Local feature descriptors based ECG beat classification

Abstract

ECG beat type analysis is important in the detection of various heart diseases. The ECG beats give useful information about the status of the monitored heart condition. Up to now, various artificial intelligence-based methods have been proposed for ECG based heart failure detection. These methods were generally based on either time or frequency domain signal processing routines. In this study, we propose a different approach for ECG beat classification. The proposed approach is based on image processing. Thus, the initial step of the proposed work is converting the ECG beat signals to the ECG beat images. To do that, the ECG beat snapshots are initially saved as ECG beat images and then local feature descriptors are considered for feature extraction from ECG beat images. Eight local feature descriptors namely Local Binary Patterns, Frequency Decoded LBP, Quaternionic Local Ranking Binary Pattern, Binary Gabor Pattern, Local Phase Quantization, Binarized Statistical Image Features, CENsus TRansform hISTogram and Pyramid Histogram of Oriented Gradients are considered for feature extraction. The Support Vector Machines (SVM) classifier is used in the classification stage of the study. Linear, Quadratic, Cubic and Gaussian kernel functions are used in the SVM classifier. Five types of ECG beats from the MIT-BIH arrhythmia dataset are considered in experiments and the classification accuracy is used for performance measure. To construct a balanced training and test sets, 5000 and 10,000 ECG beat samples are randomly selected and are used in experiments in tenfold cross-validation fashion. The obtained resultsshow that the proposed method is quite efficient where the calculated accuracy score is 99.9% and the comparisons with the state-of-the-art method show that the proposed method outperforms other methods.

The hidden waves in the ECG uncovered revealing a sound automated interpretation method

“…The comparison with other studies in the literature is not feasible since the selection of heartbeats, patients, or the classes to discriminate differs from one paper to another, in many of them, the choice seems to be made ad hoc. As far as we know, this is the first time that this milestone has been achieved for the QT database, since other authors consider specifically selected sets of patients of a much smaller size (see 27,32 and references therein). Moreover, a complete analysis is provided in the Supplementary Information including, specific-patient plots and statistics for the main FMM ecg parameters.…”

An Ensemble Learning-Based Method for Inferring Drug-Target Interactions Combining Protein Sequences and Drug Fingerprints

“…Herein, we adopted Sobel operators to detect the edges and reduce the noise of the image. The Sobel operators can be defined as follows: where Sobel x and Sobel y represent the horizontal operator and the vertical operator individually [ 32 ]. Then, the first-order differential Sobel operator is utilized to convolute the given image as follows: where G x denotes the convolution of picture F in the x -axis direction, where G y denotes the convolution of image F in the y -axis direction.…”

“…where Sobel x and Sobel y represent the horizontal operator and the vertical operator individually [32]. Then, the firstorder differential Sobel operator is utilized to convolute the given image as follows:…”

Application of Internet of Things on the Healthcare Field Using Convolutional Neural Network Processing

“…Ongoing advancements in artificial intelligence (AI) have been implemented in numerous industries, including the education and medical field. According to numerous studies [1][2][3], AI has shown the ability to outperform humans and information systems at most cases [4][5][6][7][8]. It is a mechanical, electrical, and chemical organism that constitutes the human body [5].…”

“…Automated systems have a difficult time spotting anomaly. External noise and the body response to different physical conditions are examples of this [6][7][8].…”