Multi-scale features for heartbeat classification using directed acyclic graph CNN
A new architecture of deep neural networks, directed acyclic graph convolutional neural networks (DAG-CNNs), is used to classify heartbeats from electrocardiogram (ECG) signals into different subject-based classes. DAG-CNNs not only fuse the feature extraction and classification stages of the ECG cl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2018-09-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | http://dx.doi.org/10.1080/08839514.2018.1501910 |
| _version_ | 1797684855930093568 |
|---|---|
| author | Zahra Golrizkhatami Shahram Taheri Adnan Acan |
| author_facet | Zahra Golrizkhatami Shahram Taheri Adnan Acan |
| author_sort | Zahra Golrizkhatami |
| collection | DOAJ |
| description | A new architecture of deep neural networks, directed acyclic graph convolutional neural networks (DAG-CNNs), is used to classify heartbeats from electrocardiogram (ECG) signals into different subject-based classes. DAG-CNNs not only fuse the feature extraction and classification stages of the ECG classification into a single automated learning procedure, but also utilized multi-scale features and perform score-level fusion of multiple classifiers automatically. Therefore, DAG-CNN negates the necessity to extract hand-crafted features. In most of the current approaches, only the high level features which extracted by the last layer of CNN are used. Instead of performing feature level fusion manually and feeding the results into a classifier, the proposed multi-scale system can automatically learn different level of features, combine them and predict the output label. The results over the MIT-BIH arrhythmia benchmarks database demonstrate that the proposed system achieves a superior classification performance compared to most of the state-of-the-art methods. |
| first_indexed | 2024-03-12T00:36:51Z |
| format | Article |
| id | doaj.art-10836742ed31494bb6b39d00db2a7e35 |
| institution | Directory Open Access Journal |
| issn | 0883-9514 1087-6545 |
| language | English |
| last_indexed | 2024-03-12T00:36:51Z |
| publishDate | 2018-09-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj.art-10836742ed31494bb6b39d00db2a7e352023-09-15T09:33:56ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452018-09-01327-861362810.1080/08839514.2018.15019101501910Multi-scale features for heartbeat classification using directed acyclic graph CNNZahra Golrizkhatami0Shahram Taheri1Adnan Acan2Eastern Mediterranean UniversityEastern Mediterranean UniversityEastern Mediterranean UniversityA new architecture of deep neural networks, directed acyclic graph convolutional neural networks (DAG-CNNs), is used to classify heartbeats from electrocardiogram (ECG) signals into different subject-based classes. DAG-CNNs not only fuse the feature extraction and classification stages of the ECG classification into a single automated learning procedure, but also utilized multi-scale features and perform score-level fusion of multiple classifiers automatically. Therefore, DAG-CNN negates the necessity to extract hand-crafted features. In most of the current approaches, only the high level features which extracted by the last layer of CNN are used. Instead of performing feature level fusion manually and feeding the results into a classifier, the proposed multi-scale system can automatically learn different level of features, combine them and predict the output label. The results over the MIT-BIH arrhythmia benchmarks database demonstrate that the proposed system achieves a superior classification performance compared to most of the state-of-the-art methods.http://dx.doi.org/10.1080/08839514.2018.1501910 |
| spellingShingle | Zahra Golrizkhatami Shahram Taheri Adnan Acan Multi-scale features for heartbeat classification using directed acyclic graph CNN Applied Artificial Intelligence |
| title | Multi-scale features for heartbeat classification using directed acyclic graph CNN |
| title_full | Multi-scale features for heartbeat classification using directed acyclic graph CNN |
| title_fullStr | Multi-scale features for heartbeat classification using directed acyclic graph CNN |
| title_full_unstemmed | Multi-scale features for heartbeat classification using directed acyclic graph CNN |
| title_short | Multi-scale features for heartbeat classification using directed acyclic graph CNN |
| title_sort | multi scale features for heartbeat classification using directed acyclic graph cnn |
| url | http://dx.doi.org/10.1080/08839514.2018.1501910 |
| work_keys_str_mv | AT zahragolrizkhatami multiscalefeaturesforheartbeatclassificationusingdirectedacyclicgraphcnn AT shahramtaheri multiscalefeaturesforheartbeatclassificationusingdirectedacyclicgraphcnn AT adnanacan multiscalefeaturesforheartbeatclassificationusingdirectedacyclicgraphcnn |