A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression
Arrhythmia classification is crucial in electrocardiogram (ECG) based automatic cardiovascular disease diagnosis, e.g., to help prevent stroke or sudden cardiac death. However, the complex individual differences in ECG morphology make it challenging in accurately categorizing arrhythmia heartbeats....
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/139611 |
| _version_ | 1811696727039672320 |
|---|---|
| author | Yang, Jianli Bai, Yang Lin, Feng Liu, Ming Hou, Zengguang Liu, Xiuling |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Yang, Jianli Bai, Yang Lin, Feng Liu, Ming Hou, Zengguang Liu, Xiuling |
| author_sort | Yang, Jianli |
| collection | NTU |
| description | Arrhythmia classification is crucial in electrocardiogram (ECG) based automatic cardiovascular disease diagnosis, e.g., to help prevent stroke or sudden cardiac death. However, the complex individual differences in ECG morphology make it challenging in accurately categorizing arrhythmia heartbeats. To promote robustness of the algorithm for individual differences, we propose a novel ECG arrhythmia classification method with stacked sparse auto-encoders (SSAEs) and a softmax regression (SF) model. The SSAEs is employed to hierarchically extract high-level features from huge amount of ECG data. Features are extracted automatically such that no individual difference in feature selection will bias extraction accuracy. Moreover, the input can be reconstructed completely by the features in each level of the auto-encoder. The SF is then trained to serve as a classifier for discriminating six different types of arrhythmia heartbeats. Computational experiments and comparative analyses are presented to validate the effectiveness of the theoretical models. |
| first_indexed | 2024-10-01T07:43:57Z |
| format | Journal Article |
| id | ntu-10356/139611 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:43:57Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1396112020-05-20T08:12:17Z A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression Yang, Jianli Bai, Yang Lin, Feng Liu, Ming Hou, Zengguang Liu, Xiuling School of Computer Science and Engineering Engineering::Computer science and engineering Stacked Sparse Auto-encoders ECG Arrhythmia Classification Arrhythmia classification is crucial in electrocardiogram (ECG) based automatic cardiovascular disease diagnosis, e.g., to help prevent stroke or sudden cardiac death. However, the complex individual differences in ECG morphology make it challenging in accurately categorizing arrhythmia heartbeats. To promote robustness of the algorithm for individual differences, we propose a novel ECG arrhythmia classification method with stacked sparse auto-encoders (SSAEs) and a softmax regression (SF) model. The SSAEs is employed to hierarchically extract high-level features from huge amount of ECG data. Features are extracted automatically such that no individual difference in feature selection will bias extraction accuracy. Moreover, the input can be reconstructed completely by the features in each level of the auto-encoder. The SF is then trained to serve as a classifier for discriminating six different types of arrhythmia heartbeats. Computational experiments and comparative analyses are presented to validate the effectiveness of the theoretical models. 2020-05-20T08:12:17Z 2020-05-20T08:12:17Z 2017 Journal Article Yang, J., Bai, Y., Lin, F., Hou, Z., & Liu, X. (2018). A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression. International Journal of Machine Learning and Cybernetics, 9(10), 1733-1740. doi:10.1007/s13042-017-0677-5 1868-8071 https://hdl.handle.net/10356/139611 10.1007/s13042-017-0677-5 2-s2.0-85052849353 10 9 1733 1740 en International Journal of Machine Learning and Cybernetics © 2017 Springer-Verlag Berlin Heidelberg. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Stacked Sparse Auto-encoders ECG Arrhythmia Classification Yang, Jianli Bai, Yang Lin, Feng Liu, Ming Hou, Zengguang Liu, Xiuling A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title | A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title_full | A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title_fullStr | A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title_full_unstemmed | A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title_short | A novel electrocardiogram arrhythmia classification method based on stacked sparse auto-encoders and softmax regression |
| title_sort | novel electrocardiogram arrhythmia classification method based on stacked sparse auto encoders and softmax regression |
| topic | Engineering::Computer science and engineering Stacked Sparse Auto-encoders ECG Arrhythmia Classification |
| url | https://hdl.handle.net/10356/139611 |
| work_keys_str_mv | AT yangjianli anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT baiyang anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT linfeng anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT liuming anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT houzengguang anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT liuxiuling anovelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT yangjianli novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT baiyang novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT linfeng novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT liuming novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT houzengguang novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression AT liuxiuling novelelectrocardiogramarrhythmiaclassificationmethodbasedonstackedsparseautoencodersandsoftmaxregression |