ECG waveform rhythmic analysis is very important. In recent trends, analysis processes of ECG waveform applications are available in smart devices. Still, existing methods are not able to accomplish the complete accuracy assessment while classify the multi-channel ECG waveforms. In this paper, proposed analysis of accuracy assessment of the classification of multi-channel ECG waveforms using most popular Soft Computing algorithms. In this research, main focus is on the better rule generation to analyze the multi-channel ECG waveforms. Analysis is mainly done inSoft Computing methods like the Decision Trees with different pruning analysis, Logistic Model Trees with different regression process and Support Vector Machine with Particle Swarm Optimization (SVM-PSO). All these analysis methods are trained and tested with MIT-BIH 12 channel ECG waveforms. Before trained these methods, MSO-FIR filter should be used as data preprocessing for removal of noise from original multi-channel ECG waveforms. MSO technique is used for automatically finding out the cutoff frequency of multichannel ECG waveforms which is used in low-pass filtering process. The classification performance is discussed using mean squared error, member function, classification accuracy, complexity of design, and area under curve on MIT-BIH data. Additionally, this research work is extended for the samples of multi-channel ECG waveforms from the Scope diagnostic center, Hyderabad. Our study assets the best process using the Soft Computing methods for analysis of multi-channel ECG waveforms
IRJET- A Survey on Classification and identification of Arrhythmia using Mach...IRJET Journal
This document summarizes a survey on classifying and identifying arrhythmias using machine learning techniques. The survey examines existing research that uses techniques like support vector machines, neural networks, and deep learning algorithms to classify arrhythmias based on features extracted from electrocardiogram (ECG) signals. The proposed system aims to classify four types of arrhythmias (normal rhythm, left/right bundle branch block, premature ventricular contraction) from the MIT-BIH arrhythmia database with high accuracy by optimizing the combination of preprocessing, feature extraction, and classification methods. Performance will be evaluated based on sensitivity, specificity, and accuracy metrics.
Analysis electrocardiogram signal using ensemble empirical mode decomposition...IAEME Publication
This document discusses techniques for analyzing electrocardiogram (ECG) signals that are noisy and non-stationary. It compares the Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), and Discrete Wavelet Transform (DWT) for denoising ECG signals, finding that EEMD performs best by preserving true waveform features while eliminating noise. It also analyzes normal and abnormal (atrial fibrillation) ECG signals using parametric (periodogram, capon, time-varying autoregressive) and non-parametric (S-transform, smoothed pseudo affine Wigner distributions) time-frequency techniques, determining that the periodogram technique provides the best resolution
Electrocardiogram (ECG) flag is the electrical action of the human heart. The ECG contains imperative data about the general execution of the human heart framework. In this way, exact examination of the ECG flag is extremely critical however difficult undertaking. ECG flag is regularly low adequacy and polluted with various kinds of commotions due to its estimation procedure e.g. control line obstruction, amplifier clamor and standard meander. Benchmark meander is a sort of organic commotion caused by the arbitrary development of patient amid ECG estimation and misshapes the ST fragment of the ECG waveform. In this paper, we present a far reaching near investigation of five generally utilized versatile filtering calculations for the evacuation of low recurrence clamor. We perform broad investigations on the Physionet MIT BIH ECG database and contrast the flag with commotion proportion (SNR), combination rate, and time many-sided quality of these calculations. It is discovered that modified LMS has better execution than others regarding SNR and assembly rate.
IRJET - ECG based Cardiac Arrhythmia Detection using a Deep Neural NetworkIRJET Journal
This paper presents a system for detecting cardiac arrhythmias based on electrocardiogram (ECG) signals using a deep neural network. ECG signals are first transformed into time-frequency spectrograms using short-time Fourier transform. These spectrograms are then used as input for a 2D convolutional neural network to classify five types of arrhythmias: normal beat, normal sinus rhythm, atrial fibrillation, supraventricular tachycardia, and atrial premature beat. The technique is evaluated on the MIT-BIH database and achieves 97% beat classification accuracy and perfect rhythm identification. Compared to other existing methods like SVM, RNN, RF and KNN, the deep learning approach provides better performance for E
IRJET- Arrhythmia Detection using One Dimensional Convolutional Neural NetworkIRJET Journal
1) The document discusses using a 1D convolutional neural network to detect different types of arrhythmias from electrocardiogram (ECG) signals.
2) It proposes a novel wavelet domain multiresolution convolutional neural network approach that avoids complicated heartbeat detection techniques and heavy manual feature engineering.
3) The approach segments ECG signals, applies a discrete cosine transform to select coefficients, and uses a CNN for classification and arrhythmia monitoring. It detects five types of arrhythmias from one-lead ECG signals.
IRJET- Prediction and Classification of Cardiac ArrhythmiaIRJET Journal
This document discusses a study that used an ensemble classifier to predict and classify cardiac arrhythmia. The study used a dataset from the UCI machine learning repository. Feature selection was performed using an extra trees classifier and data preprocessing including normalization and imputing missing values. An ensemble classifier combining logistic regression, SVM, random forest and gradient boosting models was implemented and achieved 90% accuracy in predicting arrhythmia, outperforming other machine learning algorithms. The ensemble approach combined the strengths of different models for improved performance in cardiac arrhythmia classification.
Data Classification Algorithm Using k-Nearest Neighbour Method Applied to ECG...IOSR Journals
This document discusses using a k-nearest neighbor algorithm to classify ECG data. It proposes using additional dimensional features of ECG signals, like the area under the curve calculated using Simpson's rule and a scanline algorithm, along with patient metadata like age, gender, exercise levels, and medical history. A mathematical model is defined to represent the ECG and patient data. The k-nearest neighbor algorithm is then described as a way to classify new ECG data based on its similarity to labeled training data, using Euclidean distance to find the closest k neighbors. This approach aims to improve ECG analysis by considering more than just the ECG signal.
Classification and Detection of ECG-signals using Artificial Neural NetworksGaurav upadhyay
An electrocardiogram (ECG) is a bio-electrical signal which is used to record the heart's electrical activity with respect to time. Early and accurate detection is important in detecting heart diseases and choosing appropriate treatment for a patient. ECG signals are used as the parameter for detection of Cardiac diseases and most of the data comes from PhysioDataNet and MIT-BIH database .The pre-processing of ECG signal is performed with help of Wavelet toolbox and also used for feature extraction of ECG signal. The complete project is implemented on MATLAB platform. The performance of the algorithm is evaluated on MIT–BIH Database. This paper presents the application of Probabilistic Neural Networks (PNN) for the classification and detection of Electrocardiogram (ECG).
IRJET- A Survey on Classification and identification of Arrhythmia using Mach...IRJET Journal
This document summarizes a survey on classifying and identifying arrhythmias using machine learning techniques. The survey examines existing research that uses techniques like support vector machines, neural networks, and deep learning algorithms to classify arrhythmias based on features extracted from electrocardiogram (ECG) signals. The proposed system aims to classify four types of arrhythmias (normal rhythm, left/right bundle branch block, premature ventricular contraction) from the MIT-BIH arrhythmia database with high accuracy by optimizing the combination of preprocessing, feature extraction, and classification methods. Performance will be evaluated based on sensitivity, specificity, and accuracy metrics.
Analysis electrocardiogram signal using ensemble empirical mode decomposition...IAEME Publication
This document discusses techniques for analyzing electrocardiogram (ECG) signals that are noisy and non-stationary. It compares the Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), and Discrete Wavelet Transform (DWT) for denoising ECG signals, finding that EEMD performs best by preserving true waveform features while eliminating noise. It also analyzes normal and abnormal (atrial fibrillation) ECG signals using parametric (periodogram, capon, time-varying autoregressive) and non-parametric (S-transform, smoothed pseudo affine Wigner distributions) time-frequency techniques, determining that the periodogram technique provides the best resolution
Electrocardiogram (ECG) flag is the electrical action of the human heart. The ECG contains imperative data about the general execution of the human heart framework. In this way, exact examination of the ECG flag is extremely critical however difficult undertaking. ECG flag is regularly low adequacy and polluted with various kinds of commotions due to its estimation procedure e.g. control line obstruction, amplifier clamor and standard meander. Benchmark meander is a sort of organic commotion caused by the arbitrary development of patient amid ECG estimation and misshapes the ST fragment of the ECG waveform. In this paper, we present a far reaching near investigation of five generally utilized versatile filtering calculations for the evacuation of low recurrence clamor. We perform broad investigations on the Physionet MIT BIH ECG database and contrast the flag with commotion proportion (SNR), combination rate, and time many-sided quality of these calculations. It is discovered that modified LMS has better execution than others regarding SNR and assembly rate.
IRJET - ECG based Cardiac Arrhythmia Detection using a Deep Neural NetworkIRJET Journal
This paper presents a system for detecting cardiac arrhythmias based on electrocardiogram (ECG) signals using a deep neural network. ECG signals are first transformed into time-frequency spectrograms using short-time Fourier transform. These spectrograms are then used as input for a 2D convolutional neural network to classify five types of arrhythmias: normal beat, normal sinus rhythm, atrial fibrillation, supraventricular tachycardia, and atrial premature beat. The technique is evaluated on the MIT-BIH database and achieves 97% beat classification accuracy and perfect rhythm identification. Compared to other existing methods like SVM, RNN, RF and KNN, the deep learning approach provides better performance for E
IRJET- Arrhythmia Detection using One Dimensional Convolutional Neural NetworkIRJET Journal
1) The document discusses using a 1D convolutional neural network to detect different types of arrhythmias from electrocardiogram (ECG) signals.
2) It proposes a novel wavelet domain multiresolution convolutional neural network approach that avoids complicated heartbeat detection techniques and heavy manual feature engineering.
3) The approach segments ECG signals, applies a discrete cosine transform to select coefficients, and uses a CNN for classification and arrhythmia monitoring. It detects five types of arrhythmias from one-lead ECG signals.
IRJET- Prediction and Classification of Cardiac ArrhythmiaIRJET Journal
This document discusses a study that used an ensemble classifier to predict and classify cardiac arrhythmia. The study used a dataset from the UCI machine learning repository. Feature selection was performed using an extra trees classifier and data preprocessing including normalization and imputing missing values. An ensemble classifier combining logistic regression, SVM, random forest and gradient boosting models was implemented and achieved 90% accuracy in predicting arrhythmia, outperforming other machine learning algorithms. The ensemble approach combined the strengths of different models for improved performance in cardiac arrhythmia classification.
Data Classification Algorithm Using k-Nearest Neighbour Method Applied to ECG...IOSR Journals
This document discusses using a k-nearest neighbor algorithm to classify ECG data. It proposes using additional dimensional features of ECG signals, like the area under the curve calculated using Simpson's rule and a scanline algorithm, along with patient metadata like age, gender, exercise levels, and medical history. A mathematical model is defined to represent the ECG and patient data. The k-nearest neighbor algorithm is then described as a way to classify new ECG data based on its similarity to labeled training data, using Euclidean distance to find the closest k neighbors. This approach aims to improve ECG analysis by considering more than just the ECG signal.
Classification and Detection of ECG-signals using Artificial Neural NetworksGaurav upadhyay
An electrocardiogram (ECG) is a bio-electrical signal which is used to record the heart's electrical activity with respect to time. Early and accurate detection is important in detecting heart diseases and choosing appropriate treatment for a patient. ECG signals are used as the parameter for detection of Cardiac diseases and most of the data comes from PhysioDataNet and MIT-BIH database .The pre-processing of ECG signal is performed with help of Wavelet toolbox and also used for feature extraction of ECG signal. The complete project is implemented on MATLAB platform. The performance of the algorithm is evaluated on MIT–BIH Database. This paper presents the application of Probabilistic Neural Networks (PNN) for the classification and detection of Electrocardiogram (ECG).
Ecg beat classification and feature extraction using artificial neural networ...priyanka leenakhabiya
This document discusses a proposed technique for ECG beat classification and feature extraction using artificial neural networks and discrete wavelet transform. The key steps of the proposed technique include ECG data pre-processing using discrete wavelet transform to remove noise, extracting features such as RR interval and QRS complex, designing and training an artificial neural network on the extracted features, and using an Euclidean classifier to classify different ECG cases based on the minimum distance between features. Experimental results on ECG data from the MIT-BIH database show that the proposed technique achieves high classification accuracy and sensitivity compared to previous methods.
A comparative study of wavelet families for electromyography signal classific...journalBEEI
The document presents a study comparing different wavelet families for classifying electromyography (EMG) signals based on discrete wavelet transform (DWT). The proposed method involves decomposing EMG signals into sub-bands using DWT, extracting statistical features from each sub-band, and using support vector machines (SVM) for classification. Results showed that the sym14 wavelet at the 8th decomposition level achieved the best classification performance for detecting neuromuscular disorders. The study demonstrates that the proposed DWT-based approach can effectively classify EMG signals and help diagnose neuromuscular conditions.
Classification of ecg signal using artificial neural networkGaurav upadhyay
An electrocardiogram (ECG) is a bio-electrical signal which is used to record the heart's electrical activity with respect to time. Early and accurate detection is important in detecting heart diseases and choosing appropriate treatment for a patient. ECG signals are used as the parameter for detection of Cardiac diseases and most of the data comes from PhysioDataNet and MIT-BIH database .The pre-processing of ECG signal is performed with help of Wavelet toolbox and also used for feature extraction of ECG signal. The complete project is implemented on MATLAB platform. The performance of the algorithm is evaluated on MIT–BIH Database. This paper presents the application of Probabilistic Neural Networks (PNN) for the classification and detection of Electrocardiogram (ECG).
Analysis of Human Electrocardiogram for Biometric Recognition Using Analytic ...CSCJournals
The electrocardiograph (ECG) contains cardiac features unique to each individual. By analyzing ECG, it should therefore be possible not only to detect the rate and consistency of heartbeats but to also extract other signal features in order to identify ECG records belonging to individual subjects. In this paper, a new approach for automatic analysis of single lead ECG for human recognition is proposed and evaluated. Eighteen temporal, amplitude, width and autoregressive (AR) model parameters are extracted from each ECG beat and classified in order to identify each individual. Proposed system uses pre-processing stage to decrease the effects of noise and other unwanted artifacts usually present in raw ECG data. Following pre-processing steps, ECG stream is partitioned into separate windows where each window includes single beat of ECG signal. Window estimation is based on the localization of the R peaks in the ECG stream that detected by Filter bank method for QRS complex detection. ECG features – temporal, amplitude and AR coefficients are then extracted and used as an input to K-nn and SVM classification algorithms in order to identify the individual subjects and beats. Signal pre-processing techniques, applied feature extraction methods and some intermediate and final classification results are presented in this paper.
Training feedforward neural network using genetic algorithm to diagnose left ...TELKOMNIKA JOURNAL
In this research work, a new technique was proposed for the diagnosis of left ventricular hypertrophy (LVH) from the ECG signal. The advanced imaging techniques can be used to diagnose left ventricular hypertrophy, but it leads to time-consuming and more expensive. This proposed technique overcomes thesef issues and may serve as an efficient tool to diagnose the LVH disease. The LVH causes changes in the patterns of ECG signal which includes R wave, QRS and T wave. This proposed approach identifies the changes in the pattern and extracts the temporal, spatial and statistical features of the ECG signal using windowed filtering technique. These features were applied to the conventional classifier and also to the neural network classifier with the modified weights using a genetic algorithm. The weights were modified by combining the crossover operators such as crossover arithmetic and crossover two-point operator. The results were compared with the various classifiers and the performance of the neural network with the modified weights using a genetic algorithm is outperformed. The accuracy of the weights modified feedforward neural network is 97.5%.
Classification of cardiac vascular disease from ecg signals for enhancing mod...hiij
“Why to be in frustration we will do new creation f
or salvation”. Based on these words we grapes your
attention towards saving a life of a heart patient
with the use of ECG in Public Health Care Center by
transmitting ECG signals to nearby hospital server.
In this paper we analyze the abnormalities found i
n the
ECG signals by identifying the Normal, Bradycardia
Arrhythmia, Tachycardia Arrhythmia and Ischemia
signal using the method of Neuro Fuzzy Classifier.
Daubechies Wavelet Transforms is used for feature
extraction and Adaptive Neuro Fuzzy Inference Syste
m (ANFIS) is used for classification. The compressi
on
algorithm is performed by using Huffman coding.
This presentation discusses using machine learning algorithms like SVM and ANN to classify ECG signals as normal or abnormal based on morphological features. It extracts 12 morphological features from preprocessed ECG data in 4 databases. SVM achieved 87% accuracy on average for binary classification, comparable to related works. ANN performed best with 24 neurons in a single hidden layer, achieving 93% accuracy. While simple models were used, the morphological features proved robust across different datasets, suggesting potential for automated preliminary ECG diagnosis. Future work could optimize feature selection and apply deep learning models.
IRJET-A Survey on Effect of Meditation on Attention Level Using EEGIRJET Journal
This document summarizes a proposed study that investigates the effect of meditation on attention level using EEG data analysis. It begins with an introduction on attention and meditation, then reviews previous related studies that analyzed EEG data to measure attention. The proposed work will record EEG data from subjects using the 10-20 electrode placement system before and after an 8-week meditation program. The EEG data will be preprocessed to remove noise, features will be extracted using wavelet transforms, and a random forest classifier will be used to classify attention levels and analyze the effect of meditation. The goal is to objectively measure how meditation impacts attention to help students improve concentration.
This document discusses a system for classifying and compressing cardiac vascular diseases using soft computing techniques to enhance rural healthcare. ECG signals are collected from patients and features are extracted from the signals using discrete wavelet transform. The features are classified using an adaptive neuro-fuzzy inference system to identify normal signals or one of four abnormal conditions. Signals classified as critical are compressed using Huffman coding and sent to a hospital server for treatment, while mild cases are advised to see a cardiologist. The system aims to help identify heart conditions early to save lives in rural areas with limited access to healthcare.
Improving Long Term Myoelectric Decoding, Using an Adaptive Classifier with L...Sarthak Jain
This document presents a novel adaptive myoelectric decoding algorithm to improve long-term accuracy of prosthetic limb control. The algorithm relies on unsupervised updates to the training set to adapt to both slow and fast changes in myoelectric signals over time. An able-bodied user performed eight wrist movements over 4.5 hours while EMG data was collected. The proposed algorithm maintained decoding accuracy with a decay rate of 0.2 per hour, compared to 3.3 per hour for a non-adaptive classifier, demonstrating its ability to adapt to changes in signals and improve reliability of myoelectric prostheses.
IRJET- Classification and Identification of Arrhythmia using Machine Lear...IRJET Journal
1) The document discusses a study that uses machine learning techniques to classify and identify different types of arrhythmias based on electrocardiography (ECG) data.
2) It proposes a system that uses the Pan-Tompkins algorithm to preprocess ECG signals and remove noise, extracts 11 features from the filtered signals, and trains a feedforward neural network classifier using the Levenberg-Marquardt algorithm to classify heartbeats into 4 arrhythmia classes.
3) The results show that the trained neural network achieves an accuracy of 96.1% based on evaluation using a confusion matrix on the test data.
IRJET- Automated Measurement of AVR Feature in Fundus Images using Image ...IRJET Journal
This document summarizes an ongoing project to automatically measure the arteriolar-to-venular ratio (AVR) in fundus images using image processing and machine learning techniques. The project involves six main stages: preprocessing, vessel segmentation, region of interest detection, vessel width measurement, vessel classification into arteries and veins, and AVR calculation. So far, the team has completed the first four stages using image processing in MATLAB and Python. They are now working on the vessel classification stage, evaluating both unsupervised k-means clustering and supervised naive Bayes classification approaches. The goal of the project is to develop a fully automated method without any user input to accurately measure AVR, which is important for predicting cardiovascular and other diseases.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Performance analysis of ecg qrs complex detection using morphological operatorsIAEME Publication
The QRS complex detection is one of the most essential tasks in ECG analysis. This paper
presents an algorithm of QRS complex detection using morphological operators. The proposed
algorithm utilizes the dilation-erosion mathematical morphology filtering to suppress the background
noise and remove the baseline drift. Then the modulus accumulation is used to enhance the signal
and improve signal-to-noise ratio. The performance of the algorithm is evaluated with MIT-BIH
arrhythmia database and wearable ECG Data. The algorithm gets the high detection rate and high
speed.
IRJET- RESULT:Wavelet Transform along with SPIHT Algorithm Used for Image Com...IRJET Journal
This document summarizes a research paper that proposes a new medical image compression algorithm combining lifting wavelet transform with the Set Partitioning in Hierarchical Trees (SPIHT) coding algorithm. The algorithm applies lifting schemes to implement wavelet transforms, which decompose an image into sub-bands. It then uses SPIHT coding to efficiently encode the wavelet coefficients. Experimental results showed the proposed algorithm achieved higher peak signal-to-noise ratios than other compression methods like JPEG, making it superior for compressing medical images like MRI scans in both lossy and lossless formats.
Novel method to find the parameter for noise removal from multi channel ecg w...eSAT Journals
This document presents a novel method for removing noise from multi-channel electrocardiogram (ECG) waveforms using a multi-swarm optimization (MSO) approach. The method involves extracting features from ECG data, using MSO to identify an optimal cutoff frequency parameter for a finite impulse response (FIR) filter, and applying the FIR filter using the identified parameter to remove noise from the ECG signals. The MSO approach divides particles into multiple swarms that each focus on a region of the search space, helping to overcome sensitivity to initial positions found in traditional particle swarm optimization. The resulting filtered ECG signals are evaluated against original clean signals to validate the noise removal performance of the MSO-identified cutoff frequency parameter and
This document discusses using neural networks for ECG classification. It provides background on neural networks in medical applications and discusses their use in classifying arrhythmias and ischemia from ECG data. The document outlines approaches taken, including feature extraction methods and training neural network classifiers. Results show correct classification rates from 88-95% depending on the network architecture.
The document summarizes a graduate thesis on developing a quantitative classification method for pulse diagnosis using machine learning techniques. It discusses collecting pulse wave data, analyzing it using chaos theory and principal component analysis, and classifying the results using self-organizing maps. The goal is to establish an objective, data-driven approach to pulse diagnosis to help diagnose lifestyle diseases and reduce healthcare costs.
This document presents a novel algorithm for automated detection of heartbeats in an electrocardiogram (ECG) signal using morphological filtering and Daubechies wavelet transform. The algorithm consists of three stages: 1) preprocessing using mathematical morphology operations to remove noise and baseline wander, 2) Daubechies wavelet transform decomposition to facilitate heartbeat detection, and 3) feature extraction to identify the QRS complex and detect heartbeats by analyzing the wavelet coefficients. Morphological filtering preserves the original ECG signal shape while removing impulsive noise, and wavelet transform aids in analyzing the non-stationary ECG signal. The algorithm aims to provide accurate and reliable heartbeat detection for diagnosing cardiac conditions.
An Experimental Investigation of Partial Replacement of Cement by Various Per...IJERA Editor
Over 15 million tons of fly ash (FA) and 3 million tons of phospho-gypsum (PG) are produced every year. The utilization of these industrial by-product materials is important in terms of environmental and economical issues are concerned. The main purpose of this study is to evaluate the technical possibilities of incorporating FA and PG in production of concrete .In this study Combination of FA and PG is use as a mineral admixture with, phosphogypsum 0%., 5%,10%, 15% and fly ash is constant as 20% , Last proportion was taken PG- 5% and FA- 25%. . The compressive, tensile and flexural strength are studied by casting and testing specimens for 7, 14 and 28 days. It is shown that a part of ordinary Portland cement can be replaced with PG and FA to develop a good and hardened concrete to achieve economy; above 10% replacement of phosphogypsum and 20% replacement of F in concrete lead to drastic reduction not only in the compressive strength but also in Flexural and split tensile strength of concrete.
An Experimental Investigation of Use of Phosphogypsum and Marble Powder for M...IJERA Editor
In this paper, the detailed experimental investigation was done to study the effect of partial replacement of ce-ment by phosphogypsum (PG) and marble powder (MP) in combine proportion started from 5% PG and 25% MP mix together in concrete by replacement of cement with the gradual increase of PG by 5% upto 15% whe-reas MP is constant at 25%.Last proportion was taken after decreasing PG by 5% and increasing MP by 10%. The tests on hardened concrete were destructive in nature which includes compressive test on cube for size (150 x 150 x 150 mm) at 7, 14 and 28 days of curing as per IS: 516 1959, Flexural strength on beam (150 x 150 x700 mm) at 28 days of curing as per IS: 516 1959 and split tensile strength on cylinder (150 mm ø x 300mm) at 28 days of curing as per IS: 5816 1999. The work presented in this paper reports the effects on the behavior of con-crete produced from cement with combination of PG and MP at different proportions on the mechanical proper-ties of concrete such as compressive strength, flexural strength, and split tensile strength. Investigation reported that compressive strength decreases by 16.89% in compared with targeted strength and decreases by 12.78% compared with control concrete at 28 days, flexural strength decreases by 26.46% compared with control con-crete at 28 days, split tensile strength increases by 10.833% compared with conventional concrete at 28 days, were obtained at combination of (5% PG and 25% MP). Partial replacement of PG and MP reduces the envi-ronmental effects, produces economical and eco-friendly concrete.
Reliability Analysis of a 3-Machine Power Station Using State Space ApproachIJERA Editor
With the advent of high-integrity fault-tolerant systems, the ability to account for repairs of partially failed (but still operational) systems become increasingly important. This paper presents a systemic method of determining the reliability of a 3-machine electric power station, taking into consideration the failure rates and repair rates of the individual component (machine) that make up the system. A state-space transition process for a 3-machine with 23 states was developed and consequently, steady state equations were generated based on Markov mathematical modeling of the power station. Important reliability components were deduced from this analysis. This research simulation was achieved with codes written in Excel®-VBA programming environment. System reliability using state space approach proofs to be a viable and efficient technique of reliability prediction as it is able to predict the state of the system under consideration. For the purpose of neatness and easy entry of data, Graphic User Interface (GUI) was designed.
Ecg beat classification and feature extraction using artificial neural networ...priyanka leenakhabiya
This document discusses a proposed technique for ECG beat classification and feature extraction using artificial neural networks and discrete wavelet transform. The key steps of the proposed technique include ECG data pre-processing using discrete wavelet transform to remove noise, extracting features such as RR interval and QRS complex, designing and training an artificial neural network on the extracted features, and using an Euclidean classifier to classify different ECG cases based on the minimum distance between features. Experimental results on ECG data from the MIT-BIH database show that the proposed technique achieves high classification accuracy and sensitivity compared to previous methods.
A comparative study of wavelet families for electromyography signal classific...journalBEEI
The document presents a study comparing different wavelet families for classifying electromyography (EMG) signals based on discrete wavelet transform (DWT). The proposed method involves decomposing EMG signals into sub-bands using DWT, extracting statistical features from each sub-band, and using support vector machines (SVM) for classification. Results showed that the sym14 wavelet at the 8th decomposition level achieved the best classification performance for detecting neuromuscular disorders. The study demonstrates that the proposed DWT-based approach can effectively classify EMG signals and help diagnose neuromuscular conditions.
Classification of ecg signal using artificial neural networkGaurav upadhyay
An electrocardiogram (ECG) is a bio-electrical signal which is used to record the heart's electrical activity with respect to time. Early and accurate detection is important in detecting heart diseases and choosing appropriate treatment for a patient. ECG signals are used as the parameter for detection of Cardiac diseases and most of the data comes from PhysioDataNet and MIT-BIH database .The pre-processing of ECG signal is performed with help of Wavelet toolbox and also used for feature extraction of ECG signal. The complete project is implemented on MATLAB platform. The performance of the algorithm is evaluated on MIT–BIH Database. This paper presents the application of Probabilistic Neural Networks (PNN) for the classification and detection of Electrocardiogram (ECG).
Analysis of Human Electrocardiogram for Biometric Recognition Using Analytic ...CSCJournals
The electrocardiograph (ECG) contains cardiac features unique to each individual. By analyzing ECG, it should therefore be possible not only to detect the rate and consistency of heartbeats but to also extract other signal features in order to identify ECG records belonging to individual subjects. In this paper, a new approach for automatic analysis of single lead ECG for human recognition is proposed and evaluated. Eighteen temporal, amplitude, width and autoregressive (AR) model parameters are extracted from each ECG beat and classified in order to identify each individual. Proposed system uses pre-processing stage to decrease the effects of noise and other unwanted artifacts usually present in raw ECG data. Following pre-processing steps, ECG stream is partitioned into separate windows where each window includes single beat of ECG signal. Window estimation is based on the localization of the R peaks in the ECG stream that detected by Filter bank method for QRS complex detection. ECG features – temporal, amplitude and AR coefficients are then extracted and used as an input to K-nn and SVM classification algorithms in order to identify the individual subjects and beats. Signal pre-processing techniques, applied feature extraction methods and some intermediate and final classification results are presented in this paper.
Training feedforward neural network using genetic algorithm to diagnose left ...TELKOMNIKA JOURNAL
In this research work, a new technique was proposed for the diagnosis of left ventricular hypertrophy (LVH) from the ECG signal. The advanced imaging techniques can be used to diagnose left ventricular hypertrophy, but it leads to time-consuming and more expensive. This proposed technique overcomes thesef issues and may serve as an efficient tool to diagnose the LVH disease. The LVH causes changes in the patterns of ECG signal which includes R wave, QRS and T wave. This proposed approach identifies the changes in the pattern and extracts the temporal, spatial and statistical features of the ECG signal using windowed filtering technique. These features were applied to the conventional classifier and also to the neural network classifier with the modified weights using a genetic algorithm. The weights were modified by combining the crossover operators such as crossover arithmetic and crossover two-point operator. The results were compared with the various classifiers and the performance of the neural network with the modified weights using a genetic algorithm is outperformed. The accuracy of the weights modified feedforward neural network is 97.5%.
Classification of cardiac vascular disease from ecg signals for enhancing mod...hiij
“Why to be in frustration we will do new creation f
or salvation”. Based on these words we grapes your
attention towards saving a life of a heart patient
with the use of ECG in Public Health Care Center by
transmitting ECG signals to nearby hospital server.
In this paper we analyze the abnormalities found i
n the
ECG signals by identifying the Normal, Bradycardia
Arrhythmia, Tachycardia Arrhythmia and Ischemia
signal using the method of Neuro Fuzzy Classifier.
Daubechies Wavelet Transforms is used for feature
extraction and Adaptive Neuro Fuzzy Inference Syste
m (ANFIS) is used for classification. The compressi
on
algorithm is performed by using Huffman coding.
This presentation discusses using machine learning algorithms like SVM and ANN to classify ECG signals as normal or abnormal based on morphological features. It extracts 12 morphological features from preprocessed ECG data in 4 databases. SVM achieved 87% accuracy on average for binary classification, comparable to related works. ANN performed best with 24 neurons in a single hidden layer, achieving 93% accuracy. While simple models were used, the morphological features proved robust across different datasets, suggesting potential for automated preliminary ECG diagnosis. Future work could optimize feature selection and apply deep learning models.
IRJET-A Survey on Effect of Meditation on Attention Level Using EEGIRJET Journal
This document summarizes a proposed study that investigates the effect of meditation on attention level using EEG data analysis. It begins with an introduction on attention and meditation, then reviews previous related studies that analyzed EEG data to measure attention. The proposed work will record EEG data from subjects using the 10-20 electrode placement system before and after an 8-week meditation program. The EEG data will be preprocessed to remove noise, features will be extracted using wavelet transforms, and a random forest classifier will be used to classify attention levels and analyze the effect of meditation. The goal is to objectively measure how meditation impacts attention to help students improve concentration.
This document discusses a system for classifying and compressing cardiac vascular diseases using soft computing techniques to enhance rural healthcare. ECG signals are collected from patients and features are extracted from the signals using discrete wavelet transform. The features are classified using an adaptive neuro-fuzzy inference system to identify normal signals or one of four abnormal conditions. Signals classified as critical are compressed using Huffman coding and sent to a hospital server for treatment, while mild cases are advised to see a cardiologist. The system aims to help identify heart conditions early to save lives in rural areas with limited access to healthcare.
Improving Long Term Myoelectric Decoding, Using an Adaptive Classifier with L...Sarthak Jain
This document presents a novel adaptive myoelectric decoding algorithm to improve long-term accuracy of prosthetic limb control. The algorithm relies on unsupervised updates to the training set to adapt to both slow and fast changes in myoelectric signals over time. An able-bodied user performed eight wrist movements over 4.5 hours while EMG data was collected. The proposed algorithm maintained decoding accuracy with a decay rate of 0.2 per hour, compared to 3.3 per hour for a non-adaptive classifier, demonstrating its ability to adapt to changes in signals and improve reliability of myoelectric prostheses.
IRJET- Classification and Identification of Arrhythmia using Machine Lear...IRJET Journal
1) The document discusses a study that uses machine learning techniques to classify and identify different types of arrhythmias based on electrocardiography (ECG) data.
2) It proposes a system that uses the Pan-Tompkins algorithm to preprocess ECG signals and remove noise, extracts 11 features from the filtered signals, and trains a feedforward neural network classifier using the Levenberg-Marquardt algorithm to classify heartbeats into 4 arrhythmia classes.
3) The results show that the trained neural network achieves an accuracy of 96.1% based on evaluation using a confusion matrix on the test data.
IRJET- Automated Measurement of AVR Feature in Fundus Images using Image ...IRJET Journal
This document summarizes an ongoing project to automatically measure the arteriolar-to-venular ratio (AVR) in fundus images using image processing and machine learning techniques. The project involves six main stages: preprocessing, vessel segmentation, region of interest detection, vessel width measurement, vessel classification into arteries and veins, and AVR calculation. So far, the team has completed the first four stages using image processing in MATLAB and Python. They are now working on the vessel classification stage, evaluating both unsupervised k-means clustering and supervised naive Bayes classification approaches. The goal of the project is to develop a fully automated method without any user input to accurately measure AVR, which is important for predicting cardiovascular and other diseases.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Performance analysis of ecg qrs complex detection using morphological operatorsIAEME Publication
The QRS complex detection is one of the most essential tasks in ECG analysis. This paper
presents an algorithm of QRS complex detection using morphological operators. The proposed
algorithm utilizes the dilation-erosion mathematical morphology filtering to suppress the background
noise and remove the baseline drift. Then the modulus accumulation is used to enhance the signal
and improve signal-to-noise ratio. The performance of the algorithm is evaluated with MIT-BIH
arrhythmia database and wearable ECG Data. The algorithm gets the high detection rate and high
speed.
IRJET- RESULT:Wavelet Transform along with SPIHT Algorithm Used for Image Com...IRJET Journal
This document summarizes a research paper that proposes a new medical image compression algorithm combining lifting wavelet transform with the Set Partitioning in Hierarchical Trees (SPIHT) coding algorithm. The algorithm applies lifting schemes to implement wavelet transforms, which decompose an image into sub-bands. It then uses SPIHT coding to efficiently encode the wavelet coefficients. Experimental results showed the proposed algorithm achieved higher peak signal-to-noise ratios than other compression methods like JPEG, making it superior for compressing medical images like MRI scans in both lossy and lossless formats.
Novel method to find the parameter for noise removal from multi channel ecg w...eSAT Journals
This document presents a novel method for removing noise from multi-channel electrocardiogram (ECG) waveforms using a multi-swarm optimization (MSO) approach. The method involves extracting features from ECG data, using MSO to identify an optimal cutoff frequency parameter for a finite impulse response (FIR) filter, and applying the FIR filter using the identified parameter to remove noise from the ECG signals. The MSO approach divides particles into multiple swarms that each focus on a region of the search space, helping to overcome sensitivity to initial positions found in traditional particle swarm optimization. The resulting filtered ECG signals are evaluated against original clean signals to validate the noise removal performance of the MSO-identified cutoff frequency parameter and
This document discusses using neural networks for ECG classification. It provides background on neural networks in medical applications and discusses their use in classifying arrhythmias and ischemia from ECG data. The document outlines approaches taken, including feature extraction methods and training neural network classifiers. Results show correct classification rates from 88-95% depending on the network architecture.
The document summarizes a graduate thesis on developing a quantitative classification method for pulse diagnosis using machine learning techniques. It discusses collecting pulse wave data, analyzing it using chaos theory and principal component analysis, and classifying the results using self-organizing maps. The goal is to establish an objective, data-driven approach to pulse diagnosis to help diagnose lifestyle diseases and reduce healthcare costs.
This document presents a novel algorithm for automated detection of heartbeats in an electrocardiogram (ECG) signal using morphological filtering and Daubechies wavelet transform. The algorithm consists of three stages: 1) preprocessing using mathematical morphology operations to remove noise and baseline wander, 2) Daubechies wavelet transform decomposition to facilitate heartbeat detection, and 3) feature extraction to identify the QRS complex and detect heartbeats by analyzing the wavelet coefficients. Morphological filtering preserves the original ECG signal shape while removing impulsive noise, and wavelet transform aids in analyzing the non-stationary ECG signal. The algorithm aims to provide accurate and reliable heartbeat detection for diagnosing cardiac conditions.
An Experimental Investigation of Partial Replacement of Cement by Various Per...IJERA Editor
Over 15 million tons of fly ash (FA) and 3 million tons of phospho-gypsum (PG) are produced every year. The utilization of these industrial by-product materials is important in terms of environmental and economical issues are concerned. The main purpose of this study is to evaluate the technical possibilities of incorporating FA and PG in production of concrete .In this study Combination of FA and PG is use as a mineral admixture with, phosphogypsum 0%., 5%,10%, 15% and fly ash is constant as 20% , Last proportion was taken PG- 5% and FA- 25%. . The compressive, tensile and flexural strength are studied by casting and testing specimens for 7, 14 and 28 days. It is shown that a part of ordinary Portland cement can be replaced with PG and FA to develop a good and hardened concrete to achieve economy; above 10% replacement of phosphogypsum and 20% replacement of F in concrete lead to drastic reduction not only in the compressive strength but also in Flexural and split tensile strength of concrete.
An Experimental Investigation of Use of Phosphogypsum and Marble Powder for M...IJERA Editor
In this paper, the detailed experimental investigation was done to study the effect of partial replacement of ce-ment by phosphogypsum (PG) and marble powder (MP) in combine proportion started from 5% PG and 25% MP mix together in concrete by replacement of cement with the gradual increase of PG by 5% upto 15% whe-reas MP is constant at 25%.Last proportion was taken after decreasing PG by 5% and increasing MP by 10%. The tests on hardened concrete were destructive in nature which includes compressive test on cube for size (150 x 150 x 150 mm) at 7, 14 and 28 days of curing as per IS: 516 1959, Flexural strength on beam (150 x 150 x700 mm) at 28 days of curing as per IS: 516 1959 and split tensile strength on cylinder (150 mm ø x 300mm) at 28 days of curing as per IS: 5816 1999. The work presented in this paper reports the effects on the behavior of con-crete produced from cement with combination of PG and MP at different proportions on the mechanical proper-ties of concrete such as compressive strength, flexural strength, and split tensile strength. Investigation reported that compressive strength decreases by 16.89% in compared with targeted strength and decreases by 12.78% compared with control concrete at 28 days, flexural strength decreases by 26.46% compared with control con-crete at 28 days, split tensile strength increases by 10.833% compared with conventional concrete at 28 days, were obtained at combination of (5% PG and 25% MP). Partial replacement of PG and MP reduces the envi-ronmental effects, produces economical and eco-friendly concrete.
Reliability Analysis of a 3-Machine Power Station Using State Space ApproachIJERA Editor
With the advent of high-integrity fault-tolerant systems, the ability to account for repairs of partially failed (but still operational) systems become increasingly important. This paper presents a systemic method of determining the reliability of a 3-machine electric power station, taking into consideration the failure rates and repair rates of the individual component (machine) that make up the system. A state-space transition process for a 3-machine with 23 states was developed and consequently, steady state equations were generated based on Markov mathematical modeling of the power station. Important reliability components were deduced from this analysis. This research simulation was achieved with codes written in Excel®-VBA programming environment. System reliability using state space approach proofs to be a viable and efficient technique of reliability prediction as it is able to predict the state of the system under consideration. For the purpose of neatness and easy entry of data, Graphic User Interface (GUI) was designed.
Image segmentation is useful in many applications. It can identify the regions of interest in a scene or annotate
the data. It categorizes the existing segmentation algorithm into region-based segmentation, data clustering, and
edge-base segmentation. Region-based segmentation includes the seeded and unseeded region growing
algorithms, the JSEG, and the fast scanning algorithm. Due to the presence of speckle noise, segmentation of
Synthetic Aperture Radar (SAR) images is still a challenging problem. We proposed a fast SAR image
segmentation method based on Particle Swarm Optimization-Gravitational Search Algorithm (PSO-GSA). In
this method, threshold estimation is regarded as a search procedure that examinations for an appropriate value in
a continuous grayscale interval. Hence, PSO-GSA algorithm is familiarized to search for the optimal threshold.
Experimental results indicate that our method is superior to GA based, AFS based and ABC based methods in
terms of segmentation accuracy, segmentation time, and Thresholding.
An Energy-Efficient Lut-Log-Bcjr Architecture Using Constant Log Bcjr AlgorithmIJERA Editor
Error correcting codes are used to correct the data from the corrupted signal due to noise and interference. There
are many error correcting codes. Among them turbo codes is considered to be the best because it is very close to
the Shannon theoretical limit. The MAP algorithm is commonly used in the turbo decoder. Among the different
versions of the MAP algorithm Constant log BCJR algorithm have less complexity and good error performance.
The Constant log BCJR algorithm can be easily designed using look up table which reduces the memory
consumption. The proposed Constant log BCJR decoder is designed to decode two blocks of data at a time, this
increases the throughput. The complexity of the decoder is further reduced by the use of the add compare select
(ACS) units and registers. The proposed decoder is simulated using Xilinx ISE and synthesized using Sparten3
FPGA and found out that Constant log BCJR decoder utilized less amount of memory and power than the LUT
log BCJR decoder.
The document analyzes crop yield data from spatial locations in Guntur District, Andhra Pradesh, India using hybrid data mining techniques. It first applies k-means clustering to the dataset, producing 5 clusters. It then applies the J48 classification algorithm to the clustered data, resulting in a decision tree that predicts cluster membership based on attributes like crop type, irrigated area, and latitude. Analysis found irrigated areas of cotton and chilies increased from 2007-2008 to 2011-2012. Association rule mining on the clustered data also found relationships between productivity and location attributes. The hybrid approach of clustering followed by classification effectively analyzed the spatial agricultural data.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The document presents a method for solving nonlinear time delay control systems using Fourier series. The key steps are:
1) Time functions in the system are expanded as truncated Fourier series with unknown coefficients.
2) Operational matrices of integration, delay, and product are presented and used to evaluate the Fourier coefficients for the solution.
3) This reduces solving the time-delay control system to solving a set of algebraic equations for the Fourier coefficients.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
CLASSIFICATION OF ECG ARRHYTHMIAS USING /DISCRETE WAVELET TRANSFORM AND NEURA...IJCSEA Journal
Automatic recognition of cardiac arrhythmias is important for diagnosis of cardiac abnormalies. Several algorithms have been proposed to classify ECG arrhythmias; however, they cannot perform very well. Therefore, in this paper, an expert system for ElectroCardioGram (ECG) arrhythmia classification is proposed. Discrete wavelet transform is used for processing ECG recordings, and extracting some features, and the Multi-Layer Perceptron (MLP) neural network performs the classification task. Two types of arrhythmias can be detected by the proposed system. Some recordings of the MIT-BIH arrhythmias database have been used for training and testing our neural network based classifier. The simulation results show that the classification accuracy of our algorithm is 96.5% using 10 files including normal and two arrhythmias.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document presents a novel deep learning approach for single-lead electrocardiogram (ECG) classification. The approach uses Restricted Boltzmann Machines (RBM) and Deep Belief Networks (DBN) for ECG classification after detecting ventricular and supraventricular heartbeats from single-lead ECG signals. Experimental results on the MIT-BIH database show the approach achieves high average recognition accuracies of 93.63% for ventricular ectopic beats and 95.57% for supraventricular ectopic beats at a low sampling rate of 114 Hz, outperforming traditional methods.
Performance analysis of ecg qrs complex detection using morphological operatorsIAEME Publication
The document summarizes a research paper that proposes a new algorithm for detecting QRS complexes in electrocardiogram (ECG) signals using mathematical morphology operators. The algorithm utilizes dilation-erosion filtering to suppress noise and remove baseline drift. It then applies modulus accumulation to enhance the signal and improve the signal-to-noise ratio. The algorithm is evaluated using standard ECG databases and achieves high detection rates with high speed.
This document summarizes research on using discrete cosine transform (DCT) to extract frequency domain features from electrocardiogram (ECG) signals for classifying cardiac arrhythmias. Features are extracted by computing the distance between RR waves. These frequency domain features are then classified using various soft computing techniques, including classification and regression trees, radial basis function networks, support vector machines, and multilayer perceptron neural networks. Experiments were conducted on the MIT-BIH arrhythmia database to evaluate the performance of these techniques for ECG-based arrhythmia classification.
This document presents research on classifying cardiac arrhythmias using frequency domain features extracted from electrocardiogram (ECG) signals. Features are extracted from ECG data using Discrete Cosine Transform to calculate the distance between RR waves. These frequency domain features are then classified using various machine learning algorithms, including Classification and Regression Trees, Radial Basis Function networks, Support Vector Machines, and Multilayer Perceptron Neural Networks. Experiments were conducted on the MIT-BIH arrhythmia database to evaluate the performance of the different classifiers.
IRJET- Detection of Abnormal ECG Signal using DWT Feature Extraction and CNNIRJET Journal
This document discusses a study that uses discrete wavelet transform (DWT) to extract features from electrocardiogram (ECG) signals and then uses a convolutional neural network (CNN) to classify the signals as normal or abnormal. DWT is used to represent the ECG signals at different resolutions, which allows numerical features to be extracted. A CNN is then trained on the extracted features to predict whether signals indicate normal or abnormal heart conditions. The goal is to develop an efficient early detection system for cardiovascular disease by combining DWT feature extraction and CNN classification of ECG signals.
Detection and Classification of ECG Arrhythmia using LSTM AutoencoderIRJET Journal
This document discusses a study that uses long short-term memory (LSTM) neural networks to detect and classify different types of arrhythmias from electrocardiogram (ECG) data. The study aims to develop a deep learning approach for classifying different types of arrhythmias in an ECG that is simple, reliable and easy to use. The proposed method achieved a high accuracy rate of 97% in classifying ECG beats into different arrhythmia categories using the MIT-BIH Arrhythmia database. This automated arrhythmia detection system could help clinicians more quickly and accurately identify arrhythmias from ECG data.
Classifying electrocardiograph waveforms using trained deep learning neural n...IAESIJAI
Due to the rise in cardiac patients, an automated system that can identify different heart disorders has been created to lighten and distribute the duty of physicians. This research uses three different electrocardiograph (ECG) signals as indicators of a person's cardiac problems: Normal sinus rhythm (NSR), arrhythmia (ARR), and congestive heart failure (CHF). The continuous wavelet transform (CWT) provides the mechanism for classifying the 190 individual cases of ECG data into a 2-dimensional time-frequency representation. In this paper, the modified GoogLeNet is used for ECG data classification. Using a transfer learning approach and adjustments to parts of the output layers, ECG classification was conducted and the effectiveness of convolutional neural network (CNN) designs was tested. By comparing the results that the optimized neural network and GoogLeNet both had classification accuracy about of 80% and 100%, respectively. The GoogLeNet provide the best result in term of accuracy and training time.
The document proposes a method for classifying electrocardiogram (ECG) arrhythmias using a 2D convolutional neural network (CNN). ECG beats are transformed into grayscale images as inputs for the CNN. The CNN achieves 99.05% average accuracy and 97.85% average sensitivity in classifying arrhythmias from the MIT-BIH database, demonstrating it can accurately classify arrhythmias without manual preprocessing of ECG signals. The method represents an improvement over previous 1D CNN approaches by leveraging the 2D structure of the ECG images.
This document summarizes a research paper that uses a backward propagation neural network with the Levenberg Marquardt algorithm to classify electrocardiogram (ECG) signals as normal or abnormal. The network was trained on the MIT-BIH arrhythmia database and achieved 99.9% accuracy at classifying heartbeats, outperforming other methods. Features extracted from the ECG signals like standard deviation and wavelet coefficients were used as input to the neural network. The results demonstrate that neural networks can accurately analyze ECG signals and detect cardiac abnormalities.
This document summarizes a research paper that uses a backward propagation neural network with the Levenberg Marquardt algorithm to classify electrocardiogram (ECG) signals as normal or abnormal. The network was trained on the MIT-BIH arrhythmia database and achieved 99.9% accuracy at classifying heartbeats, outperforming other methods. Features extracted from the ECG signals like standard deviation and wavelet coefficients were used as input to the neural network. The results demonstrate that neural networks can accurately analyze ECG signals and detect cardiac abnormalities.
An Automated ECG Signal Diagnosing Methodology using Random Forest Classifica...ijtsrd
In this project, we put forward a new automated quality aware ECG beat classification method for effectual diagnosis of ECG arrhythmias under unsubstantiated health concern environments. The suggested method contains three foremost junctures i ECG signal quality assessment ECG SQA based whether it is “acceptable†or “unacceptable†based on our preceding adapted complete ensemble empirical mode decomposition CEEMD and temporal features, ii reconstruction of ECG signal and R peak detection iii the ECG beat classification as well as the ECG beat extraction, beat alignment and Random forest RF based beat classification. The accuracy and robustness of the anticipated method is evaluated by means of different normal and abnormal ECG signals taken from the standard MIT BIH arrhythmia database. The suggested ECG beat extraction approach can recover the categorization accuracy by protecting the QRS complex portion and background noises is suppressed under an acceptable level of noise . The quality aware ECG beat classification techniques attains higher kappa values for the classification accuracies which can be reliable as evaluated to the heartbeat classification methods without the ECG quality assessment process. Akshara Jayanthan M B | Prof. K. Kalai Selvi "An Automated ECG Signal Diagnosing Methodology using Random Forest Classification with Quality Aware Techniques" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-3 , April 2020, URL: https://www.ijtsrd.com/papers/ijtsrd30750.pdf Paper Url :https://www.ijtsrd.com/engineering/electronics-and-communication-engineering/30750/an-automated-ecg-signal-diagnosing-methodology-using-random-forest-classification-with-quality-aware-techniques/akshara-jayanthan-m-b
New Method of R-Wave Detection by Continuous Wavelet TransformCSCJournals
In this paper we have employed a new method of R-peaks detection in electrocardiogram (ECG) signals. This method is based on the application of the discretised Continuous Wavelet Transform (CWT) used for the Bionic Wavelet Transform (BWT). The mother wavelet associated to this transform is the Morlet wavelet. For evaluating the proposed method, we have compared it to others methods that are based on Discrete Wavelet Transform (DWT). In this evaluation, the used ECG signals are taken from MIT-BIH database. The obtained results show that the proposed method outperforms some conventional techniques used in our evaluation.
AR-based Method for ECG Classification and Patient RecognitionCSCJournals
The electrocardiogram (ECG) is the recording of heart activity obtained by measuring the signals from electrical contacts placed on the skin of the patient. By analyzing ECG, it is possible to detect the rate and consistency of heartbeats and identify possible irregularities in heart operation. This paper describes a set of techniques employed to pre-process the ECG signals and extract a set of features – autoregressive (AR) signal parameters used to characterise ECG signal. Extracted parameters are in this work used to accomplish two tasks. Firstly, AR features belonging to each ECG signal are classified in groups corresponding to three different heart conditions – normal, arrhythmia and ventricular arrhythmia. Obtained classification results indicate accurate, zero-error classification of patients according to their heart condition using the proposed method. Sets of extracted AR coefficients are then extended by adding an additional parameter – power of AR modelling error and a suitability of developed technique for individual patient identification is investigated. Individual feature sets for each group of detected QRS sections are classified in p clusters where p represents the number of patients in each group. Developed system has been tested using ECG signals available in MIT/BIH and Politecnico of Milano VCG/ECG database. Achieved recognition rates indicate that patient identification using ECG signals could be considered as a possible approach in some applications using the system developed in this work. Pre-processing stages, applied parameter extraction techniques and some intermediate and final classification results are described and presented in this paper.
Iaetsd a review on ecg arrhythmia detectionIaetsd Iaetsd
This document proposes a method to detect cardiac arrhythmias from electrocardiogram (ECG) signals using double density discrete wavelet transformation (DD-DWT). The method involves preprocessing the ECG signal, extracting features using DD-DWT, and classifying rhythms using support vector machines (SVM). Features extracted include temporal intervals between peaks and morphological characteristics. DD-DWT decomposes the ECG into sub-bands, allowing subtle changes to be detected. SVM is used for classification. The method is tested on the MIT-BIH Arrhythmia database and is found to provide better arrhythmia detection compared to existing methods.
IRJET - Heart Health Classification and Prediction using Machine LearningIRJET Journal
1) The document discusses using machine learning models to classify heart health based on medical records and heart sounds.
2) Support vector machines, logistic regression, random forest, and ensemble learning algorithms were used to predict heart disease risk based on medical records.
3) Convolutional neural networks were used to develop models for heart sound segmentation and classification. The models classify heart sounds as normal, murmur, or extrasystole based on the timing of the S1 and S2 heart sounds.
A Review on ECG -Signal Classification of Scalogram Snap shots the use of Con...IRJET Journal
This document summarizes previous research on classifying electrocardiogram (ECG) signals using convolutional neural networks (CNNs) and continuous wavelet transforms. It discusses how CNNs trained on large ECG datasets can classify cardiac arrhythmias with higher accuracy than experts. Previous studies used CNNs to extract features from ECG time-frequency spectrograms generated via short-time Fourier transforms or continuous wavelet transforms. The document reviews several studies that achieved high classification accuracy for different types of arrhythmias using these deep learning techniques. It also mentions the motivation is to help diagnosis and early detection of heart conditions, and the objective is to reduce classification time and increase accuracy.
Less computational approach to detect QRS complexes in ECG rhythmsCSITiaesprime
Electrocardiogram (ECG) signals are normally affected by artifacts that require manual assessment or use of other reference signals. Currently, Cardiographs are used to achieve basic necessary heart rate monitoring in real conditions. This work aims to study and identify main ECG features, QRS complexes, as one of the steps of a comprehensive ECG signal analysis. The proposed algorithm suggested an automatic recognition of QRS complexes in ECG rhythm. This method is designed based on several filter structure composes low pass, difference and summation filters. The filtered signal is fed to an adaptive threshold function to detect QRS complexes. The algorithm was validated and results were checked with experimental data based on sensitivity test.
Photoplethysmography (PPG) and Phonocardiography (PCG) are two important non-invasive techniques for monitoring physiological parameters of cardiovascular diagnostics. The PCG signal discloses information about cardiac function through vibrations caused by the working heart. PPG measures relative blood volume changes in the blood vessels close to the skin. This paper emphasizes on simultaneous acquisition of PCG and PPG signals from the same subject with the aid of NIELVIS II+ DAQ and the signals are imported to MATLAB for further processing. Heart rate is extracted from both the signals which are found to be distinctive. This analytical approach of processing these signals can abet for analysis of Heart rate variability (HRV) which is widely used for quantifying neural cardiac control and low variability is particularly predictive of death in patients after myocardial infarction.
Similar to Accuracy Assessment for Multi-Channel ECG Waveforms Using Soft Computing Methodologies (20)
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...PriyankaKilaniya
Energy efficiency has been important since the latter part of the last century. The main object of this survey is to determine the energy efficiency knowledge among consumers. Two separate districts in Bangladesh are selected to conduct the survey on households and showrooms about the energy and seller also. The survey uses the data to find some regression equations from which it is easy to predict energy efficiency knowledge. The data is analyzed and calculated based on five important criteria. The initial target was to find some factors that help predict a person's energy efficiency knowledge. From the survey, it is found that the energy efficiency awareness among the people of our country is very low. Relationships between household energy use behaviors are estimated using a unique dataset of about 40 households and 20 showrooms in Bangladesh's Chapainawabganj and Bagerhat districts. Knowledge of energy consumption and energy efficiency technology options is found to be associated with household use of energy conservation practices. Household characteristics also influence household energy use behavior. Younger household cohorts are more likely to adopt energy-efficient technologies and energy conservation practices and place primary importance on energy saving for environmental reasons. Education also influences attitudes toward energy conservation in Bangladesh. Low-education households indicate they primarily save electricity for the environment while high-education households indicate they are motivated by environmental concerns.
Generative AI Use cases applications solutions and implementation.pdfmahaffeycheryld
Generative AI solutions encompass a range of capabilities from content creation to complex problem-solving across industries. Implementing generative AI involves identifying specific business needs, developing tailored AI models using techniques like GANs and VAEs, and integrating these models into existing workflows. Data quality and continuous model refinement are crucial for effective implementation. Businesses must also consider ethical implications and ensure transparency in AI decision-making. Generative AI's implementation aims to enhance efficiency, creativity, and innovation by leveraging autonomous generation and sophisticated learning algorithms to meet diverse business challenges.
https://www.leewayhertz.com/generative-ai-use-cases-and-applications/
Height and depth gauge linear metrology.pdfq30122000
Height gauges may also be used to measure the height of an object by using the underside of the scriber as the datum. The datum may be permanently fixed or the height gauge may have provision to adjust the scale, this is done by sliding the scale vertically along the body of the height gauge by turning a fine feed screw at the top of the gauge; then with the scriber set to the same level as the base, the scale can be matched to it. This adjustment allows different scribers or probes to be used, as well as adjusting for any errors in a damaged or resharpened probe.
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...shadow0702a
This document serves as a comprehensive step-by-step guide on how to effectively use PyCharm for remote debugging of the Windows Subsystem for Linux (WSL) on a local Windows machine. It meticulously outlines several critical steps in the process, starting with the crucial task of enabling permissions, followed by the installation and configuration of WSL.
The guide then proceeds to explain how to set up the SSH service within the WSL environment, an integral part of the process. Alongside this, it also provides detailed instructions on how to modify the inbound rules of the Windows firewall to facilitate the process, ensuring that there are no connectivity issues that could potentially hinder the debugging process.
The document further emphasizes on the importance of checking the connection between the Windows and WSL environments, providing instructions on how to ensure that the connection is optimal and ready for remote debugging.
It also offers an in-depth guide on how to configure the WSL interpreter and files within the PyCharm environment. This is essential for ensuring that the debugging process is set up correctly and that the program can be run effectively within the WSL terminal.
Additionally, the document provides guidance on how to set up breakpoints for debugging, a fundamental aspect of the debugging process which allows the developer to stop the execution of their code at certain points and inspect their program at those stages.
Finally, the document concludes by providing a link to a reference blog. This blog offers additional information and guidance on configuring the remote Python interpreter in PyCharm, providing the reader with a well-rounded understanding of the process.
Software Engineering and Project Management - Software Testing + Agile Method...Prakhyath Rai
Software Testing: A Strategic Approach to Software Testing, Strategic Issues, Test Strategies for Conventional Software, Test Strategies for Object -Oriented Software, Validation Testing, System Testing, The Art of Debugging.
Agile Methodology: Before Agile – Waterfall, Agile Development.
Open Channel Flow: fluid flow with a free surfaceIndrajeet sahu
Open Channel Flow: This topic focuses on fluid flow with a free surface, such as in rivers, canals, and drainage ditches. Key concepts include the classification of flow types (steady vs. unsteady, uniform vs. non-uniform), hydraulic radius, flow resistance, Manning's equation, critical flow conditions, and energy and momentum principles. It also covers flow measurement techniques, gradually varied flow analysis, and the design of open channels. Understanding these principles is vital for effective water resource management and engineering applications.
Accuracy Assessment for Multi-Channel ECG Waveforms Using Soft Computing Methodologies
1. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 41|P a g e
Accuracy Assessment for Multi-Channel ECG Waveforms Using Soft Computing Methodologies Menta Srinivasulu*, Dr. K Chennakeshava Reddy** *(Professor and HOD ECE Dept. LITS, Khammam, AP, India) **(Principal, BIET, Ibrahimpatnam, AP, India) Abstract ECG waveform rhythmic analysis is very important. In recent trends, analysis processes of ECG waveform applications are available in smart devices. Still, existing methods are not able to accomplish the complete accuracy assessment while classify the multi-channel ECG waveforms. In this paper, proposed analysis of accuracy assessment of the classification of multi-channel ECG waveforms using most popular Soft Computing algorithms. In this research, main focus is on the better rule generation to analyze the multi-channel ECG waveforms. Analysis is mainly done inSoft Computing methods like the Decision Trees with different pruning analysis, Logistic Model Trees with different regression process and Support Vector Machine with Particle Swarm Optimization (SVM-PSO). All these analysis methods are trained and tested with MIT-BIH 12 channel ECG waveforms. Before trained these methods, MSO-FIR filter should be used as data preprocessing for removal of noise from original multi-channel ECG waveforms. MSO technique is used for automatically finding out the cutoff frequency of multichannel ECG waveforms which is used in low-pass filtering process. The classification performance is discussed using mean squared error, member function, classification accuracy, complexity of design, and area under curve on MIT-BIH data. Additionally, this research work is extended for the samples of multi-channel ECG waveforms from the Scope diagnostic center, Hyderabad. Our study assets the best process using the Soft Computing methods for analysis of multi-channel ECG waveforms. Keywords: Multi-swarm optimization, Decision Trees,Logistic Model Trees and SVM with Particle Swarm Optimization (SVM-PSO).
I. Introduction
In recent days, human being has been suffered with heart diseases are more comparatively with olden days. Broad research is continuing for ECG waveform analysis to find the heart diseases. Still research needs to improve in area of classify the ECG waveforms based on dynamic environments of smart devices. An electrocardiogram (ECG) records electrical activity of the heart in time. The ECG waveform consists of P wave, QRS wave, T wave and U Wave. These are designated by capital letters. P, T and U Waves are rounded deflections with lower amplitude. Q, R and S waves are thin and sharp deflections. Basic unit of the ECG waveform is shown below Fig 1. The main parameters in ECG waveform are P wave, QRS complex, T wave and R-R interval. Based on these main parameters will suggest an illness of the heart. The entire irregular beat phases are commonly called arrhythmia and some arrhythmias are very dangerous for a patient. In these parameters, P represents considered to be upright, uniform, and round in a one-to-one ratio with QRS complexes. Next QRS complexes show the interval reflects the length of time the impulse takes to depolarize the ventricles. The T wave is usually upright in leads with an upright R wave, round and slightly asymmetrical with a more gradual slope on the first half of the wave than the second half of the wave and final parameter is R-R interval which is in between an R wave and the next R wave. Normal resting heart rate is in between 60 and 100 bpm. Normal ECG waveforms are generated using different number of leads. The most recent and weighted leads are 12, means 12 channel ECG waveforms [1]. A 12-lead ECG provides multiple electrical views of the heart along a frontal and a horizontal plane. The 12-lead ECG provides the most thorough ability to interpret electrical activity within the heart. In a 12-lead ECG, an electrode is placed on each upper arm and lower leg to monitor the standard leads (I, II, and III) and augmented leads (aVR, aVL, and aVF) along the frontal plane. In addition, chest leads may be used to evaluate the horizontal plane of electrical activity through assessment of V1 to V6.
RESEARCH ARTICLE OPEN ACCESS
2. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 42|P a g e
Figure 1: Basic Unit of the ECG Waveform The ECG waveform is usually corrupted with noise from various sources including imperfect contact of electrodes to the body, machine malfunction, electrical noise from elsewhere in the body, respiration and muscle contractions. ECG noise removal is complicated due to the time varying nature of ECG waveforms. In noise removal, it is necessary to identify the cutoff frequency of the filter. However, this is difficult to determine and improper treatment may introduce additional artifacts to the signal especially on the QRS wave. The important consideration of the popular technique is in automatically identifying the correct pass bands in the frequency spectrum using the intelligent methods. The intelligent methods are Artificial Neural Networks (ANN), Swarm Intelligence (SI) and Support Vector Machine (SVM) etc. An insufficient and incomplete research effort has been observed in the area of automated calculation of cutoff frequencies for noise removal using filters. Therefore, the incompleteness in this area has been the motivation factor to pursue the present research i.e. to find cutoff frequency using FIR filter with MSO (Multi-swarm optimization) methodology (Our paper reference). The next section provides a brief implementation description on FIR-MSO noise removal method [2] [3] [4].
Recent and current real time of the classification algorithms are Soft Computing algorithms. In that, most standard is decision trees in linear manner, next furthermost mixed classification method is a logistic model tree (LMT). It is a combination of logistic regression (LR) and decision tree learning. The Logistic Model Tree classifier was fed by the combination of linear and non-linear parameters derived from ECG Waveforms and greatest successfully classifier method is Support Vector Machine (SVM). Basic SVM method is most supported for binary classification. Recently SVM implemented for multi class classification problems. As per details from the WIKI, SVMs are also useful in many applications to classify with up to 90% of the compounds classified correctly. Many recent methods are used to extended SVM from binary classification to multi class classification problem, in that main popular methods are four: One Against One (OAO), One Against All (OAA), Fuzzy Decision Function (FDF) and Decision Directed Acyclic Graph (DDAG). And next hard step in SVM is feature selection. So many researchers used Principle Component Analysis (PCA) for identify feature selection in SVM process. PCA has some type of limitations at the time of multi-dimensional problems solutions. Find the best feature selection for multi-channel or multi- dimensional problems used Particle Swarm Optimization (PSO) and explained PSO in details development manner in next sections [5].
II. Back Ground
An ECG facilitates two major kinds of information; firstly, if the time intervals on the ECG waveform are measured, it helps in determining the duration of the electrical wave crossing the heart and consequently we can determine whether the electrical activity is normal or slow, fast or irregular. Secondly, if the amount of electrical activity passing through the heart muscle is measured, it enables apediatric cardiologist to find out the parts of the heart are too large or overworked [6] Physicians interpret the morphology of the ECG waveform and decide whether the heartbeat belongs to the normal sinus rhythm or to the class of arrhythmia. Many researchers analyzed and implemented different methods in Soft Computing algorithms for classify the ECG Waveforms. In that most popular and standard methods are Decision trees, Model trees, Logistic Regression and Support Vector Machines.
Most popular and standard methodology for classification of analysis is Decision Trees. Decision trees classifiers differ in the ways they partition the training sample into subsets and thus form sub-trees. That is, they differ in their criteria for evaluating splits into subsets. The See5 or C4.5 induction algorithm uses information theory to evaluate splits. CART uses Gini Index to split the training samples and some methods use Chi-Square measure. Many studies have been done comparing See5 decision tree algorithm with other classifiers and found that See5 based on the Information theory is more accurate and gives reliable results. The other advantage of See5 algorithm is that it can convert decision tree into corresponding classification rules. Rules are more comprehensive, easy to understand and easy to implement. As decision trees, a test on one of the attributes is associated with every inner node. Decision trees are not support regression
3. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 43|P a g e
functionality. Logistic Model Tree (LMT) is combination of logistic regression (LR) and decision tree learning.A LMT basically consists of a standard decision tree structure with logistic regression functions at the leaves, much like a model tree is a regression tree with regression functions at the leaves. Logistic model trees are based on the earlier idea of a model tree [7] [8]. SVM is a Soft Computing system developed by Dr. Vapnik (1995) in Bell Lab. Its basic concept is to construct the best super plane in sample space so that the margin between super plane and the sample set of different types will be a maximum. Particle Swarm Optimization is a candidate solution is a member of a set of possible solutions to a given problem. PSO is most popular method in part of Swarm intelligence (SI) algorithms. PSO studied in many multi feature identification problems in solution space. Below Fig 2 shows information of PSO particles movement to the best particle position using different particles position values [10] [11].
Figure 2: Sample PSO process with five Swarms
III. Proposed Methodology
Proposed methodology is shown below Fig 3. Major process divided into four steps:
The initial step is noise removal process of the ECG channel using with new methodology(MSO FIR Filter).
Next followed Feature Extraction and Reduction.
Analyze the current research trends in Soft Computing Algorithms and implement the following methodologies for classify the 12- channel ECG waveforms with analysis and results. Decision Tree Classifier, Logistic Model Tree Classifier and SVM Classification with Particle Swarm Optimization (SVM-PSO).
Final Step is results accuracy analysis.
In this paper, demonstrate best process for multi- channel ECG Waveforms classification using novel MSO-FIR and with best Soft Computing Algorithms.
Figure 3: Process of the Proposed Methodology Architecture. 3.1 Test Data In this Research, data is collected from three centers: PTB Diagnostic ECG Database: This database contains 549 records from 290 subjects. Each subject is represented by one to five records. Each record includes 15 simultaneously measured signals. Each signal is digitized at 1000 samples per second, with 16 bit resolution over a range of ± 16.384 mV. St.-Petersburg Institute of Cardio logical Technics 12-lead Arrhythmia Database: This database contains 75 twelve-lead ECGs from 32 Holter records. Each record is 30 minutes long and contains 12 standard leads, each sampled at 257 Hz, with gains varying from 250 to 1100 analog-to-digital converter units per mill volt. PhysioNet/Computing in Cardiology Challenge 2011: This database contains 1500 twelve-lead ECGs. These ECGs have been classified individually with respect to acceptability for purposes of diagnostic interpretation.
4. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 44|P a g e
Table 1: Extract Features Descriptions
An MSO and Soft Computing algorithm needs some inputs - derived from 22 features of the test data sets. For each signal 22 temporal features such as R-R interval, PQ interval, PR interval, and PT interval and threemorphological features are recognized. These features aremanually extracted for each beat and put into a separatevector. Each vector is tagged with one the four possiblelabels N, P, LB, RB.Features have been extracted including the time and voltageof Q/R/S/T/P and time interval for each of 5 features fromthe next feature such as RS/ ST/ QR also the difference of voltage in these featuressuch as V(Q)-V(S). Another feature that have considered isthe time and voltage of RR. The description of the featureshas summarized in Table 2. X(R) means the position of R inthe ECG signal and V(R) means the value of that position inthe signal.MSO methodology needs more inputs for each data set point and in this paper included new interval feature compare with existing research scope. In addition, some of the standard attributes like mean and median are considered. Another additional feature is Form Factor (FF). Form factor (FF) is another technique to represent ECG waveform complexity in a scalar value. All above features are used to find the cutoff frequency using MSO methodology. Same set of the features are derived from the after Noise removal Waveform (Clean ECG Waveform) for Soft Computing algorithms learning. List of the features is shown above Table 1. 3.2 Multi Swarm Optimization FIR Filter
MSO is a technique for estimating the solution to difficult or impossible numerical problems. Itis an alternative of particle swarm optimization (PSO) based on the use of multiple sub-swarms instead of one (standard) swarm. The general approach in multi- swarm optimization is that each sub-swarm focuses on a specific region while a specific diversification method decides where and when to launch the sub- swarms. The multi-swarm framework is especially fitted for the optimization on multi-modal problems [12]. The particles or inputs of the Multi-swarm optimization are determined by the features of the dataset. MSO Particles bases its diversification mechanism on the “collision” of particles. When particles get too close, a repulsive force expels the particles into new waves/sub-swarms, and this avoids a complete convergence. A key feature of the new sub-swarms is that their initial positions are not randomly selected as in normal swarms. Instead, they maintain some information from the previous trajectories of the particles. A similar relationship exists with initial velocities. This multi- swarm system bases its diversification mechanism on a “devour and move on” strategy. Once a sub-swarm has devoured a region (intensive search) the swarm is ready to move on to another promising region. The initial positions of the new sub-swarm are selected using a scouting process around the best position found by the previous sub-swarm [13]. With fewer iterations per particle, it may be beneficial to increase the convergence rate of the sub- swarms (i.e. decrease the constriction factor). In standard PSO [1]the velocitiesof each particle are updated by 푣 푑 =푥 푣 푑 +푐 1∈ 1 푝푏푒푠푡 푑 −푥 푑 +푐 2∈ 2 푔푏푒푠푡 푑 − 푥 푑 (1) In (1), Vis the particle’s velocity; xis the position of the particle, and푑isa given dimension. The variables ∈1and∈2are random values, which togetherwith the weights푐1and 푐2determinethe contribution of attractions to thepersonalandglobal bests푝푏푒푠푡푑 and푔푏푒푠푡푑respectively. The constriction factor is represented by푥, thespecific value used for the constriction factor in is 푥= 0.792.By changing the value of this parameter, it is possible to modify theparticle’s momentum, and therefore to either promote a more exploratory or amore exploitative behavior.
The impulse response of an Nth-order discrete- time FIR filter lasts for N + 1 samples, and then settles to zero. Higher orders give sharper cutoff in thefrequency response therefore; the desired sharpness willdetermine the filtering order. The default window is theHamming of size N +1. The FIR filter (w) is representedby
Feature No.
Description
Feature No.
Description
1
X(R1)
13
X(R2)
2
V(R1)
14
V(R2)
3
X(S)
15
X(R2)- X(R1)
4
V(S)
16
V(R2)- V(R1)
5
X(T)
17
X(S)- X(R1)
6
V(T)
18
X(T)-X(S)
7
X(P)
19
X(P)-X(T)
8
V(P)
20
X(Q)-X(P)
9
X(Q)
21
X(R2)- X(Q)
10
V(Q)
22
Median
11
Standard Deviation
23
Form Factor
12
Mean
24
Average of intervals
5. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 45|P a g e
푤푛=0.54−0.46cos 2휋푛 푁 for0≤n≤N(2) The cutoff frequency must be identified for the ECG signal tobe filtered. The next sectionprovides the test results achievedfor automatic identification of the cutoff frequency by theMSONN and the FIR filter in denoising the ECG signals. 3.3 Decision Tree Classifier Decision tree is non parametric classifier. Decision tree is an example of Soft Computing algorithm. It is a predictive model most often used for classification. It is based on the “divide and conquer” strategy. Decision trees partition the input space into cells where each cell belongs to one class.For any subset S of X, where X is the population, let freq(ji,S) be the number of objects in S, which belongs to class i. 퐼푛푓표 푠 =−푙표푔2(퐹푟푒푞(퐶푗푆)/|푠|) (3)
When applied to a set of training objects, Info(T) gives the average amount of information needed to identify the object of a class in T. This amount is also known as the entropy of the set T. Consider a similar measurement after T has been partitioned in accordance with the n outcomes of a test X. The expected information requirement can be found as a weighted sum over the subsets {Ti}: Info푥 푇 = | 푇푖| 푇 .퐼푛푓표 푇푖 (4) 푛 푖=1 푇푕푒푞푢푎푛푡푖푡푦푔푎푖푛 푋 =푖푛푓표 푇 −푖푛푓표푋 푇 (5) Measures the information that is gained by partitioning T in accordance with the test X. The gain criterion selects a test to maximize this information gain. The gain criterion has one significant disadvantage in that it is biased towards tests with many outcomes. The gain ratio criterion (Quinlan, 1993) was developed to avoid this bias [11]. The information generated by dividing T into n subsets is given by Split Info(X)=± 푇푖 푇 .푙표푔2 푇푖 푇 (6) 푛 푖=1 The proportion of information generated by the split that is useful for classification is [14] 퐺푎푖푛푟푎푡푖표푛= 푔푎푖푛 푋 푠푝푙푖푡푖푛푓표(푋) (7)
If the split is near trivial, split information will be small and this ratio will be unstable. Hence, the gain ratio criterion selects a test to maximize the gain ratio subject to the constraint that the information gain is large.Stratified random sampling methods were used to collect separate training and test data sets in the study area using ECG data and reference data generated from different research data centers (Data details are specified in section 3.1).ECG waveforms datawith 24 feature collected by random sampling were divided into two subsets, one of which was used for training and the other for testing the classifiers, so as to remove any bias resulting from the use of the same set of sample for both training and testing. Using the training set samples created above, the classifier was built in the form of a decision tree. Fig 4 shows the decision tree generated using See5 algorithm.
Figure 4: Output of Decision Tree 3.4 Logistic Model Tree Classifier Logistic Model Tree is a combination of tree structure and logistic regression functions to produce a single decision tree. The decision tree structure has the logistic regression functions at the leaves.The leaf node has two child nodes which is branched rightand left depending on the threshold. If the value of the attribute is smaller than the threshold it is sorted to left branch and value of attribute greater than the threshold it is sorted to right branch. The threshold is usually fixed by Logit Boost method. Logit Boost uses an ensemble of functions FK to predict classes 1. . . K using M “weak learners”. Steps followed for developing the LMT classifier:
The linear regression function is fitted using the Logit Boost method to build a logistic model tree. The Logit Boost method uses 5 steps for the cross validation to determine the best number of iterations to run, when fitting the logistic regression function at a node of the decision tree.
The logistic model is built using all data.
The split of the data at the root is constructed using the threshold.
This splitting is continued till some stopping criterion is met. Here the stopping criterion helps in cross validation for logit Boost method.
Once the tree has been build it is pruned using CART-based pruning.
Reasons for choosing the Logistic Model Tree classifier:
Logistic Regression is very good at detecting linear relationships and then combining those relationships into an equation that provides the
6. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 46|P a g e
odds of the dependent variable reaching a particular outcome, when the various independent variables are fed into the resulting equation.
Logistic Regression models are widely used and they are considered robust and not prone to over fitting the data.
These models can be built with high level of accuracy using little data preparation.
Logistic Model Trees give explicit class probability estimates rather than just a classification.
3.5 SVM Classification with PSO Support Vector Machines are based on the concept of decision planes that define decision boundaries.Support Vector Machine (SVM) is primarily a classifier method that performs classification tasks by constructing hyper planes in a multidimensional space that separates cases of different class labels. SVM supports both regression and classification tasks and can handle multiple continuous and categorical variables.There are number of kernels that can be used in Support Vector Machines models. Still many issues with kernel functions for identify the feature selection process. This paper introduce Particle Swarm Optimization(PSO) for identify features in best way compare with existing solutions and newly introduced PSO for identifying feature attributes in multi-channel ECG waveform sector. PSO is used to serve as feature selection for classification problems. It helps to improve the performance owing to its smaller number of simple parameter settings. In PSO, the potential solutions, called particles, fly through the problem Space by following the current optimum particles. Each particle keeps track of its coordinates in the problem space which are associated with the best solution (fitness) it has achieved so far. This is called the pbest. Another “best” value that is tracked by the particle swarm optimizer is the best value, obtained so far by any particle in the neighbors or the particle. This location is called lbest, when a particle takes all the population as its topological neighbors, the best value is a global best and is called gbest.The particle swarm optimization concept consists of, at each time step, changing the velocity of (accelerating) each particle towards its pbest and lbest locations. Acceleration is weighted by a random term, with separate random numbers being generated for acceleration towardspbest and lbest locations. Following figure 5 shows algorithm steps of PSO methodology to find the best feature values [.
Currently there are two types of approaches for multiclass SVM. One is by constructing and combining several binary classifiers while the other is by directly considering all data in one optimization formulation. The formulation to solve multiclass SVM problems in one step has variables proportional to the number of classes. Therefore, for multiclass SVM methods, either several binary classifiers have to be constructed or a larger optimization problem is needed. Hence in general it is computationally more expensive to solve a multiclass problem than a binary problem with the same number of data. There are four methods for multiclass classification based on binary classification: One Against One (OAO), One Against All (OAA), Fuzzy Decision Function (FDF) and Decision Directed Acyclic Graph (DDAG). Assume S={(푥1,푦1),(푥2,푦2), 푥3,푦3 ,……(푥푖,푦푖)} is a training set, where푥푖∈푅푚and 푦푖∈(1,2,….푘). For the One Against-One method, one needs to determine 푘 (푘−1)/2classifiers for the 푘−classes problems. The optimal hyperplane with SVMs for class 푖 against class 푗 is 퐷푖푗 푥 =푤푖푗푇 Ǿ 푥 +푏푖푗=0 푖<푗,1<푗≤푘,1≤ 푖<푘 (8) WherewijTa vector in the feature space, ∅(x) is mapping function, and bijis a scalar. Here the orientation of the optimal hyper plane is defined as per the following equation: 퐷푖푗 푥 =−퐷푗푖(푥) (9) SVM. Compare with above four methods, OAA method shows best results for classify the ECG waveforms [20].
Figure 5: PSO Algorithms steps Feature selection is selecting a subset of the weighted features from training set, using this feature set in classification. Feature selection process is more advantages in classification analysis mainly:
First, it makes training and applying a classifier more efficient by decreasing the size of the effective features.
7. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 47|P a g e
Second, feature selection often increases
classification accuracy by eliminating noisy
features. A noisy feature is one that when added to the document representation, increases the classification error on new data.
One of top most approach for feature selection is Principle Component Analysis (PCA),PCA is performance is poor for multi-channel or high dimensional channels. In this research mainly used multi-channel ECG waveforms, so PCA is not sufficient to find the right feature attributes. In process of the feature identification selected as best methodology is PSO for multi-channel in this research. In this research proposed PSO methodology in part SVM feature selection process for Multi- Channel ECG waveform classification.
IV. Accuracy Assessments
Three different data set sources are used which are specified in section 3.1andfor additionalperformance analysis purpose, tested for real time data sets from Scope diagnostic center, Hyderabad. Total data classified as 8 Arrhythmia Classes with 2324 instances for all data sets. Each instance has 24 attribute values. Each instance has categorize one of the below 8 classes.Following table 2 shows all details about data instance and class information.
Class
Class Name
No of Instances
1
Left Bundle Branch Block
276
2
Normal Sinus Rhythm
420
3
Pre-ventricular Contraction
295
4
Atrial Fibrillation
220
5
Ventricular Fibrillation
280
6
Complete Heart Block
297
7
Ischemic Dilated Cardiomyopathy
256
8
Sick Sinus Syndrome
280
Table 2: Tested data Arrhythmia Classes and each Class No of Instances Consider above instance records with different data sets as train data and test data for each analysis cycle is shown below table 3. Accuracy tested for following methods with above Analysis Cycle data instances:
Decision Trees- C 4.5 algorithm (DTC)
Logistic Model Trees (LMT)
SVM-PSO with OAA multi class method (SVM-PSO)
Overall Accuracy is shown below Figure 6 for all proposed methods. Our research is demonstrated comparatively existing and old methods, our proposed SVM-PSO explore more accuracy in Multi- channel ECG Waveform Classifications. This research done for different test cycles for different data, always attest SVM-PSO is best classification accuracy in all circumstances. Our research is analyzed in point of classes wise also, below Figure 7 shows accuracy details about of the each class for different analysis cycles in depth of proposed methods, here research confirmed is for all time with SVM-PSO process is classified with pinnacle accuracy. And additional analyzed in increasing manner of the Test Data samples and decreasing manner of Train Data sets, here research successfully shows SVM- PSO method is near variance compare with other research methods, which is very clear in Figures 6 and 7.
Analysis 1
Analysis 2
Analysis 3
Class
Class Name
No of Instances
Train Data
Test Data
Train Data
Test Data
Train Data
Test Data
1
Left Bundle Branch Block
276
248
28
221
55
193
83
2
Normal Sinus Rhythm
420
378
42
336
84
294
126
3
Pre-ventricular Contraction
295
266
29
236
59
207
88
4
Atrial Fibrillation
220
198
22
176
44
154
66
5
Ventricular Fibrillation
280
252
28
224
56
196
84
6
Complete Heart Block
297
267
30
238
59
208
89
7
Ischemic Dilated Cardiomyopathy
256
230
26
205
51
179
77
8
Sick Sinus Syndrome
280
252
28
224
56
196
84
Table 3: Train and Test Data Table for Testing Analysis
8. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 48|P a g e
Figure 6: Overall Accuracy for all Analysis Cycles for Tested Models
Figure 7: Class wise Accuracy for Tested methods and Analysis Cycles
V. CONCLUSIONS
This paper exhibits classification of 12- Channel ECG Waveforms datasets with various popular Soft Computing methodologies. Initially it is used for noise removal methodology; also most recent new methodologies are introduced by ours in different part of the research. Next steps of research are used for soft computing methods on clear 12 Channel ECG Waveforms. In this research, applied different well known methodologies newly introduced in area of 12 Channel ECG waveform Classification and those methods are Decision Trees – C4.5, Logistic Model Tress and SVM-PSO with multi class OAA method. In part of accuracy analysis, collected data from different research sources and additionally consider different data set samples for training the methods from collected data. Finally, accuracy assessment of the methods with some random samples which are not used in part of the trained data samples. Found best process and methodology for classify the Multi-Channel ECG Waveforms. SVM- PSO is zenith classifier accuracy comparatively with most benchmark soft computing methods for large and small data samples. This research results is provide evidence for SVM –PSO method is best for classifier for classification Multi-Channel ECG Waveforms. SVM-PSO future extended used for any multi dimension class problem in different application areas. References
[1]. Jenkins,Peggy, “Nurse to Nurse ECG Interpretation” McGraw-Hill Professional, Published in 2009.
[2]. Menta Srinivasulu, K. Chennakeshava Reddy “Novel Method To Find The Parameter For Noise Removal From Multi- Channel ECG Waveforms” IJRET, Volume: 03 Issue: 02, 2014 PP 395-401.
[3]. GintautasGarsva, PauliusDanenas“Particle Swarm Optimization For Linear Support VectorMachines Based Classifier Selection” Nonlinear Analysis: Modelling and Control, 2014, Vol. 19, No. 1 PP 26–42.
[4]. Bhumika Chandrakar1, O.P.Yadav2, V.K.Chandra, “ASurvey Of Noise Removal Techniques For ECG Signals”International Journal of Advanced Research inComputerand Communication
70
75
80
85
90
95
100
DTC
LMT
SVM-PSO
Analysis 1
Analysis 2
Analysis 3
0
50
100
150
DTC
LMT
SVM-PSO
DTC
LMT
SVM-PSO
DTC
LMT
SVM-PSO
Analysis 1
Analysis 2
Analysis 3
Sick Sinus Syndrome
Ischemic Dilated Cardiomyopathy
Complete Heart Block
Ventricular Fibrillation
Atrial Fibrillation
9. Menta Srinivasulu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 7( Version 4), July 2014, pp.41-49
www.ijera.com 49|P a g e
Engineering Vol. 2,Issue 3, March 2013, pp, 1354-1357.
[5]. Jukka A Lipponen, Mika P Tarvainen “AdvancedMaternal ECG Removal and Noise Reduction forApplication of Fetal QRS Detection” Computing inCardiology 2013 PP. 161-164.
[6]. ManpreetKaur, Birmohan Singh, Seema “Comparisonsof Different Approaches for Removal ofBaselineWanderfrom ECG Sign” International Journal of ComputerApplications 2011 pp, 32-36.
[7]. V´ıctorBarbero Romero, Professor director: DavidAtienza Alonso, Professoracolaboradora: Nadia Khaled,UC3M, “ECG baseline wander removal and noisesuppression analysis in an embedded platform”International Conference of Curso 2008-2009.
[8]. Sara Moein, RajasvaranLogeswaran and KhazaimatolShimaSubari “An Automated Intelligent Approach forECG Signal Noise Removal” International Journal ofComputer Science Issues 2012.
[9]. Hassoun M.H., “Fundamentals of Artificial NeuralNetwork”, MIT 1995.
[10]. Minami K., Nakajima H., Toyoshima T., “Real-timediscrimination of ventricular tachyarrhythmiawithFourier transform neural network”, IEEE, 1999.
[11]. Jalal A. Nasiri, Mahmoud Naghibzadeh,“ECGArrhythmia Classification with Support VectorMachines and Genetic Algorithm” IEEE 2009 ThirdUKSim European Symposium on Computer Modelingand Simulation pp 187- 192.
[12]. Omran, M. G., Salman, A., &Engelbrecht, “ParticleSwarm Optimization forPattern Recognition and ImageProcessing”. Springer 2008.
[13]. Sara Moein, RajasvaranLogeswaran, “Intelligent ECGSignal Noise Removal using PSONN” InternationalJournal of Computer Applications’ (0975 – 8887)Volume 45– No.6, May 2012.
[14]. Junliang Li, Xinping Xiao “Multi- Swarm and Multi-Best Particle Swarm Optimization Algorithm” IEEE2008 PP 6281 – 6286.
[15]. Zhao, Liang.J.J, Suganthan .P.N,”Dynamic Multi-SwarmParticle Swarm Optimizer with Local Search for LargeScale Global Optimization” IEEE Congress onEvolutionary Computation 2008, pp. 3845-3852.
[16]. Kim J., Shin H.S., Shin K., and Lee M. Robust Algorithm for Arrhythmia Classification in ECG Using Extreme
LearningMachine, Biomedical Engineering OnLine 2009., pp. 31-42.
[17]. Liu B., Hao Z., and Tsang E.C.C. Nesting One-Against-One Algorithm based on SVM’s for Pattern Classification, IEEE Transactions on Neural Networks, 2008 Volume 19, pp. 2044-2052.
[18]. X. Wang. Corporate financial warning model based on PSO and SVM, 2nd International Conference on Information Engineering and Computer Science (ICIECS-2010).
[19]. J. Kennedy, R.C. Eberhart, Y. Shi, Swarm Intelligence, Morgan Kaufmann Publishers, 2001.
[20]. NarendraKohli, Nishchal K. Verma “Arrhythmia classification using SVM with selected features” International Journal of Engineering, Science and TechnologyVol. 3, No. 8, 2011, PP 122-131.
BIOGRAPHIES:
Prof. M.Srinivasulu, received his B.Tech Degree in Electronics & Communication Engineering andM.Tech degree in Electronic Instrumentation & Communication Systems from S V University- Tirupati. A.P-India. He is currently working as Professor in the Department of ECE in LAQSHYA INSTITUTE OF TECHNOLOGY & SCIENCES, Khammam, A.P-India. His research interests on Signal Processing. He is a Member of IEEE, Member of Institution of Engineers (MIE) and Member of Indian Society for Technical Education (MISTE).
Dr.K.CHENNAKESHAVA REDDY is the Principal, Bharathi Engineering College and Professor of Electronics & Communication Engineering. He did his B.E. &M.Tech. fromRegional Engineering College,Warangal and Ph.D. from JNTU-Hyderabad. He was the former Director of Evolution –JNTUH, Principal of JNTU – Jagityaland Deputy Director of UGC-Academic Staff College –JNTUH.He was an expert committee member constituted by AICTE, South Western region, Bangalore. He Published 20-International, 50- National Research papers in various international & National Journals. He also guided 16 Ph.D. Research scholars.