Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram
Abstract Heart health monitoring based on wearable devices is often contaminated by various noises to varying degrees. Using signal quality indicators (SQIs) to achieve signal quality assessment (SQA) is among the most promising ways to solve this problem, but the performance of SQIs in expressing E...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-09-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-022-00861-z |
| _version_ | 1797863121967120384 |
|---|---|
| author | Shuaiying Yuan Ziyang He Jianhui Zhao Zhiyong Yuan |
| author_facet | Shuaiying Yuan Ziyang He Jianhui Zhao Zhiyong Yuan |
| author_sort | Shuaiying Yuan |
| collection | DOAJ |
| description | Abstract Heart health monitoring based on wearable devices is often contaminated by various noises to varying degrees. Using signal quality indicators (SQIs) to achieve signal quality assessment (SQA) is among the most promising ways to solve this problem, but the performance of SQIs in expressing ECG quality features contaminated by motion artifact (MA) noise remains disappointing. Here, we present a novel SQA method that fuses the proposed depth local dual-view (DLDV) features and the dual-input transformer (DI-Transformer) framework to improve the recognition ability of MA-contaminated ECGs. The proposed DLDV features are to identify subtle differences between MA and ECG through depth local amplitude and phase angle features. When it fuses with the temporal relationship features extracted by DI-Transformer, its accuracy is significantly improved compared to the SQIs-based methods. In addition, we also verify the robustness and the accuracy of DLDV features on four traditional classifiers. Finally, we conduct our experiments on the two datasets. On the PhysioNet/Computing in Cardiology Challenge dataset, the DLDV features (Acc = 95.49%) outperform the combination of six SQIs features (Acc = 91.26%). When combined with our DI-Transformer, it delivered an accuracy of 99.62%, outperforming the state-of-the-art SQA methods. On the artificial testset constructed by MA noise, our DI-Transformer outperforms four traditional methods and also delivered an accuracy of 97.69%. |
| first_indexed | 2024-04-09T22:31:36Z |
| format | Article |
| id | doaj.art-457ad9c6261645c99ee14225083426ea |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-04-09T22:31:36Z |
| publishDate | 2022-09-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-457ad9c6261645c99ee14225083426ea2023-03-22T12:44:16ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-09-019198199910.1007/s40747-022-00861-zFusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogramShuaiying Yuan0Ziyang He1Jianhui Zhao2Zhiyong Yuan3School of Computer Science, Wuhan UniversitySchool of Computer Science, Wuhan UniversitySchool of Computer Science, Wuhan UniversitySchool of Computer Science, Wuhan UniversityAbstract Heart health monitoring based on wearable devices is often contaminated by various noises to varying degrees. Using signal quality indicators (SQIs) to achieve signal quality assessment (SQA) is among the most promising ways to solve this problem, but the performance of SQIs in expressing ECG quality features contaminated by motion artifact (MA) noise remains disappointing. Here, we present a novel SQA method that fuses the proposed depth local dual-view (DLDV) features and the dual-input transformer (DI-Transformer) framework to improve the recognition ability of MA-contaminated ECGs. The proposed DLDV features are to identify subtle differences between MA and ECG through depth local amplitude and phase angle features. When it fuses with the temporal relationship features extracted by DI-Transformer, its accuracy is significantly improved compared to the SQIs-based methods. In addition, we also verify the robustness and the accuracy of DLDV features on four traditional classifiers. Finally, we conduct our experiments on the two datasets. On the PhysioNet/Computing in Cardiology Challenge dataset, the DLDV features (Acc = 95.49%) outperform the combination of six SQIs features (Acc = 91.26%). When combined with our DI-Transformer, it delivered an accuracy of 99.62%, outperforming the state-of-the-art SQA methods. On the artificial testset constructed by MA noise, our DI-Transformer outperforms four traditional methods and also delivered an accuracy of 97.69%.https://doi.org/10.1007/s40747-022-00861-zDepth local dual-view (DLDV) featuresDual-input transformer (DI-Transformer)Motion artifacts (MA)Signal quality assessment (SQA)Electrocardiogram (ECG) |
| spellingShingle | Shuaiying Yuan Ziyang He Jianhui Zhao Zhiyong Yuan Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram Complex & Intelligent Systems Depth local dual-view (DLDV) features Dual-input transformer (DI-Transformer) Motion artifacts (MA) Signal quality assessment (SQA) Electrocardiogram (ECG) |
| title | Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram |
| title_full | Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram |
| title_fullStr | Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram |
| title_full_unstemmed | Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram |
| title_short | Fusing depth local dual-view features and dual-input transformer framework for improving the recognition ability of motion artifact-contaminated electrocardiogram |
| title_sort | fusing depth local dual view features and dual input transformer framework for improving the recognition ability of motion artifact contaminated electrocardiogram |
| topic | Depth local dual-view (DLDV) features Dual-input transformer (DI-Transformer) Motion artifacts (MA) Signal quality assessment (SQA) Electrocardiogram (ECG) |
| url | https://doi.org/10.1007/s40747-022-00861-z |
| work_keys_str_mv | AT shuaiyingyuan fusingdepthlocaldualviewfeaturesanddualinputtransformerframeworkforimprovingtherecognitionabilityofmotionartifactcontaminatedelectrocardiogram AT ziyanghe fusingdepthlocaldualviewfeaturesanddualinputtransformerframeworkforimprovingtherecognitionabilityofmotionartifactcontaminatedelectrocardiogram AT jianhuizhao fusingdepthlocaldualviewfeaturesanddualinputtransformerframeworkforimprovingtherecognitionabilityofmotionartifactcontaminatedelectrocardiogram AT zhiyongyuan fusingdepthlocaldualviewfeaturesanddualinputtransformerframeworkforimprovingtherecognitionabilityofmotionartifactcontaminatedelectrocardiogram |