFCL). VI. NETWORK ARCHITECTURE AND TRAINING METHOD An FANN classifier is presented as a diagnostic tool to aid physicians in the classification of heart diseases. For the classification of the cardiac beats A Multi-Layer Feedforward Neural Network (MLFN) used to Analyze the PQRST is referenced to as NN in this paper. NN was constructed using the neural network software packages in Matlab. Fig.8 illustrates the architecture of NN. which included an input layer a hidden layer and an output layer neurons in the input layer act only as buffers for distributing the input signals.input signals are P-Wave, PR-Interval, QRS-Interval, ST-Interval, T-Wave in the hidden layer sums up its input signals xi after weighting them with the strengths of the respective connection w ij form the input layer and computes its output as an activation function f of the sum. Where f is hyperbolic tangent function. As illustrate in fig 12. The back propagation (BP) algorithm was chosen as the training algorithm for Neural Network. Fig 12 Neural Network architecture Sparsly Connected Y NN when y NN = f ( w i1 x 1 + w i2 x 2 + w i3 x w im x m ) Fig 13 Pulse-based diagnosis set-up VIII. NEURO FUZZY SYSTEMS Describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for classification of electrocardiogram (ECG) signals. Decision making was performed in two stages: feature extraction by computation of Lyapunov exponents and classification by the ANFIS trained with the back propagation gradient descent method in combination with the least squares method. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, and atrial fibrillation beat) obtained from the PhysioBank database was classified by four ANFIS classifiers. To improve diagnostic accuracy, the fifth ANFIS classifier (combining ANFIS) was trained using the outputs of the four ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the saliency of features on classification of the ECG signals were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in classifying the ECG signals. 477 A. ANFIS Structure s The ANFIS is a fuzzy inference system based on the model of Takagi-Sugeno and uses four layers. For reasons of representation, we will consider a system with two inputs and two outputs and also consider a model of the 1st order using two rules: If x1 is A1 and x2 is B1 then y1=f1(x1,x2) = a1x1 + b1x2 + c1. If x1 is A2 and x2 is B2 then y2=f2(x1,x2) = a2x1 + b2x2 + c2. The ANFIS architecture that allows representing in fig 14.The basic rules is carried out by an adaptive network that contains fixed nodes.each node square or circular applies a function on its input signals and for a given layer nodes have the same type of function. The output O ik of a node i of the k layer (called node (i, k)) depends on the signals from the layer k-1 and parameters of the node (i, k). O i k =f(o 1 k-1 O k-1 nk-1,a,b,c ) n k-1 is the number of nodes in the (k-1)layer, and a, b, c are the parameters of the (i,k) node. It should be noted that a circular node has no parameters. Layer1: Nodes of this layer all adaptive nodes. This layer performs fuzzification of the inputs; it determines the membership of each input O i 1 =µ Ai (x) Layer2: The nodes of this layer are fixed nodes. They receive the output signals from the previous layer and send their product output W i =µ Ai (X1).µ Bi (X) i=1,2 W i the degree of truth of the rule i. Layer3: Each neuron in this layer calculates the normalized degree of truth of the fuzzy rule Xi=w1/w1+w2 The result out of each node represents the contribution of this rule on the final result. Layer4: The node in this layer are adaptive and perform the consequent of the rules.the output of node I is given by O i 4 =X i.f i =X i (a 1 x 1 +b 1 x 2 +c 1 ) O i 4 =X i.f i =X i (a 1 x 1 +b 1 x 2 +c 2 ) The parameters in this layer(a i,b i,c i ) are to be determined and are referred to as the consequent parameters. Layer5: This layer consists of a two neurons circular makes the sum of signals from the previous layer to give the final output of the network. Layer6: The generalization of the system to a system with multiple inputs done not pose any problem the number of nodes in the first layer is always equal to the total number of linguistic terms defined. X input of i node, Fig.14 ANFIS Architecture. 1 A i : linguistic variable & O i x to Ai degree of membership of The parameters of a node in this layer are those of the corresponding membership function, these are the premise parameters. IX. RESULTS AND DISCUSSIONS In this section features and usage examples of webecg are presented. As illustrate in fig 17,18, the WebECG developed in PHP.It consists of three sections called as A.prediction with fuzzylogic , b.anylisis by fast Fourier transformation, c.ecg Signal prediction using PHP and neural networks. A. prediction with fuzzy logic RRp:the distance between the current R-wave and the previous R-wave. RRs:the distance between the current R-wave and the following R-wave. RRs/RRp:the ratio between the distance RR following the previous one 478 QRS: the duration of the QRS complex The rule base generated by the NFCL is : 1. If (RRP is small) and (RRS / RRP is small) and (QRS is small) then (class C1) 2. If (RRP is small) and (RRS / RRP is small) and (QRS is great) then (class is C1) 3. If (RRP is small) and (RRS / RRP is average) and (QRS is small) then (class C1) 4. If (RRP is small) and (RRS / RRP is average) and (QRS is great) then (class is C1) 5. If (RRP is small) and (RRS / RRP is high) and (QRS is small) then (class is C1) 6. If (RRP is small) and (RRS / RRP is high) and (QRS is great) then (class is C1) 7. If (RRP is average) and (RRS / RRP is small) and (QRS is small) then (class is C2) 8. If (RRP is average) and (RRS / RRP is small) and (QRS is great) then (class is C2) 9. If (RRP is average) and (RRS / RRP is average) and (QRS is small) then (class is C2) 10. If (RRP is average) and (RRS / RRP is average) and (QRS is great) then (class is C2) 11. If (RRP is average) and (RRS / RRP is high) and (QRS is small) then (class is C2) 12.If (RRP is average) and (RRS / RRP is high) and (QRS is great) then (class is C2) B. Modeling of Basic ECG Signal With Fourier Series The second section allows fast Fourier series to find out ECG signals according to the parameters such as heart rate, amplitudes and durations, frequency. ECG signals are periodic; they can be represented by Fourier series. Typical Fourier series is shown in Eq. (1). f(x) represents instantaneous amplitude value of an ECG signal. a 0 is constant representing average amplitude value and x is a variable representing the angular frequency of ECG signal defined as ω =2 /T. T stands for the period of ECG signal. (1) The constants an and bn are called Fourier coefficient. The calculation of a 0, an and b n are given, C. Modeling of Q, QRS and S waves Q, QRS and S waves can be assumed in triangular waveform as shown in Fig. 15 Let the period of signal is equal to T =2l and a is assumed the amplitude of signal, f(x) can be calculated as Eq.(3). Fig.15 QRS Waveform Fig.16 P,T, and U waves f Q, QRS,S(x) can be calculated by Eq. (1). It can be seen below no sinusoidal harmonic since f Q,QRS,S(x) is symmetric and b n =0 (4) (3) Let a 0 and an in Eq. (4) are solved by the help of Eqs. (2) and (3), we get, C. Modeling of P, T and U waves P, T and U waves can be assumed in sinusoidal waveform as shown in Fig. 16, thus, f(x) can be calculated by f P,T,U(x) may be written as Eq. (7). It can be seen below no sinusoidal harmonic since f P,T,U(x) is symmetric and bn =0 (6) (5) (2) (7) 479 Let a0 and an in Eq. (7) are solved by the help of Eqs. (2) and (6), we get, Finally, a clear ECG signal consists of the combination of P, Q, R, S, T and U waves. Thus, it can be calculated as (8) f ECG (x)=f Q (x)+f QRS(X)+f s (x)+f p (X)+f T (x)+f u (x) (9) C. Properties and Usage of Web ECG The third section allows to ECG Signal prediction using neural networks. To shows details

Recommended

Related Search

Condition monitoring and fault diagnosis of eMonitoring and Evaluation for Evidence-Based Heavy metal monitoring and analysisSocial Media Monitoring and AnalysisFault Diagnosis and Condition MonitoringEcg Signal AnalysisGenetic Diversity Analysis for Yield and Othemonitoring and evaluation services for smeMonitoring and Evaluation in Water Supply andMonitoring and Evaluation of Water Supply and

We Need Your Support

Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks

SAVE OUR EARTH

We need your sign to support Project to invent "SMART AND CONTROLLABLE REFLECTIVE BALLOONS" to cover the Sun and Save Our Earth.

More details...Sign Now!

We are very appreciated for your Prompt Action!

x