Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform
Currently, there are many works in the literature focused on the analysis of heart sounds, specifically on the development of intelligent systems for the classification of normal and abnormal heart sounds. However, the available heart sound databases are not yet large enough to train generalized mac...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/19/7003 |
| _version_ | 1797551557526421504 |
|---|---|
| author | Pedro Narváez Winston S. Percybrooks |
| author_facet | Pedro Narváez Winston S. Percybrooks |
| author_sort | Pedro Narváez |
| collection | DOAJ |
| description | Currently, there are many works in the literature focused on the analysis of heart sounds, specifically on the development of intelligent systems for the classification of normal and abnormal heart sounds. However, the available heart sound databases are not yet large enough to train generalized machine learning models. Therefore, there is interest in the development of algorithms capable of generating heart sounds that could augment current databases. In this article, we propose a model based on generative adversary networks (GANs) to generate normal synthetic heart sounds. Additionally, a denoising algorithm is implemented using the empirical wavelet transform (EWT), allowing a decrease in the number of epochs and the computational cost that the GAN model requires. A distortion metric (mel–cepstral distortion) was used to objectively assess the quality of synthetic heart sounds. The proposed method was favorably compared with a mathematical model that is based on the morphology of the phonocardiography (PCG) signal published as the state of the art. Additionally, different heart sound classification models proposed as state-of-the-art were also used to test the performance of such models when the GAN-generated synthetic signals were used as test dataset. In this experiment, good accuracy results were obtained with most of the implemented models, suggesting that the GAN-generated sounds correctly capture the characteristics of natural heart sounds. |
| first_indexed | 2024-03-10T15:47:50Z |
| format | Article |
| id | doaj.art-6c0d52fe59c847f2b79bffae708fa37e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:47:50Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6c0d52fe59c847f2b79bffae708fa37e2023-11-20T16:21:00ZengMDPI AGApplied Sciences2076-34172020-10-011019700310.3390/app10197003Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet TransformPedro Narváez0Winston S. Percybrooks1Department of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081001, ColombiaDepartment of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081001, ColombiaCurrently, there are many works in the literature focused on the analysis of heart sounds, specifically on the development of intelligent systems for the classification of normal and abnormal heart sounds. However, the available heart sound databases are not yet large enough to train generalized machine learning models. Therefore, there is interest in the development of algorithms capable of generating heart sounds that could augment current databases. In this article, we propose a model based on generative adversary networks (GANs) to generate normal synthetic heart sounds. Additionally, a denoising algorithm is implemented using the empirical wavelet transform (EWT), allowing a decrease in the number of epochs and the computational cost that the GAN model requires. A distortion metric (mel–cepstral distortion) was used to objectively assess the quality of synthetic heart sounds. The proposed method was favorably compared with a mathematical model that is based on the morphology of the phonocardiography (PCG) signal published as the state of the art. Additionally, different heart sound classification models proposed as state-of-the-art were also used to test the performance of such models when the GAN-generated synthetic signals were used as test dataset. In this experiment, good accuracy results were obtained with most of the implemented models, suggesting that the GAN-generated sounds correctly capture the characteristics of natural heart sounds.https://www.mdpi.com/2076-3417/10/19/7003generative adversarial networkheart sound classificationEWTsound synthesismachine learninge-health |
| spellingShingle | Pedro Narváez Winston S. Percybrooks Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform Applied Sciences generative adversarial network heart sound classification EWT sound synthesis machine learning e-health |
| title | Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform |
| title_full | Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform |
| title_fullStr | Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform |
| title_full_unstemmed | Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform |
| title_short | Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform |
| title_sort | synthesis of normal heart sounds using generative adversarial networks and empirical wavelet transform |
| topic | generative adversarial network heart sound classification EWT sound synthesis machine learning e-health |
| url | https://www.mdpi.com/2076-3417/10/19/7003 |
| work_keys_str_mv | AT pedronarvaez synthesisofnormalheartsoundsusinggenerativeadversarialnetworksandempiricalwavelettransform AT winstonspercybrooks synthesisofnormalheartsoundsusinggenerativeadversarialnetworksandempiricalwavelettransform |