Pattern Recognition Application in ECG Arrhythmia Classification

Nikan, Soodeh; Gwadry-Sridhar, Femida; Bauer, Michael

doi:10.5220/0006116300480056

Cited by 18 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extract 17 shape features from the PPG samples [19], including the maximum and minimum value, peak value, and mean amplitude. The 1DLBP method can effectively extract binary codes from one-dimensional signals [29], and we use it for PPG samples by comparing the amplitude of each sampling point with its neighbours. The MSDF considers the specific amplitude of the PPG signals and reinforces the preservation of PPG signal morphology with multi-scale differential characteristics [6].…”

Section: Time-domain Featuresmentioning

confidence: 99%

Time–frequency fusion learning for photoplethysmography biometric recognition

Liu

Huang

et al. 2022

IET Biometrics

View full text Add to dashboard Cite

Photoplethysmography (PPG) signal is a novel biometric trait related to the identity of people; many time-and frequency-domain methods for PPG biometric recognition have been proposed. However, the existing domain methods for PPG biometric recognition only consider a single domain or the feature-level fusion of time and frequency domains, without considering the exploration of the fusion correlations of the time and frequency domains. The authors propose a time-frequency fusion for a PPG biometric recognition method with collective matrix factorisation (TFCMF) that leverages collective matrix factorisation to learn a shared latent semantic space by exploring the fusion correlations of the time and frequency domains. In addition, the authors utilise the ℓ 2,1 norm to constrain the reconstruction error and shared matrix, which can alleviate the influence of noise and intra-class variation, and ensure the robustness of learnt semantic space. Experiments demonstrate that TFCMF has better recognition performance than current state-of-the-art methods for PPG biometric recognition.

show abstract

Section: Time-domain Featuresmentioning

confidence: 99%

Time–frequency fusion learning for photoplethysmography biometric recognition

Liu

Huang

et al. 2022

IET Biometrics

View full text Add to dashboard Cite

show abstract

“…The discrete wavelet coefficients of the heartbeat are obtain as wavelet features, and we chose Daubechies wavelet Db3 with five levels of decomposition to obtain the heartbeat feature value [37]. The 1D-LBP method [38] can effectively extract binary codes from ECG signals by comparing each sampling point with its neighbors. We can obtain the multiple sparse representation matrices from the extracted features by the sparse representation learning.…”

Section: Multiple Feature Extractionmentioning

confidence: 99%

Multi-Feature Sparse Representations Learning via Collective Matrix Factorization for ECG Biometric Recognition

Liu

Huang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Electrocardiogram (ECG) signal is a promising biometric trait, and many methods have been proposed for ECG biometric recognition. However, it is challenging to design a robust and precise method to improve the recognition performance of ECG signals with noise and signal variation. We present a multi-feature sparse representations learning model via collective matrix factorization for ECG biometric recognition, MSRCMF for short. First, we extract one-dimensional local binary pattern (1D-LBP), shape and wavelet features of ECG signals and then obtain their sparse representations. Second, to extract discriminative information and preserve the intra-and inter-subject similarities, we leverage the collective matrix factorization on multiple sparse representations and the label information to obtain the latent semantic space. At last, we can recognize the ECG signals in the learned semantic space. Extensive experiments on four ECG databases show that MSRCMF can achieve competitive performance compared to state-of-the-art methods.

show abstract

“…Several heartbeat classification algorithms have been proposed [4,5]. Neural networks [6], wavelet transform [7,8], correlation coefficients [9,10], energy operator [11,12], pattern recognition [13,14] have been used to develop PVC beat recognition algorithms. The precision and the execution time differ from one algorithm to another.…”

Section: Introductionmentioning

confidence: 99%

Three‐Bits Linear Interpolation Error Signal Based ECG Beat Classification

Alshrouf

Mansouri

Alharbi

2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

About three million people die from sudden cardiac arrest (SCA) or infarction each year. It is the biggest killer on the planet and it can happen to anyone, anywhere, and anytime. Early and effective diagnosis from ECG signals can help save a large part of these SCAs. Premature ventricular contraction (PVC) detection and classification was performed with different methods. A new method of automatic classification of PVC based on a three‐bit linear interpolation error signal (LIES) is proposed in this paper. We start by a QRS detection, a nonlinear transformation and then a sliding window. This method was tested on normal and abnormal beats obtained from MIT‐BIH and AHA databases. The proposed algorithm with a sensitivity 94.8% and a specificity was 98.6%. is accurate. This algorithm is also automatic, robust, and fast. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Pattern Recognition Application in ECG Arrhythmia Classification

Cited by 18 publications

References 20 publications

Time–frequency fusion learning for photoplethysmography biometric recognition

Time–frequency fusion learning for photoplethysmography biometric recognition

Multi-Feature Sparse Representations Learning via Collective Matrix Factorization for ECG Biometric Recognition

Three‐Bits Linear Interpolation Error Signal Based ECG Beat Classification

Contact Info

Product

Resources

About