ECG Classification With Event-Driven Sampling
Electrocardiogram (ECG) data’s high dimensionality challenges real-time arrhythmia classification. Our approach employs functional approximation to condense ECG recordings into a compact feature set for simpler classification using Chebyshev polynomials. These polynomials, with 200 time p...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10427994/ |
| _version_ | 1797302681215172608 |
|---|---|
| author | Maryam Saeed Olev Martens Benoit Larras Antoine Frappe Deepu John Barry Cardiff |
| author_facet | Maryam Saeed Olev Martens Benoit Larras Antoine Frappe Deepu John Barry Cardiff |
| author_sort | Maryam Saeed |
| collection | DOAJ |
| description | Electrocardiogram (ECG) data’s high dimensionality challenges real-time arrhythmia classification. Our approach employs functional approximation to condense ECG recordings into a compact feature set for simpler classification using Chebyshev polynomials. These polynomials, with 200 time points and 80 coefficients, accurately represent arrhythmias in an <inline-formula> <tex-math notation="LaTeX">$81 \times 1$ </tex-math></inline-formula> feature vector. We prove Chebyshev polynomials act as implicit low-pass filters on input signals. Using MIT-BIH Arrhythmia and MIT-BIH Supraventricular Arrhythmia datasets, we introduce classifiers that achieve significant accuracy. A three-layered Artificial Neural Network yields high F1-scores (0.99, 0.90, 0.93, and 0.76 for classes N, S, V, and F) with minimal parameters (20,964), surpassing existing models. Furthermore, our proposed ECG classification system exhibits minimal computational demands, requiring only 0.1 MIPS per beat. We also propose efficient signal reconstruction methods, with the iterative approach showcasing accurate reconstruction with negligible error. This approach accommodates various data sampling types and determines optimal Chebyshev coefficients for capturing signal bandwidth. |
| first_indexed | 2024-03-07T23:41:26Z |
| format | Article |
| id | doaj.art-77708a6d4f094f3e981ee1090e21b212 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T23:41:26Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-77708a6d4f094f3e981ee1090e21b2122024-02-20T00:00:39ZengIEEEIEEE Access2169-35362024-01-0112251882519910.1109/ACCESS.2024.336411510427994ECG Classification With Event-Driven SamplingMaryam Saeed0https://orcid.org/0000-0002-7046-2898Olev Martens1https://orcid.org/0000-0003-2899-9197Benoit Larras2https://orcid.org/0000-0003-2501-8656Antoine Frappe3https://orcid.org/0000-0002-0977-549XDeepu John4https://orcid.org/0000-0002-6139-1100Barry Cardiff5https://orcid.org/0000-0003-1303-8115UCD School of Electrical and Electronic Engineering, UCD Engineering and Materials Science Centre, Dublin 4, Belfield, IrelandThomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Tallinn, EstoniaUniv. Lille, CNRS, Centrale Lille, Junia, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, FranceUniv. Lille, CNRS, Centrale Lille, Junia, Univ. Polytechnique Hauts-de-France, UMR 8520-IEMN, Lille, FranceUCD School of Electrical and Electronic Engineering, UCD Engineering and Materials Science Centre, Dublin 4, Belfield, IrelandUCD School of Electrical and Electronic Engineering, UCD Engineering and Materials Science Centre, Dublin 4, Belfield, IrelandElectrocardiogram (ECG) data’s high dimensionality challenges real-time arrhythmia classification. Our approach employs functional approximation to condense ECG recordings into a compact feature set for simpler classification using Chebyshev polynomials. These polynomials, with 200 time points and 80 coefficients, accurately represent arrhythmias in an <inline-formula> <tex-math notation="LaTeX">$81 \times 1$ </tex-math></inline-formula> feature vector. We prove Chebyshev polynomials act as implicit low-pass filters on input signals. Using MIT-BIH Arrhythmia and MIT-BIH Supraventricular Arrhythmia datasets, we introduce classifiers that achieve significant accuracy. A three-layered Artificial Neural Network yields high F1-scores (0.99, 0.90, 0.93, and 0.76 for classes N, S, V, and F) with minimal parameters (20,964), surpassing existing models. Furthermore, our proposed ECG classification system exhibits minimal computational demands, requiring only 0.1 MIPS per beat. We also propose efficient signal reconstruction methods, with the iterative approach showcasing accurate reconstruction with negligible error. This approach accommodates various data sampling types and determines optimal Chebyshev coefficients for capturing signal bandwidth.https://ieeexplore.ieee.org/document/10427994/Level-crossing ADCelectrocardiogramsfunctional approximationChebyshev polynomialsartificial neural networksarrhythmia |
| spellingShingle | Maryam Saeed Olev Martens Benoit Larras Antoine Frappe Deepu John Barry Cardiff ECG Classification With Event-Driven Sampling IEEE Access Level-crossing ADC electrocardiograms functional approximation Chebyshev polynomials artificial neural networks arrhythmia |
| title | ECG Classification With Event-Driven Sampling |
| title_full | ECG Classification With Event-Driven Sampling |
| title_fullStr | ECG Classification With Event-Driven Sampling |
| title_full_unstemmed | ECG Classification With Event-Driven Sampling |
| title_short | ECG Classification With Event-Driven Sampling |
| title_sort | ecg classification with event driven sampling |
| topic | Level-crossing ADC electrocardiograms functional approximation Chebyshev polynomials artificial neural networks arrhythmia |
| url | https://ieeexplore.ieee.org/document/10427994/ |
| work_keys_str_mv | AT maryamsaeed ecgclassificationwitheventdrivensampling AT olevmartens ecgclassificationwitheventdrivensampling AT benoitlarras ecgclassificationwitheventdrivensampling AT antoinefrappe ecgclassificationwitheventdrivensampling AT deepujohn ecgclassificationwitheventdrivensampling AT barrycardiff ecgclassificationwitheventdrivensampling |