Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models

Background/Objectives: The implementation of artificial intelligence-based systems for disease detection using biomedical signals is challenging due to the limited availability of training data. This paper deals with the generation of synthetic EEG signals using deep learning-based models, to be use...

Descripción completa

Detalles Bibliográficos
Autores: Alqaysi, Bakr Rashid, Rosa Zurera, Manuel|||0000-0002-3073-3278, Aldujaili, Ali Abdulameer
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/68756
Acceso en línea:http://hdl.handle.net/10017/68756
https://dx.doi.org/10.3390/ai6050089
Access Level:acceso abierto
Palabra clave:EEG
Time series
Synthetic data
LSTM
Telecomunicaciones
Telecommunication
id ES_c8f9fcb040f11ea41fb60cf97efadc4d
oai_identifier_str oai:ebuah.uah.es:10017/68756
network_acronym_str ES
network_name_str España
repository_id_str
spelling Non-linear synthetic time series generation for electroencephalogram data using long short-term memory modelsAlqaysi, Bakr RashidRosa Zurera, Manuel|||0000-0002-3073-3278Aldujaili, Ali AbdulameerEEGTime seriesSynthetic dataLSTMTelecomunicacionesTelecommunicationBackground/Objectives: The implementation of artificial intelligence-based systems for disease detection using biomedical signals is challenging due to the limited availability of training data. This paper deals with the generation of synthetic EEG signals using deep learning-based models, to be used in future research for training Parkinson?s disease detection systems. Methods: Linear models, such as AR, MA, and ARMA, are often inadequate due to the inherent non-linearity of time series. To overcome this drawback, long short-term memory (LSTM) networks are proposed to learn long-term dependencies in non-linear EEG time series and subsequently generate synthetic signals to enhance the training of detection systems. To learn the forward and backward time dependencies in the EEG signals, a Bidirectional LSTM model has been implemented. The LSTM model was trained on the UC San Diego Resting State EEG Dataset, which includes samples from two groups: individuals with Parkinson?s disease and a healthy control group. Results: To determine the optimal number of cells in the model, we evaluated the mean squared error (MSE) and cross-correlation between the original and synthetic signals. This method was also applied to select the length of the hidden state vector. The number of hidden cells was set to 14, and the length of the hidden state vector for each cell was fixed at 4. Increasing these values did not improve MSE or cross-correlation and unnecessarily increased computational complexity. The proposed model?s performance was evaluated using the mean-squared error (MSE), Pearson?s correlation coefficient, and the power spectra of the synthetic and original signals, demonstrating the suitability of the proposed method for this application. Conclusions: The proposed model was compared to Autoregressive Moving Average (ARMA) models, demonstrating superior performance. This confirms that deep learning-based models, such as LSTM, are strong alternatives to statistical models like ARMA for handling non-linear, multifrequency, and non-stationary signals.Agencia Estatal de InvestigaciónMDPI20252025-04-25journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/68756https://dx.doi.org/10.3390/ai6050089reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-129043OB-I00 VIGILANCIA ACUSTICA INTELIGENTE DE INTERIORES PARA EL ANALISIS Y MODELADO DE ESCENAS PARA LA DETECCION DE COMPORTAMIENTOS ANOMALOS DE PERSONAS Y MAQUINASopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/687562026-06-18T11:13:07Z
dc.title.none.fl_str_mv Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
title Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
spellingShingle Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
Alqaysi, Bakr Rashid
EEG
Time series
Synthetic data
LSTM
Telecomunicaciones
Telecommunication
title_short Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
title_full Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
title_fullStr Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
title_full_unstemmed Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
title_sort Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models
dc.creator.none.fl_str_mv Alqaysi, Bakr Rashid
Rosa Zurera, Manuel|||0000-0002-3073-3278
Aldujaili, Ali Abdulameer
author Alqaysi, Bakr Rashid
author_facet Alqaysi, Bakr Rashid
Rosa Zurera, Manuel|||0000-0002-3073-3278
Aldujaili, Ali Abdulameer
author_role author
author2 Rosa Zurera, Manuel|||0000-0002-3073-3278
Aldujaili, Ali Abdulameer
author2_role author
author
dc.subject.none.fl_str_mv EEG
Time series
Synthetic data
LSTM
Telecomunicaciones
Telecommunication
topic EEG
Time series
Synthetic data
LSTM
Telecomunicaciones
Telecommunication
description Background/Objectives: The implementation of artificial intelligence-based systems for disease detection using biomedical signals is challenging due to the limited availability of training data. This paper deals with the generation of synthetic EEG signals using deep learning-based models, to be used in future research for training Parkinson?s disease detection systems. Methods: Linear models, such as AR, MA, and ARMA, are often inadequate due to the inherent non-linearity of time series. To overcome this drawback, long short-term memory (LSTM) networks are proposed to learn long-term dependencies in non-linear EEG time series and subsequently generate synthetic signals to enhance the training of detection systems. To learn the forward and backward time dependencies in the EEG signals, a Bidirectional LSTM model has been implemented. The LSTM model was trained on the UC San Diego Resting State EEG Dataset, which includes samples from two groups: individuals with Parkinson?s disease and a healthy control group. Results: To determine the optimal number of cells in the model, we evaluated the mean squared error (MSE) and cross-correlation between the original and synthetic signals. This method was also applied to select the length of the hidden state vector. The number of hidden cells was set to 14, and the length of the hidden state vector for each cell was fixed at 4. Increasing these values did not improve MSE or cross-correlation and unnecessarily increased computational complexity. The proposed model?s performance was evaluated using the mean-squared error (MSE), Pearson?s correlation coefficient, and the power spectra of the synthetic and original signals, demonstrating the suitability of the proposed method for this application. Conclusions: The proposed model was compared to Autoregressive Moving Average (ARMA) models, demonstrating superior performance. This confirms that deep learning-based models, such as LSTM, are strong alternatives to statistical models like ARMA for handling non-linear, multifrequency, and non-stationary signals.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-04-25
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/68756
https://dx.doi.org/10.3390/ai6050089
url http://hdl.handle.net/10017/68756
https://dx.doi.org/10.3390/ai6050089
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-129043OB-I00 VIGILANCIA ACUSTICA INTELIGENTE DE INTERIORES PARA EL ANALISIS Y MODELADO DE ESCENAS PARA LA DETECCION DE COMPORTAMIENTOS ANOMALOS DE PERSONAS Y MAQUINAS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419332122968064
score 15,812429

Similares en LA Referencia