Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks
The paper describes a process of formulating a classifier on the basis information contained by MIT-BIH arrhythmia database. This data source contains electrocardiographic signals from two sensors. Both were used, which represent not a typical phenomenon. In the learning process, the classifier uses...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Computer Methods and Programs in Biomedicine Update |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266699002200026X |
| _version_ | 1811178063131574272 |
|---|---|
| author | Dominik Siekierski Krzysztof Siwek |
| author_facet | Dominik Siekierski Krzysztof Siwek |
| author_sort | Dominik Siekierski |
| collection | DOAJ |
| description | The paper describes a process of formulating a classifier on the basis information contained by MIT-BIH arrhythmia database. This data source contains electrocardiographic signals from two sensors. Both were used, which represent not a typical phenomenon. In the learning process, the classifier uses only information with high certainty. Data are based on expert endorsements and the errors found have been corrected over the years. Specific types of heartbeats were divided into special groups according to the standard ''Association for the Advancement of Medical Instrumentation'' (AAMI). It recommends splitting the specific types into five separate groups according to physiological origin. Rare heartbeats have a limited number of occurrences. For one group, modifying methods were used which allowed to increase sufficiently the amount of data in training sets. This had a beneficial impact on the results. The solution includes features extraction. The main module of the classifier is a deep neural network. Good result was obtained with tools supporting automatic hyperparameter selection. In ECG signal diagnostics, the most significant task is to properly separate the group of supraventricular and ventricular beats. The study managed to obtain this error at an exceptionally low level and an overall accuracy of 98.37%. |
| first_indexed | 2024-04-11T06:13:07Z |
| format | Article |
| id | doaj.art-8bf1c578632f4f28be2e94618f54b9b5 |
| institution | Directory Open Access Journal |
| issn | 2666-9900 |
| language | English |
| last_indexed | 2024-04-11T06:13:07Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computer Methods and Programs in Biomedicine Update |
| spelling | doaj.art-8bf1c578632f4f28be2e94618f54b9b52022-12-22T04:41:09ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002022-01-012100075Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocksDominik Siekierski0Krzysztof Siwek1Corresponding author.; Faculty of Electrical Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electrical Engineering, Warsaw University of Technology, Warsaw, PolandThe paper describes a process of formulating a classifier on the basis information contained by MIT-BIH arrhythmia database. This data source contains electrocardiographic signals from two sensors. Both were used, which represent not a typical phenomenon. In the learning process, the classifier uses only information with high certainty. Data are based on expert endorsements and the errors found have been corrected over the years. Specific types of heartbeats were divided into special groups according to the standard ''Association for the Advancement of Medical Instrumentation'' (AAMI). It recommends splitting the specific types into five separate groups according to physiological origin. Rare heartbeats have a limited number of occurrences. For one group, modifying methods were used which allowed to increase sufficiently the amount of data in training sets. This had a beneficial impact on the results. The solution includes features extraction. The main module of the classifier is a deep neural network. Good result was obtained with tools supporting automatic hyperparameter selection. In ECG signal diagnostics, the most significant task is to properly separate the group of supraventricular and ventricular beats. The study managed to obtain this error at an exceptionally low level and an overall accuracy of 98.37%.http://www.sciencedirect.com/science/article/pii/S266699002200026XHeartbeat classificationArrhythmiaECG signalDeep learningSpectrogram |
| spellingShingle | Dominik Siekierski Krzysztof Siwek Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks Computer Methods and Programs in Biomedicine Update Heartbeat classification Arrhythmia ECG signal Deep learning Spectrogram |
| title | Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks |
| title_full | Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks |
| title_fullStr | Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks |
| title_full_unstemmed | Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks |
| title_short | Heart beats classification method using a multi-signal ECG spectrogram and convolutional neural network with residual blocks |
| title_sort | heart beats classification method using a multi signal ecg spectrogram and convolutional neural network with residual blocks |
| topic | Heartbeat classification Arrhythmia ECG signal Deep learning Spectrogram |
| url | http://www.sciencedirect.com/science/article/pii/S266699002200026X |
| work_keys_str_mv | AT dominiksiekierski heartbeatsclassificationmethodusingamultisignalecgspectrogramandconvolutionalneuralnetworkwithresidualblocks AT krzysztofsiwek heartbeatsclassificationmethodusingamultisignalecgspectrogramandconvolutionalneuralnetworkwithresidualblocks |