NEURAL NETWORK AUTOENCODER MODEL FOR FORMING REDUCED VECTOR CHARACTERISTICS OF ECG SIGNALS
The paper considers the actual problem of improving neural network models for the classification of cardiovascular pathologies by compressing the information contained in electrocardiographic (ECG) signals. Due to the active implementation of artificial intelligence in medical diagnostics, the study...
Saved in:
| Published in: | Bulletin of Kyiv Polytechnic Institute. Series Instrument Making no. 69(1); pp. 93 - 105 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
28.06.2025
|
| ISSN: | 0321-2211, 2663-3450 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The paper considers the actual problem of improving neural network models for the classification of cardiovascular pathologies by compressing the information contained in electrocardiographic (ECG) signals. Due to the active implementation of artificial intelligence in medical diagnostics, the study focuses on creating a reduced ECG feature vector that allows for a significant reduction in training data volume without losing important diagnostic information. The research is dedicated to the development of an autoencoder model with a specialized architecture that combines convolutional and fully connected layers, attention layers, residual connections, and a symmetric structure with shared weights. This approach enables not only to compress the input multichannel signal but also to form a latent space from which the signal can be restored or used as a feature vector for classification. In the proposed autoencoder architecture, the latent representation is combined with the layer weight vector into a single reduced vector that contains information about both the shape and the structural features of the ECG signal. The model was trained using a composite loss function, which allows for balancing between signal reconstruction quality and classification accuracy. To evaluate the model, several alternative dimensionality reduction methods were used, including downsampling, transformation to Frank's orthogonal leads, calculation of a resultant vector, and principal component analysis (PCA). A number of alternative dimensionality reduction methods were used to test the model: reduction of the sampling frequency; transformation to Frank orthogonal derivations; calculation of the resulting vector; principal component analysis (PCA). All methods were tested on the PTB-XL dataset, which contains 12-lead ECG recordings with a wide range of cardiovascular pathologies. The effectiveness of the reduced feature vector was assessed using two models—a convolutional neural network (EcgNet) and a fully connected network with two hidden layers. The analysis of the results showed that, on average, classification accuracy using the reduced vector decreased by only 2% for EcgNet and increased by 3–6% for the fully connected network, indicating preservation of diagnostic information even with a high compression ratio of 25. In contrast, traditional dimensionality reduction methods such as PCA and orthogonal transformation showed a significant deterioration in classification quality (up to –16%). While downsampling to 75 Hz significantly reduces data volume, it also leads to the loss of high-frequency information critical for detecting ischemia and arrhythmias. Particular attention is given to ventricular and atrial late potentials, which are low-amplitude and high-frequency in nature. The constructed reduced feature vector preserved the informative characteristics of these classes, resulting in improved classification accuracy compared to traditional dimensionality reduction methods. Thus, the developed reduced feature vector demonstrates the ability to retain diagnostic information under significant ECG data compression, achieving a balance between computational efficiency, classification accuracy, and application versatility. The obtained results suggest that the use of the proposed reduced feature vector may serve as a promising solution for compact and efficient systems for automated ECG analysis, particularly in mobile or computing-limited systems, while also enabling faster development and testing of new neural network models for diagnostics. |
|---|---|
| AbstractList | The paper considers the actual problem of improving neural network models for the classification of cardiovascular pathologies by compressing the information contained in electrocardiographic (ECG) signals. Due to the active implementation of artificial intelligence in medical diagnostics, the study focuses on creating a reduced ECG feature vector that allows for a significant reduction in training data volume without losing important diagnostic information. The research is dedicated to the development of an autoencoder model with a specialized architecture that combines convolutional and fully connected layers, attention layers, residual connections, and a symmetric structure with shared weights. This approach enables not only to compress the input multichannel signal but also to form a latent space from which the signal can be restored or used as a feature vector for classification. In the proposed autoencoder architecture, the latent representation is combined with the layer weight vector into a single reduced vector that contains information about both the shape and the structural features of the ECG signal. The model was trained using a composite loss function, which allows for balancing between signal reconstruction quality and classification accuracy. To evaluate the model, several alternative dimensionality reduction methods were used, including downsampling, transformation to Frank's orthogonal leads, calculation of a resultant vector, and principal component analysis (PCA). A number of alternative dimensionality reduction methods were used to test the model: reduction of the sampling frequency; transformation to Frank orthogonal derivations; calculation of the resulting vector; principal component analysis (PCA). All methods were tested on the PTB-XL dataset, which contains 12-lead ECG recordings with a wide range of cardiovascular pathologies. The effectiveness of the reduced feature vector was assessed using two models—a convolutional neural network (EcgNet) and a fully connected network with two hidden layers. The analysis of the results showed that, on average, classification accuracy using the reduced vector decreased by only 2% for EcgNet and increased by 3–6% for the fully connected network, indicating preservation of diagnostic information even with a high compression ratio of 25. In contrast, traditional dimensionality reduction methods such as PCA and orthogonal transformation showed a significant deterioration in classification quality (up to –16%). While downsampling to 75 Hz significantly reduces data volume, it also leads to the loss of high-frequency information critical for detecting ischemia and arrhythmias. Particular attention is given to ventricular and atrial late potentials, which are low-amplitude and high-frequency in nature. The constructed reduced feature vector preserved the informative characteristics of these classes, resulting in improved classification accuracy compared to traditional dimensionality reduction methods. Thus, the developed reduced feature vector demonstrates the ability to retain diagnostic information under significant ECG data compression, achieving a balance between computational efficiency, classification accuracy, and application versatility. The obtained results suggest that the use of the proposed reduced feature vector may serve as a promising solution for compact and efficient systems for automated ECG analysis, particularly in mobile or computing-limited systems, while also enabling faster development and testing of new neural network models for diagnostics. |
| Author | Mnevec, Anton Ivanushkina, Natalia |
| Author_xml | – sequence: 1 givenname: Anton orcidid: 0000-0001-5448-4045 surname: Mnevec fullname: Mnevec, Anton – sequence: 2 givenname: Natalia orcidid: 0000-0001-8389-7906 surname: Ivanushkina fullname: Ivanushkina, Natalia |
| BookMark | eNotkDtPwzAYRS1UJErpb8AjDCn-_EzGyHXTiDSRHBckFisvS5WgRcnEv6elDPde6Qx3OPdodjwdB4QegawoEUy8QKLISiZP8HwGVKwYg4SSGzSnUrKIcUFmaE4YhYhSgDu0nKZDSyQolijO5-ijNHubFrg07r2yrzjdu8qUulobi3fnLvCmspfs8jLD1qz32qzxm9HujPU2tal2xua1y3WNqw02OsN1npVpUT-g29B8TsPyfxfIbYzT26ioslynRdQlkkSt4G0vRExj2UqietErCC0VIUggnErWBUKVlECHOMRd27FeCSZ7FjcN77hgC6Sut914mqZxCP57PHw1448H4v8k-YskLxMP3l8k-ask9gsX7VOP |
| ContentType | Journal Article |
| DBID | AAYXX CITATION |
| DOI | 10.20535/1970.69(1).2025.331920 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2663-3450 |
| EndPage | 105 |
| ExternalDocumentID | 10_20535_1970_69_1__2025_331920 |
| GroupedDBID | AAYXX CITATION |
| ID | FETCH-LOGICAL-c960-b54bd558286b607d5d71fb25ff6104263cf0276612e8f8cbc3d7536d38aa4c453 |
| ISSN | 0321-2211 |
| IngestDate | Sat Nov 29 07:48:29 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Issue | 69(1) |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c960-b54bd558286b607d5d71fb25ff6104263cf0276612e8f8cbc3d7536d38aa4c453 |
| ORCID | 0000-0001-5448-4045 0000-0001-8389-7906 |
| OpenAccessLink | https://visnykpb.kpi.ua/article/download/331920/322714 |
| PageCount | 13 |
| ParticipantIDs | crossref_primary_10_20535_1970_69_1__2025_331920 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-06-28 |
| PublicationDateYYYYMMDD | 2025-06-28 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-06-28 day: 28 |
| PublicationDecade | 2020 |
| PublicationTitle | Bulletin of Kyiv Polytechnic Institute. Series Instrument Making |
| PublicationYear | 2025 |
| SSID | ssib061739744 ssib044764647 |
| Score | 1.9130275 |
| Snippet | The paper considers the actual problem of improving neural network models for the classification of cardiovascular pathologies by compressing the information... |
| SourceID | crossref |
| SourceType | Index Database |
| StartPage | 93 |
| Title | NEURAL NETWORK AUTOENCODER MODEL FOR FORMING REDUCED VECTOR CHARACTERISTICS OF ECG SIGNALS |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2663-3450 dateEnd: 99991231 omitProxy: false ssIdentifier: ssib044764647 issn: 0321-2211 databaseCode: M~E dateStart: 19700101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FwoELAgGC8tAeOIAsB3sffhwj1y1R80CpKRUXy7tei0rIVLRE7YXfw89kxrtOTDlADxxiRatkvMl8nsfu7DeEvDKxkMLIxK_Bvfii0tJXcVz7XGkjlVCcde2AjmfxYpGcnKTvR6Of_VmY9Ze4bZPLy_Tsv6oaxkDZeHT2BureCIUBeA9KhyuoHa7_pPhF_mE1mXmLvPi4XB16MKtlDpn7Xr7y5nCdeZD34WuO61Qr7LyT73nHeVYskSBhsppkEOFOj4pp1rU1z7MD72h6gEV-v20AO9puDDYPr07XWEh3ZQlh9bYCYYy2CHLxbgRpGtoLb971v9ooujVrox2NwbYkYAoB_vfzz_DJyvoAJGqshksUTGIpFRtY1YCz0GfMWVXTjUFgwH0uLOusA1mUIjlVvwRiLartn-h8c9gd0f7D7DMkqcEliDQOxhshY5zKmIONYcHW2_U7_Nec4KY0EZKiTlyJwsooLcOyREGlFXSL3GaxTLF4cP4j7y2XEHEkBsRsEBZCnCcsd5n77ba4sJP91k30dfhmOMlBaDSIcYr75J5LTujEguoBGZn2IflkAUUdoOgAULQDFAUwUQco6gBFLaDoNUDR5T4FQFEHqEek2M-L7J3vOnL4GjJdX0mhaokbrZGKgriWdRw2ismmgSAcmf91E8CzDUGzSZpEK81ryIajmidVJbSQ_DHZab-25gmhTCcsVEmipKrAbQRVEMEtjGacVykEsU9J0P8X5ZnlXSn_oprdm3_lGbm7xetzsgNPgnlB7uj1xen5t5edin8BSxBlag |
| linkProvider | ISSN International Centre |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=NEURAL+NETWORK+AUTOENCODER+MODEL+FOR+FORMING+REDUCED+VECTOR+CHARACTERISTICS+OF+ECG+SIGNALS&rft.jtitle=Bulletin+of+Kyiv+Polytechnic+Institute.+Series+Instrument+Making&rft.au=Mnevec%2C+Anton&rft.au=Ivanushkina%2C+Natalia&rft.date=2025-06-28&rft.issn=0321-2211&rft.eissn=2663-3450&rft.issue=69%281%29&rft.spage=93&rft.epage=105&rft_id=info:doi/10.20535%2F1970.69%281%29.2025.331920&rft.externalDBID=n%2Fa&rft.externalDocID=10_20535_1970_69_1__2025_331920 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0321-2211&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0321-2211&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0321-2211&client=summon |