ECG signal denoising through kernel principal components

Gualsaqui, Marco; Vizcaino, E. Ivan P.; Flores-Calero, Marco; Carrera, Enrique V.

doi:10.1109/intercon.2017.8079670

Cited by 8 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, earlier studies (Ozbay and Karlik, 2001) demonstrated that automated ECG categorization works best when concentrating on the shape of the R-T interval (of the ECG), which also holds true for rbbb and timed beats. Rpeaks must be successfully recognised using QRS detection in order to derive the R-T interval from the ECG [24]. The QRS detection is done using the well-known Pan-Tompkins method (Pan and Tompkins, 1985).…”

Section: Arrhythmia Class Predictionmentioning

confidence: 99%

Recognition and Evaluation of Heart Arrhythmias via a General Sparse Neural Network

Sanamdikar,

Waghmare,

Patil

et al. 2023

IJRITCC

View full text Add to dashboard Cite

In clinical use, an electrocardiogram (ECG) is an essential medical tool for assessing heart arrhythmias. Thousands of human beings worldwide are affected by different cardiac problems nowadays. As a consequence, studying the features of the ECG pattern is critical for detecting a wide range of cardiac diseases. The ECG is a test which assesses the intensity of the electrical impulses in the circulatory system. In the present investigation, detection and examination of arrhythmias in the heart on the system using GSNNs (General sparsed neural network classifier) can be carried out[1]. In this paper, the methodologies of support vector regression(SVR), neural mode decomposition(NMD), Artificial Neural Network (ANN), Support Vector Machine(SVM) and are examined. To assess the suggested structure, three distinct ECG waveform situations are chosen from the MIT-BIH arrhythmia collection. The main objective of this assignment is to create a simple, accurate, and simply adaptable approach for classifying the three distinct heart diseases chosen. The wavelet transform Db4 is used in the present paper to obtain several features from an ECG signal. The suggested setup was created using the MATLAB programme. The algorithms suggested are 98% accurate for forecasting cardiac arrhythmias, which is greater than prior techniques.

show abstract

Section: Arrhythmia Class Predictionmentioning

confidence: 99%

Recognition and Evaluation of Heart Arrhythmias via a General Sparse Neural Network

Sanamdikar,

Waghmare,

Patil

et al. 2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Gaussian Kernel was employed in this case. KPCA works on the premise of mapping data to a higherdimensional component space F with a nonlinear relationship to the input space [40]. Because KPCA is a circle and PCA is a straight line for the biggest difference between the projections of the points onto the eigenvector (new coordinates), KPCA has greater variance than PCA.…”

Section: Kpcamentioning

confidence: 99%

A Low Complex Algorithm for Detection of Sleep Apnea from ECG Signals using Sliding SSA Combined with PCA, KPCA, and SPPCA

Zubair¹

2021

Preprint

View full text Add to dashboard Cite

Sleep apnea is a potentially life-threatening sleep condition in which breathing stops and resumes repeatedly. It is caused by breathing pauses during sleep, which leads to frequent awakenings. As we all know, computational time and efficiency are essential in the healthcare industry; to address this issue, we proposed an algorithm that performs more computations in less time without compromising the machine learning model’s performance. This study employs a unique technique called Sliding Singular Spectrum Analysis (SSSA) to decompose and de-noise the ECG signals. To identify the significant apnea and non-apnea components from the pre-processed ECG data and to reduce the dimensionality, we used Principal Component Analysis (PCA), Kernal PCA (KPCA), and Sub-Pattern based PCA (SPPCA). These characteristics were then used to train and evaluate various machine learning models, including KNN, SVM, GaussianNB, SGD, and XGBoost, to distinguish between apnea and non-apnea ECG data. The publicly available Physionet Apnea-ECG database is used for the simulation of the proposed algorithm. To verify the performance of machine learning models, we have calculated various metrics like accuracy, precision, recall and F1 score. The validation of the proposed method is done by comparing the classification metrics with the latest state-of-the-art works.

show abstract

“…In earlier, numerous methods are proposed to denoise the ECG signals based on filter banks, adaptive filtering [7,8], Neural Networks (NNs), independent component analysis (ICA) [6,12], principal component analysis (PCA) [10], Kernel PCA [11], wavelet transform [14 -16], Empirical Mode Decomposition [5,9,13] and hybrid approaches by involving both EMD and wavelet transform [17,18].…”

Section: Literature Surveymentioning

confidence: 99%

ECG Signal Enhancement through Subband Adaptive Soft Thresholding and EMD for Efficient Cardiac Arrhythmia Analysis

Ramesh¹,

Satyanarayana²,

Sailaja³

2018

IJIES

View full text Add to dashboard Cite

Among various Bio-medical signals, Electrocardiogram (ECG) is most important signal to diagnose Cardiac Arrhythmia (CA). However the noises added during ECG signal acquisition makes the system less accurate in CA detection. This paper presents a new ECG denoising approach based on noise reduction aspects in Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) domains. The main objective to use DWT is to remove the high frequency noise components like EMG noise which leads to significant cropping in QRS complexes and also lead to distortions at the beginning and ending of QRS complexes. This approach also designs an adaptive threshold which considers the average noise and signal powers to remove the noise form ECG signal. The segmentation of ECG signal involves to focus only on the noise dominant components such that the overall complexity also in the control. Further the EMD preserves the QRS complexes information by adapting the adaptive thresholding for the Intrinsic Mode Functions (IMFs) after finding the noise dominant IMFs from signal dominant IMFs. Simulation results are carried out through MIT-BIH Arrhythmia database and the performance is evaluated with respect to the performance metrics like Mean Square Error and Signal to Noise Ratio. The proposed approach provides better results compared to the conventional state-of the-art techniques.

show abstract

ECG signal denoising through kernel principal components

Cited by 8 publications

References 7 publications

Recognition and Evaluation of Heart Arrhythmias via a General Sparse Neural Network

Recognition and Evaluation of Heart Arrhythmias via a General Sparse Neural Network

A Low Complex Algorithm for Detection of Sleep Apnea from ECG Signals using Sliding SSA Combined with PCA, KPCA, and SPPCA

ECG Signal Enhancement through Subband Adaptive Soft Thresholding and EMD for Efficient Cardiac Arrhythmia Analysis

Contact Info

Product

Resources

About