Cargando…
Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models
Electroencephalography (EEG) is often used to evaluate several types of neurological brain disorders because of its noninvasive and high temporal resolution. In contrast to electrocardiography (ECG), EEG can be uncomfortable and inconvenient for patients. Moreover, deep-learning techniques require a...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007254/ https://www.ncbi.nlm.nih.gov/pubmed/36904661 http://dx.doi.org/10.3390/s23052458 |
_version_ | 1784905474213150720 |
---|---|
author | Yang, Chia-Yen Chen, Pin-Chen Huang, Wen-Chen |
author_facet | Yang, Chia-Yen Chen, Pin-Chen Huang, Wen-Chen |
author_sort | Yang, Chia-Yen |
collection | PubMed |
description | Electroencephalography (EEG) is often used to evaluate several types of neurological brain disorders because of its noninvasive and high temporal resolution. In contrast to electrocardiography (ECG), EEG can be uncomfortable and inconvenient for patients. Moreover, deep-learning techniques require a large dataset and a long time for training from scratch. Therefore, in this study, EEG–EEG or EEG–ECG transfer learning strategies were applied to explore their effectiveness for the training of simple cross-domain convolutional neural networks (CNNs) used in seizure prediction and sleep staging systems, respectively. The seizure model detected interictal and preictal periods, whereas the sleep staging model classified signals into five stages. The patient-specific seizure prediction model with six frozen layers achieved 100% accuracy for seven out of nine patients and required only 40 s of training time for personalization. Moreover, the cross-signal transfer learning EEG–ECG model for sleep staging achieved an accuracy approximately 2.5% higher than that of the ECG model; additionally, the training time was reduced by >50%. In summary, transfer learning from an EEG model to produce personalized models for a more convenient signal can both reduce the training time and increase the accuracy; moreover, challenges such as data insufficiency, variability, and inefficiency can be effectively overcome. |
format | Online Article Text |
id | pubmed-10007254 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100072542023-03-12 Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models Yang, Chia-Yen Chen, Pin-Chen Huang, Wen-Chen Sensors (Basel) Article Electroencephalography (EEG) is often used to evaluate several types of neurological brain disorders because of its noninvasive and high temporal resolution. In contrast to electrocardiography (ECG), EEG can be uncomfortable and inconvenient for patients. Moreover, deep-learning techniques require a large dataset and a long time for training from scratch. Therefore, in this study, EEG–EEG or EEG–ECG transfer learning strategies were applied to explore their effectiveness for the training of simple cross-domain convolutional neural networks (CNNs) used in seizure prediction and sleep staging systems, respectively. The seizure model detected interictal and preictal periods, whereas the sleep staging model classified signals into five stages. The patient-specific seizure prediction model with six frozen layers achieved 100% accuracy for seven out of nine patients and required only 40 s of training time for personalization. Moreover, the cross-signal transfer learning EEG–ECG model for sleep staging achieved an accuracy approximately 2.5% higher than that of the ECG model; additionally, the training time was reduced by >50%. In summary, transfer learning from an EEG model to produce personalized models for a more convenient signal can both reduce the training time and increase the accuracy; moreover, challenges such as data insufficiency, variability, and inefficiency can be effectively overcome. MDPI 2023-02-23 /pmc/articles/PMC10007254/ /pubmed/36904661 http://dx.doi.org/10.3390/s23052458 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yang, Chia-Yen Chen, Pin-Chen Huang, Wen-Chen Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title | Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title_full | Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title_fullStr | Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title_full_unstemmed | Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title_short | Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models |
title_sort | cross-domain transfer of eeg to eeg or ecg learning for cnn classification models |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007254/ https://www.ncbi.nlm.nih.gov/pubmed/36904661 http://dx.doi.org/10.3390/s23052458 |
work_keys_str_mv | AT yangchiayen crossdomaintransferofeegtoeegorecglearningforcnnclassificationmodels AT chenpinchen crossdomaintransferofeegtoeegorecglearningforcnnclassificationmodels AT huangwenchen crossdomaintransferofeegtoeegorecglearningforcnnclassificationmodels |