ECG Signal processing

Sleep is a naturally life style of the zoological species like human, animals, birds, mammals, Reptiles etc. The some species sleep time eye is open & mostly eye is closed. Different-different species sleeping time is dissimilar. The human sleep timing is dissimilar to born to older adults. Sleep is not functioning properly i.e. many disease is generated i.e. Blood pressure & other sleep disorder. Sleep is measured in different-different signal i.e. EEG, EOG, EMG signal. The stages of sleep are measuring α wave, Ɵ wave, delta wave. Stages of sleep are basically in two part Non REM and REM stages.

This paper aims to analyze the heart electrocardiograph (ECG) to diagnose the heart performance and predict any future complications. The authors utilize the MIT BIH database to obtain the original data. The discrete wavelet transform (DWT) is used to decompose the ECG signal and to reconstruct it. The means of different performance measures of the heart performance (QRS,RR,ST,QT,PR) are tested for their significance before comparing them to the limits of normal performance. Any abnormal measure is used to diagnose the corresponding disease(s). Prediction techniques are used to expect any future complications regarding the abnormal measure(s). Two methods of prediction are applied: the Linear Prediction Method (LPM) and the Grid Partitioning and Fuzzy c-mean Clustering based on Neuro-Fuzzy prediction.

The computer-assisted analysis of biomedical records has become an essential tool in clinical settings. However, current devices provide a growing amount of data that often exceeds the processing capacity of normal computers. As this amount of information rises, new demands for more efficient data extracting methods appear. This paper addresses the task of data mining in physiological records using a feature selection scheme. An unsupervised method based on relevance analysis is described. This scheme uses a least-squares optimization of the input feature matrix in a single iteration. The output of the algorithm is a feature weighting vector. The performance of the method was assessed using a heartbeat clustering test on real ECG records. The quantitative cluster validity measures yielded a correctly classified heartbeat rate of 98.69% (specificity), 85.88% (sensitivity) and 95.04% (general clustering performance), which is even higher than the performance achieved by other similar ECG clustering studies. The number of features was reduced on average from 100 to 18, and the temporal cost was a 43% lower than in previous ECG clustering schemes.

Signal Processing could be stated as a science that enhances our ability to communicate, understand and share the data, thus helping us extract this information for effective studies. Not being able to access a comprehensible format data could turn out to be the breaking point for a key factor or a principal research. This following paper proposes specific algorithms or rather techniques on how to convert such incomprehensive data into a comprehensive fact using four different formats with an accuracy of 99.99%. One such signal chosen for reference here is Electrocardiogram (ECG) and the plotting and processing have been implemented using MATLAB. We have specifically chosen Lead-II ECG Configuration for our research work. This technique is applicable for any real-time general waveform that exists in these specific formats as discussed in the paper.

The paper introduces a viable short range signal triangulation method, which will enable users to identify and monitor animals in a given area. “Zig-bee- Zig bee pairs” are used as a more precise and a relatively long-lasting alternative to the traditional radio collars. Additionally, the collar itself ‘broadcasts’ the animal’s current state (EEG, ECG , EMG) and can trigger an S.O.S signal in case of an emergency. Allowing authorities to react to certain cases where the animal might be in critical danger (for rescue) and also allow end users to map certain behavioral patterns in animals.

Objective: Several different measures of heart rate variability, and particularly of respiratory sinus arrhythmia, are widely used in research and clinical applications. For many purposes it is important to know which features of heart rate variability are directly related to respiration and which are caused by other aspects of cardiac dynamics.
Approach: Inspired by ideas from the theory of coupled oscillators, we use simultaneous measurements of respiratory and cardiac activity to perform a nonlinear disentanglement of the heart rate variability into the respiratory-related component and the rest.
Main results: The theoretical consideration is illustrated by the analysis of 25 data sets from healthy subjects. In all cases we show how the disentanglement is manifested in the different measures of heart rate variability.
Significance: The suggested technique can be exploited as a universal preprocessing tool, both for the analysis of respiratory influence on the heart rate and in cases when effects of other factors on the heart rate variability are in focus.

This article presents an innovative research methodology that enables the efficient classification of cardiac disorders (17 classes) based on ECG signal analysis and an evolutionary-neural system.

From a social point of view, it is extremely important to prevent heart diseases, which are the most common cause of death worldwide. According to statistical data, 50 million people are at risk for cardiac diseases worldwide. The subject of ECG signal analysis is very popular. However, due to the great difficulty of the task undertaken, and high computational complexity of existing methods, there remains substantial work to perform.

This research collected 1000 fragments of ECG signals from the MIH-BIH Arrhythmia database for one lead, MLII, from 45 patients. An original methodology that consisted of the analysis of longer (10-s) fragments of the ECG signal was used (an average of 13 times less classifications). To enhance the characteristic features of the ECG signal, the spectral power density was estimated (using Welch’s method and a discrete Fourier transform). Genetic optimization of parameters and genetic selection of features were tested. Pre-processing, normalization, feature extraction and selection, cross-validation and machine learning algorithms (SVM, kNN, PNN, and RBFNN) were used.

The best evolutionary-neural system, based on the SVM classifier, obtained a recognition sensitivity of 17 myocardium dysfunctions at a level of 90.20% (98 errors per 1000 classifications, accuracy = 98.85%, specificity = 99.39%, time for classification of one sample = 0.0023 [s]). Against the background of the current scientific literature, these results are some of the best results to date.

Electrocardiogram (ECG) is commonly used in medical field in order to diagnose different cardiovascular diseases and patient's general health. ECG Signal are often affected by artifacts from the environment including baseline wander, power line interference and electromyographic (EMG) noise. In this project, ECG Signal to be processed is collected from MIT/BIH (Massachusetts Institute of Technology-Beth Israel Hospital) Arrythmia Database [1]. This method is being tested on one dataset only and serves as a beginner guide to digital signal processing with MATLAB for an affordable, precise, and portable Electrocardiogram device that may be used at underserved hospitals. With MATLAB, to remove the baseline wander, Detrend function can be used to remove low frequency below 0.5 Hz. Powerline interference (50 Hz or 60 Hz) can be filtered out by using bandstop IIR filter. EMG and high frequency noise can be reduced by using IIR low-pass filter to cut off high frequency signal. The resulting signal is filtered out successfully with less noise and P wave, QRS complex, T wave can be inferred properly.

The calibration process performed on ECG (Electrocardiography) and other devices that
measure the vital signals of these devices are done by devices which are called ECG
simulators. By connecting electrodes of the device to simulator device, the desired signal
types can be simulated. By using this simulator, it is possible to calibrate and fix a lot of
devices, and also it is possible to control the functions, the signal alarms and the cable
connections of the devices.
FPGA (Field Programmable Gate Array) is a digital integrated circuit that has the feature of
reprogrammability. After the production, the hardware structure of FPGA can be changed by
the user/designer according to the desired function. Compared to the other platforms, parallel
processing, fast production and high performance are the distinctive features of FPGAs.
In this study, the ECG signal is mathematically modeled using the Matlab program and then
designed and implemented to work on FPGA chips using the VHDL (Very High-Speed
Integrated Circuit Hardware Description Language) and the Xilinx-Vivado program. Matlab
based ECG signal was accepted as a reference and statistically compared with the results
obtained from FPGA-based studies and a value of 10E-02 MSE (Mean Square Error) was
obtained. With this study, it has been shown that FPGA-based ECG signal generation system
can be designed using FPGA chips and can be safely used in biomedical applications.

In this paper, we present a new complex electronic system for facilitating communication with severely disabled patients and telemonitoring their physiological parameters. The proposed assistive system includes three subsystems (Patient, Server, and Caretaker) connected to each other via the Internet. The two-way communication function is based on keywords technology using a WEB application implemented at the server level, and the application is accessed remotely from the patient’s laptop/tablet PC. The patient’s needs can be detected by using different switch-type sensors that are adapted to the patient’s physical condition or by using eye-tracking interfaces. The telemonitoring function is based on a wearable wireless sensor network, organized around the Internet of Things concept, and the sensors acquire different physiological parameters of the patients according to their needs. The mobile Caretaker device is represented by a Smartphone, which uses an Android application for communicating with patients and performing real-time monitoring of their physiological parameters.

Electrocardiography (ECG) is a form of physiological data used to record the electrical activity of the heart. Numerous researchers have proposed and developed methods to extract features from the ECG signal (for example, R-R segment, P-R segment). These features can be used to analyse and classify various forms of heart arrhythmia. In this work, a method for ECG classification that employs a generalised signal pre-processing technique and uses a Multi-Layer Perceptron network to classify arrhythmia per the AAMI EC57 standard accurately is presented. The method is trained and evaluated using PhysioNet's MIT-BIH dataset, and an average accuracy of 98.72% is achieved. The proposed methodology is comparable to state-of-the-art CNN models, both in terms of accuracy and efficiency.

A graphical representation of the electrical signals generated during the heart activity could be termed as Electrocardiogram (ECG). Analysis of ECG by identifying the various features and traits could help us detect the normal and pathological physiology of the heart, thus providing valuable information about the activity of the human heart. Automatic classification of ECG has evolved as an emerging tool in medical diagnosis for effective treatments. In this paper, a real time algorithm for detection of QRS Complex and its duration has been developed. Also, the work proposed in this paper reviews and summarizes the various techniques used by researchers in order to detect and delineate QRS Complex. ECG signals in this work are collected from MIT-BIH database and it has been implemented using MATLAB routine consisting of four different databases formats. The processing of the data was done on the Lead-II ECG signals.

El presente artículo tiene como objetivo implementar filtros digitales en señales electrocardiográficas a través de un microcontrolador portable de bajo costo. En este trabajo se utilizan bloques de Simulink de procesamiento de señales que serán embebidos en un microcontrolador DSPic, utilizando la herramienta Mplab Device Blocks for Simulink

La señal electrocardiográfica (ECG) es susceptible a diversas fuentes de ruido que distorsionan la señal y afectan el análisis auto-mático llevado a cabo por los dispositivos de monitoreo cardiaco, lo que podría conducir a decisiones médicas que pueden com-prometer la salud de un paciente. El desplazamiento de la línea de base del ECG es un ruido de baja frecuencia (<1 Hz) que afecta considerablemente la identificación automática del inicio y fin de las ondas que componen el ECG, los cuales permiten identificar las fases de despolarización y repolarización de las aurículas y los ventrículos. Varios enfoques han sido propuestos en la literatura para reducir esta interferencia, sin comprometer la integridad de las ondas del ECG. En este trabajo se analiza el desempeño de dos tipos de filtro pasa alto, uno de repuesta finita al impulso (FIR) y otro de respuesta infinita al impulso (IIR), con diferentes valores del orden del filtro, sobre diez registros ECG adquiridos a 360 Hz de la base de datos MIT-BIH de Physionet. Tres indicadores de desem-peño son utilizados para analizar la señal filtrada (sin desplazamiento de la línea de base): la reducción de la potencia de la señal filtrada en la banda de rechazo del filtro, la distorsión de la señal filtrada en la banda de paso del filtro y el tiempo de respuesta del filtro. Los resultados obtenidos muestran que para los valores óptimos obtenidos del orden de los filtros, en comparación con el filtro FIR, el filtro IIR atenúa mejor el ruido (2,25 vs 84,35 x10-6 V-2), a una velocidad de respuesta mayor (10,43 vs 202,05 ms), pero con una mayor distorsión en la banda de paso del filtro (234,76 vs 134,63 x10-6 V-2). No obstante, dado que el filtro FIR tiene una respuesta de fase lineal, lo que implica un retardo de grupo constante para todas las frecuencias, es preferible utilizar un filtro FIR para eliminar el desplazamiento de la línea de base del ECG, a pesar de implicar un orden mucho mayor para cumplir con las especificaciones técnicas del filtro. Abstract The electrocardiographic (ECG) signal is susceptible to various sources of noise that distort the signal and affect the automatic analysis carried out by cardiac monitoring devices, which could lead to medical decisions that may compromise the health of a patient. The baseline wander in the ECG is a low frequency noise (<1 Hz) that considerably affects the automatic identification of the beginning and end of the ECG waves, which allows the identification of atrial and ventricular depolarization and repolarization phases. Several approaches have been proposed in the literature to reduce this interference, without compromising the integrity of ECG waves. In this work, the performance of two high pass filters, a finite impulse response (FIR) and an infinite impulse response (IIR), is analyzed for different filter order, on ten ECG records acquired at 360 Hz from the Physionet's MIT-BIH. Three performance indicators are used to analyze the filtered signal (without baseline wander): the power reduction of the filtered signal in the rejection band of the filter, the distortion of the filtered signal in the pass band of the filter and the time of the filter response. Results show that, for the optimum values of the filter orders, in comparison with the FIR filter, the IIR filter attenuates the noise better (2,25 vs 84,35 x10-6 V-2), with a faster response (10.43 vs 202.05 ms), but with a greater distortion in the passband of the filter (234,76 vs 134,63 x10-6 V-2). However, since the FIR filter has a linear phase response, which implies a constant group delay in all frequencies, it is preferable to use an FIR filter to remove the baseline wandering in the ECG, despite involving a much larger order to meet the technical filter requirements.

An Electrocardiogram (ECG) is defined as a test that is performed on the heart to detect any abnormalities in the cardiac cycle. Automatic classification of ECG has evolved as an emerging tool in medical diagnosis for effective treatments. The work proposed in this paper has been implemented using MATLAB. In this paper, we have proposed an efficient method to classify the ECG into normal and abnormal as well as classify the various abnormalities. To brief it, after the collection and filtering the ECG signal, morphological and dynamic features from the signal were obtained which was followed by two step classification method based on the traits and characteristic evaluation. ECG signals in this work are collected from MIT-BIH, AHA, ESC, UCI databases. In addition to this, this paper also provides a comparative study of various methods proposed via different techniques. The proposed technique used helped us process, analyze and classify the ECG signals with an accuracy of 97% and with good convenience.

Wearable sensors are widely adopted for the provision of healthcare services. Unfortunately the noise always degrades the quality of the acquired signals. In this paper, we propose a framework for mobile ECG denoising, based on a novel numerical scheme with low computational requirements. The proposed system is able to store a signal from a wearable sensor and process it in a remote way or directly on the device.

Wearable sensors are widely adopted for the provision of healthcare services. Unfortunately the noise always degrades the quality of the acquired signals. In this paper, we propose a framework for mobile ECG denoising, based on a novel numerical scheme with low computational requirements. The proposed system is able to store a signal from a wearable sensor and process it in a remote way or directly on the device.

Signal & Image Processing : An International Journal is an Open Access peer-reviewed journal intended for researchers from academia and industry, who are active in the multidisciplinary field of signal & image processing. The scope of the journal covers all theoretical and practical aspects of the Digital Signal Processing & Image processing, from basic research to development of application.

Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Signal & Image processing.

Human heart being the electro-mechanical pump supplies blood via a cardiovascular network. Its rhythmic beating gives rise to a pattern which when recorded can be used to find out the functionality of a heart. The diagnostic tool is called as Electrocardiogram (ECG) and its tracing contains a lot of attributes whose proper analysis may detect any cardiac peculiarity. Among them, is an entity called as the beat-to-beat interval (R-R interval). The analysis of beat to beat fluctuations of heart rate is known as heart rate variability (HRV) which is a concise marker to study the health of the heart along with a lot of measures clinically. This paper talks about the importance of the HRV and the various processing yet analysis techniques used to calculate the HRV by researchers.

An electrocardiogram (ECG) is a simple test that is used to check one's heart's electrical activity. Sensors attached to the skin are used to detect the electrical signal produced by one's heart each time it beats. Many people around the world suffer from cardiovascular diseases. So it is important to detect arrhythmia/abnormal and normal ECG signal more accurately. In this paper, ECG signal is classified by support vector machine (SVM) and neural network. The research is conducted on the normal and arrhythmia ECG datasets obtained from the PhysioNet website. The raw ECG data are preprocessed using different filters and then the features are extracted based on morphological values of the waveform. Twelve features are extracted and these are used to train classifiers to classify normal and abnormal ECG data. For SVM classifier, the accuracy is around 87% while for artificial neural network, MATLAB's pattern recognition app is used where the classification accuracy found is around 90 % - 93%. The accuracy varies for different numbers of hidden neurons. Diverse ECG databases are used to prove the efficacy and robustness of the use of proposed morphological features and obtained results are compared with existing state-of-the-art research works. This work can be further developed in the future by incorporating deep learning for better performance and it can eventually help to detect cardiac diseases.

In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM have been compared. This comparison was conducted to seek a robust method that would produce good classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG) signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder with SVM has been proposed. The EEG dataset used in this research was created by the University of Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature engineering. However, our prosed method of autoencoder in combination with SVM produced a similar accuracy of 65% without using any feature engineering technique. This research shows that this system of classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally control a robotic device or an exoskeleton.

This consensus guideline discusses the electrocardiographic phenomenon of beat-to-beat QT interval variability (QTV) on surface electrocar-diograms. The text covers measurement principles, physiological basis, and clinical value of QTV. Technical considerations include QT interval measurement and the relation between QTV and heart rate variability. Research frontiers of QTV include understanding of QTV physiology, systematic evaluation of the link between QTV and direct measures of neural activity, modelling of the QTV dependence on the variability of other physiological variables, distinction between QTV and general T wave shape variability, and assessing of the QTV utility for guiding therapy. Increased QTV appears to be a risk marker of arrhythmic and cardiovascular death. It remains to be established whether it can guide therapy alone or in combination with other risk factors. QT interval variability has a possible role in non-invasive assessment of tonic sympathetic activity.

Electrocardiogram (ECG) is a commonly recorded bio-signal that captures the electrical activity of the heart. Identifying various features and traits could help us detect the normal and pathological physiology of the heart, thus providing valuable information about the activity of the human heart which is a very important step in ECG signal analysis. Computer processing of ECG has evolved as an emerging tool in medical diagnosis for effective treatments. The work proposed in this paper deals with the detection of the R peak and its feature evaluation and reviews and summarizes the various techniques used by researchers in order to detect the same. ECG signals in this work are collected from several places and it has been implemented using MATLAB routine consisting of four different databases formats. The processing of the data was done on the Lead-II ECG signals.

When two people are on the phone, although they cannot observe the other person's facial expression and physiological state, it is possible to estimate the speaker's emotional state by voice roughly. In medical care, if the emotional state of a patient, especially a patient with an expression disorder, can be known, different care measures can be made according to the patient's mood to increase the amount of care. The system that capable for recognize the emotional states of human being from his speech is known as Speech emotion recognition system (SER). Deep learning is one of most technique that has been widely used in emotion recognition studies, in this paper we implement CNN model for Arabic speech emotion recognition. We propose ASERS-CNN model for Arabic Speech Emotion Recognition based on CNN model. We evaluated our model using Arabic speech dataset named Basic Arabic Expressive Speech corpus (BAES-DB). In addition of that we compare the accuracy between our previous ASERS-LSTM and new ASERS-CNN model proposed in this paper and we comes out that our new proposed mode is outperformed ASERS-LSTM model where it get 98.18% accuracy.

In this paper we propose an approach for testing time-domain properties of analog and mixed-signal circuits. The approach is based on an adaptation of a recently developed test generation technique for hybrid systems and a new concept of coverage for such systems. The approach is illustrated by its application to some benchmark circuits.