A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions
This paper proposes a robust and real-time capable algorithm for classification of the first and second heart sounds. The classification algorithm is based on the evaluation of the envelope curve of the phonocardiogram. For the evaluation, in contrast to other studies, measurements on 12 probands we...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/4/972 |
| _version_ | 1798038983570096128 |
|---|---|
| author | Angelika Thalmayer Samuel Zeising Georg Fischer Jens Kirchner |
| author_facet | Angelika Thalmayer Samuel Zeising Georg Fischer Jens Kirchner |
| author_sort | Angelika Thalmayer |
| collection | DOAJ |
| description | This paper proposes a robust and real-time capable algorithm for classification of the first and second heart sounds. The classification algorithm is based on the evaluation of the envelope curve of the phonocardiogram. For the evaluation, in contrast to other studies, measurements on 12 probands were conducted in different physiological conditions. Moreover, for each measurement the auscultation point, posture and physical stress were varied. The proposed envelope-based algorithm is tested with two different methods for envelope curve extraction: the Hilbert transform and the short-time Fourier transform. The performance of the classification of the first heart sounds is evaluated by using a reference electrocardiogram. Overall, by using the Hilbert transform, the algorithm has a better performance regarding the F<sub>1</sub>-score and computational effort. The proposed algorithm achieves for the S<sub>1</sub> classification an F<sub>1</sub>-score up to 95.7% and in average 90.5%. The algorithm is robust against the age, BMI, posture, heart rate and auscultation point (except measurements on the back) of the subjects. |
| first_indexed | 2024-04-11T21:47:40Z |
| format | Article |
| id | doaj.art-41160d6f85384c3db1d5ad12e36b3ae0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:47:40Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-41160d6f85384c3db1d5ad12e36b3ae02022-12-22T04:01:21ZengMDPI AGSensors1424-82202020-02-0120497210.3390/s20040972s20040972A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological ConditionsAngelika Thalmayer0Samuel Zeising1Georg Fischer2Jens Kirchner3Institute for Electronics Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91058 Erlangen, GermanyInstitute for Electronics Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91058 Erlangen, GermanyInstitute for Electronics Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91058 Erlangen, GermanyInstitute for Electronics Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91058 Erlangen, GermanyThis paper proposes a robust and real-time capable algorithm for classification of the first and second heart sounds. The classification algorithm is based on the evaluation of the envelope curve of the phonocardiogram. For the evaluation, in contrast to other studies, measurements on 12 probands were conducted in different physiological conditions. Moreover, for each measurement the auscultation point, posture and physical stress were varied. The proposed envelope-based algorithm is tested with two different methods for envelope curve extraction: the Hilbert transform and the short-time Fourier transform. The performance of the classification of the first heart sounds is evaluated by using a reference electrocardiogram. Overall, by using the Hilbert transform, the algorithm has a better performance regarding the F<sub>1</sub>-score and computational effort. The proposed algorithm achieves for the S<sub>1</sub> classification an F<sub>1</sub>-score up to 95.7% and in average 90.5%. The algorithm is robust against the age, BMI, posture, heart rate and auscultation point (except measurements on the back) of the subjects.https://www.mdpi.com/1424-8220/20/4/972heart soundsenvelopehilbert transformshort-time fourier transformclassificationreal-timeauscultationrobust |
| spellingShingle | Angelika Thalmayer Samuel Zeising Georg Fischer Jens Kirchner A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions Sensors heart sounds envelope hilbert transform short-time fourier transform classification real-time auscultation robust |
| title | A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions |
| title_full | A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions |
| title_fullStr | A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions |
| title_full_unstemmed | A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions |
| title_short | A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions |
| title_sort | robust and real time capable envelope based algorithm for heart sound classification validation under different physiological conditions |
| topic | heart sounds envelope hilbert transform short-time fourier transform classification real-time auscultation robust |
| url | https://www.mdpi.com/1424-8220/20/4/972 |
| work_keys_str_mv | AT angelikathalmayer arobustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT samuelzeising arobustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT georgfischer arobustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT jenskirchner arobustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT angelikathalmayer robustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT samuelzeising robustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT georgfischer robustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions AT jenskirchner robustandrealtimecapableenvelopebasedalgorithmforheartsoundclassificationvalidationunderdifferentphysiologicalconditions |