Cardiac disease classification using total variation denoising and morlet continuous wavelet transformation of ECG signals

abdi, Rabah M. Al; Jarrah, Mohamad

doi:10.1109/cspa.2018.8368685

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is achieved by calculating the absolute differences between adjacent data points and summing them up. The goal of this step was to mitigate the impact of noise on the measurements, preventing at the same time the loss of valuable information [18]:…”

Section: A Preprocessingmentioning

confidence: 99%

Human Activity Recognition Based on Wireless Electrocardiogram and Inertial Sensors

Farrokhi,

Dargie,

Poellabauer

2024

IEEE Sensors J.

View full text Add to dashboard Cite

Wearable devices enable remote, long-term, and unobtrusive monitoring of patients in their everyday living and working environments. Remote health monitoring often involves monitoring physical and cardiac activities (exertions) in order to establish correlations between the two. With recent advances in sensor technologies and machine learning, the efficiency with which these activities can be recognized has been steadily improving. In this paper, we apply Convolutional Neural Networks (CNN) to measurements taken with wireless electrocardiograms and inertial sensors for Human Activity Recognition (HAR). Experimental results confirm that our approach is able to recognize a wide range of everyday activities with a high degree of accuracy. Specifically, activities such as Jumping, Running, and Sitting could be recognized with accuracy exceeding 99%, while activities such as Bending Over, Walking, Standing Up, and Climbing Stairs could be recognized with accuracy exceeding 90%. Overall, the results suggest that the combined use of inertial sensors and ECG leads to a better recognition accuracy. Likewise, the paper closely examines the contributions of individual sensors and if and to what extent their placement affects recognition accuracy.

show abstract

Section: A Preprocessingmentioning

confidence: 99%

Human Activity Recognition Based on Wireless Electrocardiogram and Inertial Sensors

Farrokhi,

Dargie,

Poellabauer

2024

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…We chose the Morlet and Mexican Hat wavelets because of their wide use in the literature considering ECG [24][25][26]. In regard to the Gauss7 wavelet, we chose this one mainly because we could not find works in the literature that had experimented with it before (the one that came close to it ran experiments up to the sixth derivative of the Gaussian function [27]) and also to check the effects that an asymmetric wavelet would have on the ECG signal.…”

Section: Modelmentioning

confidence: 99%

Preprocessing Selection for Deep Learning Classification of Arrhythmia Using ECG Time-Frequency Representations

2023

View full text Add to dashboard Cite

The trend of using deep learning techniques to classify arbitrary tasks has grown significantly in the last decade. Such techniques in the background provide a stack of non-linear functions to solve tasks that cannot be solved in a linear manner. Naturally, deep learning models can always solve almost any problem with the right amount of functional parameters. However, with the right set of preprocessing techniques, these models might become much more accessible by negating the need for a large set of model parameters and the concomitant computational costs that accompany the need for many parameters. This paper studies the effects of such preprocessing techniques, and is focused, more specifically, on the resulting learning representations, so as to classify the arrhythmia task provided by the ECG MIT-BIH signal dataset. The types of noise we filter out from such signals are the Baseline Wander (BW) and the Powerline Interference (PLI). The learning representations we use as input to a Convolutional Neural Network (CNN) model are the spectrograms extracted by the Short-time Fourier Transform (STFT) and the scalograms extracted by the Continuous Wavelet Transform (CWT). These features are extracted using different parameter values, such as the window size of the Fourier Transform and the number of scales from the mother wavelet. We highlight that the noise with the most significant influence on a CNN’s classification performance is the BW noise. The most accurate classification performance was achieved using the 64 wavelet scales scalogram with the Mexican Hat and with only the BW noise suppressed. The deployed CNN has less than 90k parameters and achieved an average F1-Score of 90.11%.

show abstract

“…Meiniel et al [19] proposed a novel sparsity-based image denoising algorithm that combines TV spatial regu-larization, low-frequency information enhancement, and sparse estimation aggregation, which can handle simple and complex types of noise (Gaussian, Poisson, and mixed noise) without any prior model, only requiring a set of parameter values. Rabah et al [20] used TV denoising to filter electrocardiogram signals, removing sharp edges and calculating the Morlet continuous wavelet coefficient matrix, which effectively distinguishes patients with cardiac diseases from normal electrocardiogram patients. However, there is currently a lack of research on directly applying TV denoising techniques to the backend of underwater acoustic-based deconvolution methods for noise suppression in acoustic BTRs.…”

Section: Introductionmentioning

confidence: 99%

A Robust Denoised Algorithm Based on Hessian–Sparse Deconvolution for Passive Underwater Acoustic Detection

Yin,

Li,

Wang

et al. 2023

JMSE

View full text Add to dashboard Cite

Digital beamforming techniques find wide applications in the field of underwater acoustic array signal processing. However, their azimuthal resolution has long been constrained by the Rayleigh limit, consequently limiting their detection performance. In this paper, we propose a novel two-dimensional Hessian–sparse deconvolution algorithm based on image processing techniques. This method assumes a priori that the underwater acoustic bearing time record (BTR) images exhibit sparsity, and then it first constructs partial differential equations in the beamforming domain with sparsity-norm constraints for optimal noise reduction. Subsequently, a two-dimensional deconvolution operation is applied to narrow the main lobe, aiming to achieve additional temporal gains in two-dimensional processing. The simulation and real sea trial data processing results show that the main lobe width of the proposed method is about 1.3 degrees at 0 dB. It effectively reduces the main lobe width and enhances the detection resolution of BTRs in the post-processing part, especially in low-signal-to-noise-ratio (SNR) environments. Therefore, the proposed method provides nice opportunities to further improve the target-detecting ability of hydrophone arrays.

show abstract

Cardiac disease classification using total variation denoising and morlet continuous wavelet transformation of ECG signals

Cited by 8 publications

References 14 publications

Human Activity Recognition Based on Wireless Electrocardiogram and Inertial Sensors

Human Activity Recognition Based on Wireless Electrocardiogram and Inertial Sensors

Preprocessing Selection for Deep Learning Classification of Arrhythmia Using ECG Time-Frequency Representations

A Robust Denoised Algorithm Based on Hessian–Sparse Deconvolution for Passive Underwater Acoustic Detection

Contact Info

Product

Resources

About