FPGA-based reservoir computing system for ECG denoising

Elbedwehy, Aya N.; El-Mohandes, Awny M.; Elnakib, Ahmed; Abou-Elsoud, Mohy Eldin A.

doi:10.1016/j.micpro.2022.104549

Cited by 13 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A model of reservoir computing at an economical expense by means of FPGA and ECG denoising of high-speed was done by Elbedwehy et al (2022). An architecture was applied here employing the back propagation recurrence bound with technologically advanced and less complex modules.…”

Section: Stage 1: Preprocessing (Denoising)mentioning

confidence: 99%

Real-Time Processing Stages of Electrocardiogram Signal: A Review

Waleed

2024

JMTE

View full text Add to dashboard Cite

Signal analysis is a multidisciplinary field that combines various processes to create robust pipelines for automating data analysis. Within the medical field, its application revolves around physiological signals. Electrocardiogram (ECG) signal provides vital information concerning various cardiac conditions affecting the human heart. ECG analysis is a central pillar of medical research with the goal of detecting and preventing potentially fatal cardiac events. This review article aims to provide a comprehensive analysis of real-time processing techniques for electrocardiogram signals. It discusses the different methods and algorithms used for detecting and analyzing ECG signals in real-time, with a focus on their effectiveness and efficiency. Where, it evaluates the use of various techniques such as ECG signal preprocessing (denoising), ECG fiducial points detecting and ECG signal classification. It also highlights the challenges faced in real-time ECG signal processing, such as High-fidelity signal acquisition and noise reduction, and computational efficiency and resource constraints. Furthermore, the article presents an overview of the existing QRS-peak detection strategies, including methods such as Haar wavelet transform, and modified MaMeMi Filter.

show abstract

Section: Stage 1: Preprocessing (Denoising)mentioning

confidence: 99%

Real-Time Processing Stages of Electrocardiogram Signal: A Review

Waleed

2024

JMTE

View full text Add to dashboard Cite

show abstract

“…Remember that the integral of the product of the two original Gaussian functions is computed using the sum of their variances to determine the value of the Gaussian determined at the point where the arguments diverge. Consequently, 𝐻 ̂2(𝑒) can be expressed as (5).…”

Section: Minimum Error Entropy Algorithmmentioning

confidence: 99%

A novel adaptive noise cancellation method based on minimization of error entropy for electrocardiogram denoising

Mousa Saad,

Al-Chaabawi,

H. Hassan

2023

IJEECS

View full text Add to dashboard Cite

<span>In this paper, we use an adaptive method that conforms to the error entropy criterion in order to eliminate noise from cardiac signals electrocardiogram (ECG). In previous works, the mean squared error (MSE) criterion has been used to adaptive noise cancelation of ECG signals, which only has the ability to minimize the second moment of error. The MSE criterion only works optimally on systems with Gaussian noise and stationary signals, so this is not suitable for ECG signals that are non-stationary and have non-Gaussian noise. In contrast, the use of error entropy-based algorithms like minimum error entropy (MEE) is very useful in ECG noise cancelation. The results of the proposed algorithm indicate a significant advantage in terms of signal-to-noise ratio (SNR) and convergence value compared to the algorithm based on MSE criteria.</span>

show abstract

“…RC models have been widely applied to various applications that involve the analysis of ECG signals. These applications comprise ECG de-noising [43], ventricular heartbeat classification [44], stress detection [45], and arrhythmia detection [46,47].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Heartbeat Classification through Cascading Next Generation and Conventional Reservoir Computing

Arbateni,

Benzaoui

2024

Applied Sciences

View full text Add to dashboard Cite

Electrocardiography (ECG) is a simple and safe tool for detecting heart conditions. Despite the diaspora of existing heartbeat classifiers, improvements such as real-time heartbeat identification and patient-independent classification persist. Reservoir computing (RC) based heartbeat classifiers are an emerging computational efficiency solution that is potentially recommended for real-time concerns. However, multiclass patient-independent heartbeat classification using RC-based classifiers has not been considered and constitutes a challenge. This study investigates patient-independent heartbeat classification by leveraging traditional RC and next-generation reservoir computing (NG-RC) solely or in a cascade. Three RCs were investigated for classification tasks: a linear RC featuring linear internal nodes, a nonlinear RC with a nonlinear internal node, and an NG-RC. Each of these has been evaluated independently using either linear ridge regression or multilayer perceptron (MLP) as readout models. Only three classes were considered for classification: the N, V, and S categories. Techniques to deal with the imbalanced nature of the data, such as the synthetic minority oversampling technique (SMOTE) and oversampling by replacement, were used. The MIT-BIH dataset was used to evaluate classification performance. The area under the curve (AUC) criterion was used as an evaluation metric. The NG-RC-based model improves classification performance and mitigates the overfitting issue. It has improved classification performance by 4.18% and 2.31% for the intra-patient and inter-patient paradigms, respectively. By cascading RC and NG-RC, the identification performance of the three heartbeat categories is further enhanced. AUCs of 97.80% and 92.09% were reported for intra- and inter-patient scenarios, respectively. These results suggest promising opportunities to leverage RC technology for multiclass, patient-independent heartbeat recognition.

show abstract

FPGA-based reservoir computing system for ECG denoising

Cited by 13 publications

References 25 publications

Real-Time Processing Stages of Electrocardiogram Signal: A Review

Real-Time Processing Stages of Electrocardiogram Signal: A Review

A novel adaptive noise cancellation method based on minimization of error entropy for electrocardiogram denoising

Enhancing Heartbeat Classification through Cascading Next Generation and Conventional Reservoir Computing

Contact Info

Product

Resources

About