Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data
Arrhythmia detection through deep learning is mainly classified through supervised learning. Supervised learning progresses through the labeled data. However, in the medical field, it is challenging to collect ECG data of patients with arrhythmia than ECG data of healthy people, and thus data bias o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9110549/ |
| _version_ | 1819276397736099840 |
|---|---|
| author | Dong-Hoon Shin Roy C. Park Kyungyong Chung |
| author_facet | Dong-Hoon Shin Roy C. Park Kyungyong Chung |
| author_sort | Dong-Hoon Shin |
| collection | DOAJ |
| description | Arrhythmia detection through deep learning is mainly classified through supervised learning. Supervised learning progresses through the labeled data. However, in the medical field, it is challenging to collect ECG data of patients with arrhythmia than ECG data of healthy people, and thus data bias occurs. Therefore, if you use a supervised learning model, there are problems with lack of data and imbalance between labels that arise during learning. Accordingly, this study proposes the decision boundary-based Anomaly detection model using improved AnoGAN from ECG data. In this study, at the time of learning, the loss of the Generator does not reduce, but the loss of a Discriminator lowers. Even if the Generator and Discriminator were designed to have the same learning count, the learning competency of Generator was judged to be lowered. In repeated experiments, it was found that the best loss balance was achieved when the learning count of Discriminator was 1 and that of Generator was 4. Another problem is that the decision boundary of AnoGAN is subjective. Accordingly, the repeated experiments based on F-measure are conducted to determine a decision boundary. For performance evaluation, the accuracy of the model is evaluated on the basis of Epoch, and the goodness-of-fit of the model is evaluated on the basis of AUC and F-measure. According to the evaluation of F-measure, the model has the best performance when the decision boundary is 200. In terms of Epoch, the model has the highest accuracy when the Epoch is 10. In addition, the proposed model has better goodness-of-fit than AnoGAN. |
| first_indexed | 2024-12-23T23:39:34Z |
| format | Article |
| id | doaj.art-50dd565675334155add5a5556a4aefc8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:39:34Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-50dd565675334155add5a5556a4aefc82022-12-21T17:25:43ZengIEEEIEEE Access2169-35362020-01-01810866410867410.1109/ACCESS.2020.30006389110549Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG DataDong-Hoon Shin0https://orcid.org/0000-0003-2616-0865Roy C. Park1https://orcid.org/0000-0002-4348-9753Kyungyong Chung2https://orcid.org/0000-0002-6439-9992Department of Computer Science, Kyonggi University, Suwon, South KoreaDepartment of Information Communication Software Engineering, Sangji University, Wonju, South KoreaDivision of Computer Science and Engineering, Kyonggi University, Suwon, South KoreaArrhythmia detection through deep learning is mainly classified through supervised learning. Supervised learning progresses through the labeled data. However, in the medical field, it is challenging to collect ECG data of patients with arrhythmia than ECG data of healthy people, and thus data bias occurs. Therefore, if you use a supervised learning model, there are problems with lack of data and imbalance between labels that arise during learning. Accordingly, this study proposes the decision boundary-based Anomaly detection model using improved AnoGAN from ECG data. In this study, at the time of learning, the loss of the Generator does not reduce, but the loss of a Discriminator lowers. Even if the Generator and Discriminator were designed to have the same learning count, the learning competency of Generator was judged to be lowered. In repeated experiments, it was found that the best loss balance was achieved when the learning count of Discriminator was 1 and that of Generator was 4. Another problem is that the decision boundary of AnoGAN is subjective. Accordingly, the repeated experiments based on F-measure are conducted to determine a decision boundary. For performance evaluation, the accuracy of the model is evaluated on the basis of Epoch, and the goodness-of-fit of the model is evaluated on the basis of AUC and F-measure. According to the evaluation of F-measure, the model has the best performance when the decision boundary is 200. In terms of Epoch, the model has the highest accuracy when the Epoch is 10. In addition, the proposed model has better goodness-of-fit than AnoGAN.https://ieeexplore.ieee.org/document/9110549/Heart diseasearrhythmiahealth caredeep learningelectrocardiogramgenerative adversarial network |
| spellingShingle | Dong-Hoon Shin Roy C. Park Kyungyong Chung Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data IEEE Access Heart disease arrhythmia health care deep learning electrocardiogram generative adversarial network |
| title | Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data |
| title_full | Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data |
| title_fullStr | Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data |
| title_full_unstemmed | Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data |
| title_short | Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data |
| title_sort | decision boundary based anomaly detection model using improved anogan from ecg data |
| topic | Heart disease arrhythmia health care deep learning electrocardiogram generative adversarial network |
| url | https://ieeexplore.ieee.org/document/9110549/ |
| work_keys_str_mv | AT donghoonshin decisionboundarybasedanomalydetectionmodelusingimprovedanoganfromecgdata AT roycpark decisionboundarybasedanomalydetectionmodelusingimprovedanoganfromecgdata AT kyungyongchung decisionboundarybasedanomalydetectionmodelusingimprovedanoganfromecgdata |