Feature Extraction Of ECG Signal Research Articles

A Linearly Adaptive Sine–Cosine Algorithm with Application in Deep Neural Network for Feature Optimization in Arrhythmia Classification using ECG Signals

This work proposes a novel variant namely Linear Adaptive Sine–Cosine Algorithm (LA-SCA) of newly developed metaheuristic called Sine–Cosine Algorithm (SCA). The developed variant utilizes a linearly adaptive operator that is based on the number of generations, followed by an Opposition based Learning (OBL) model applied around the best solution. The applied mechanisms help LA-SCA to overcome the slow convergence problem in SCA and capable of achieving appropriate balance between macro and micro search ability of SCA. The performance of proposed LA-SCA is evaluated using a set of 23 state-of-the-art benchmark problems having a variety of characteristics and diverse complexities. The LA-SCA is statistically analysed by applying a Wilcoxon ranksum test and performance analysis using convergence curves and diversity analysis. In second part, the proposed LA-SCA is utilized to offer an intelligent Deep Neural Network (DNN) mechanism for improving the feature extraction of ECG signal for efficient classification of arrhythmia diseases. During the pre-processing step, Discrete Wavelet Transformation (DWT) is utilized to categorize ECG data followed by improving the extraction of QRS complex features using proposed LA-SCA. The MIT-BIH Arrhythmia ECG dataset is used in order to perform classification of signals among sixteen categories of arrhythmia disease. By using the classification analysis on the basis of variation including optimized feature vector and the LA-SCA method with DNN, the heart rate has been observed with an improved 99.29 percent accuracy as compared to other techniques. This achieved accuracy demonstrated the superiority of proposed model for appropriately classifying the ECG signal.

ECG signal classification based on Deep Learning by using Convolutional Neural Network (CNN)

Cardiovascular diseases (CVDs) are consider the main cause of death today According to World Health Organization (WHO),and because that ECG signal is very important tool in monitoring and diagnosis of these disease , different automatic methods were proposed based on this signal. [1]. The manual analysis of ECG signals is suffered different challenges such as differeculty of detecting and classify waveform of this signal, So, many machine learning methods are explored to describe the anomalies ECG signal accurately . Deep learning (DL) can be used in ECG classification, it can improve the quality of the automatic classification system. In this paper , we have proposed a deep learning classification system by using different layers of convolution, rectifier and pooling operations that can be used to increase feature extraction of ECG signal.
 We have proposed two models, one is used for input signal of 1-D, in which we designed model for classification csv type of data for ECG signal, while in the second proposed system, we used model for 2-D signal after convert it from its csv type . 2-D signal (ECG image) is used in order to augment the two dimensional signal with different methods to increase the accuracy of the model by training it with geometric transformation of the original input images such as rotation, shearing etc.The results are compared with AlexNet and other models based on the metrics, which are used to measure the performance of the proposed work, the result show that, the proposed models improve the efficiency of the classification in the two systems.

Automatic feature extraction of ECG signal based on adaptive window dependent differential histogram approach and validation with CSE database

A very simple and novel idea based on adaptive window dependent differential histogram approach has been proposed for automatic detection and identification of ECG waves with its characteristic features. To facilitate the estimation of the waves, the normalised signal has been divided into a few small windows by an adaptive window selection technique. By counting the number of changes between successive samples as frequency, the differential histogram has been plotted. Some of the zones having an area more than a pre-defined threshold are depicted as QRS zones. The local maxima of these zones are referred as the R-peaks. T and P peaks are also detected. Baseline point and clinically significant time plane features have been computed and validated with reference values of the CSE database. The proposed technique achieved better performance in comparison with CSE groups. Its accuracy is achieved in sensitivity (99.86%), positive productivity (99.76%) and detection accuracy (99.8%).

Automatic feature extraction of ECG signal based on adaptive window dependent differential histogram approach and validation with CSE database

A very simple and novel idea based on adaptive window dependent differential histogram approach has been proposed for automatic detection and identification of ECG waves with its characteristic features. To facilitate the estimation of the waves, the normalised signal has been divided into a few small windows by an adaptive window selection technique. By counting the number of changes between successive samples as frequency, the differential histogram has been plotted. Some of the zones having an area more than a pre-defined threshold are depicted as QRS zones. The local maxima of these zones are referred as the R-peaks. T and P peaks are also detected. Baseline point and clinically significant time plane features have been computed and validated with reference values of the CSE database. The proposed technique achieved better performance in comparison with CSE groups. Its accuracy is achieved in sensitivity (99.86%), positive productivity (99.76%) and detection accuracy (99.8%).

Disease Detection by Feature Extraction of ECG Signal based on ANFIS

Disease Detection by Feature Extraction of ECG Signal based on ANFIS

The Application of Frequency Slice Wavelet Transform in ECG Signal Feature Extraction

The Application of Frequency Slice Wavelet Transform in ECG Signal Feature Extraction

A PVC Identification Method of ECG Signal Based on Improved BPNN

Computer-aided diagnosis of Premature Ventricular Contraction (PVC) plays an important role in timely detection and treatment of arrhythmias. Conventional identification methods based on back propagation neural network (BPNN) get problems of overlong training time and local optimum. This paper proposes an application of improved BPNN on PVC identification and the improvements of BPNN are based on self-adaptive learning rate and momentum in training. Denoising and feature extraction of ECG signal obtained from MIT-BIH arrhythmia database are processed first. A comparison between standard BPNN and improved BPNN shows that the latter gets less training time and better accuracy.

Feature extraction of ECG signal using a support vector machine

Additionally, areas of slowed impulse propagation velocity led to ST segment deviations in the “reciprocal” leads, shifting the ST segment change towards the affected areas. Conclusion: Using computer modeling we showed that the localized alteration of impulse propagation modified not only the QRS complex, but produced also changes in the ST segment consistent with changes which are usually interpreted as the effect of “injury current”. Supported by the grant VEGA 2/0131/13.

A 30 $\mu$W Analog Signal Processor ASIC for Portable Biopotential Signal Monitoring

This paper presents the design and implementation of an analog signal processor (ASP) ASIC for portable ECG monitoring systems. The ASP ASIC performs four major functionalities: 1) ECG signal extraction with high resolution, 2) ECG signal feature extraction, 3) adaptive sampling ADC for the compression of ECG signals, 4) continuous-time electrode-tissue impedance monitoring for signal integrity monitoring. These functionalities enable the development of wireless ECG monitoring systems that have significantly lower power consumption yet that are more capable than their predecessors. The ASP has been implemented in 0.5 μm CMOS process and consumes 30 μW from a 2 V supply. The noise density of the ECG readout channel is 85 nV/√Hz and the CMRR is better that 105 dB. The adaptive sampling ADC is capable of compressing the ECG data by a factor of 7 and the heterodyne chopper readout extracts the features of the ECG signals. Combination of these two features leads to a factor 4 reduction in the power consumption of a wireless ECG monitoring system. Furthermore, the proposed continuous-time impedance monitoring circuit enables the monitoring of the signal integrity.

Long-term ECG signal feature extraction

This paper proposes a cepstrum coefficient method applying the dynamic time warping technique to extract the feature vectors from long-term ECG signals. Utilizing this method, one can identify the characteristics hidden in an ECG signal; and then classify the signal as well as diagnose the abnormalities. To evaluate this method, the Normal and PACED BEAT data from the MIT/BIH database are used. The results show that the proposed method successfully extracts the corresponding feature vectors, distinguishes the difference and classifies both signals.