A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal. (May 2023)
- Record Type:
- Journal Article
- Title:
- A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal. (May 2023)
- Main Title:
- A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal
- Authors:
- Qiu, Xuanjie
Yan, Fang
Liu, Haihong - Abstract:
- Abstract: Epileptic seizures can affect the patient's physical function and cause irreversible damage to their brain. It is vital to detect epilepsy seizures in time and give patients antiepileptic medical treatment. Hybrid deep learning models, which combine convolutional neural network and recurrent neural network, have better epileptic seizure detection performance as they could simultaneously extract spatial and temporal features. However, the existing hybrid deep learning models still have the following two weaknesses. Firstly, they directly input the raw electroencephalogram signals, where the epilepsy seizure information is limited. Secondly, some characteristic information is extracted in the feature map, distracting the attention of deep learning model. To address these issues, this paper proposes a difference attention ResNet-LSTM network (DARLNet). The proposed model uses a residual neural network (ResNet) and a long short-term memory network (LSTM) to capture spatial correlations and temporal dependencies, respectively. Besides, a difference layer is developed to automatically mine additional epileptic seizure information. Moreover, the channel attention module is introduced to make the model focus on seizure-relevant information. Several groups of experiments are conducted to evaluate the performance of DARLNet based on the Bonn Electroencephalogram dataset, which verifies the superiority of DARLNet on the two-category and five-category epileptic seizureAbstract: Epileptic seizures can affect the patient's physical function and cause irreversible damage to their brain. It is vital to detect epilepsy seizures in time and give patients antiepileptic medical treatment. Hybrid deep learning models, which combine convolutional neural network and recurrent neural network, have better epileptic seizure detection performance as they could simultaneously extract spatial and temporal features. However, the existing hybrid deep learning models still have the following two weaknesses. Firstly, they directly input the raw electroencephalogram signals, where the epilepsy seizure information is limited. Secondly, some characteristic information is extracted in the feature map, distracting the attention of deep learning model. To address these issues, this paper proposes a difference attention ResNet-LSTM network (DARLNet). The proposed model uses a residual neural network (ResNet) and a long short-term memory network (LSTM) to capture spatial correlations and temporal dependencies, respectively. Besides, a difference layer is developed to automatically mine additional epileptic seizure information. Moreover, the channel attention module is introduced to make the model focus on seizure-relevant information. Several groups of experiments are conducted to evaluate the performance of DARLNet based on the Bonn Electroencephalogram dataset, which verifies the superiority of DARLNet on the two-category and five-category epileptic seizure detection tasks. Highlights: DARLNet captures spatial correlations and temporal dependencies by ResNet and LSTM. DARLNet is able to automate and focus on developing information about seizures. Several experiments have demonstrated the superior performance of DARLNet. … (more)
- Is Part Of:
- Biomedical signal processing and control. Volume 83(2023)
- Journal:
- Biomedical signal processing and control
- Issue:
- Volume 83(2023)
- Issue Display:
- Volume 83, Issue 2023 (2023)
- Year:
- 2023
- Volume:
- 83
- Issue:
- 2023
- Issue Sort Value:
- 2023-0083-2023-0000
- Page Start:
- Page End:
- Publication Date:
- 2023-05
- Subjects:
- Epileptic seizure detection -- Electroencephalogram -- Deep learning -- ResNet -- LSTM
Signal processing -- Periodicals
Biomedical engineering -- Periodicals
Signal Processing, Computer-Assisted -- Periodicals
Image Processing, Computer-Assisted -- Periodicals
Biomedical Engineering -- Periodicals
610.28 - Journal URLs:
- http://www.sciencedirect.com/science/journal/17468094 ↗
http://www.elsevier.com/journals ↗
http://www.sciencedirect.com/science?_ob=PublicationURL&_tockey=%23TOC%2329675%232006%23999989998%23626449%23FLA%23&_cdi=29675&_pubType=J&_auth=y&_acct=C000045259&_version=1&_urlVersion=0&_userid=836873&md5=664b5cf9a57fc91971a17faf20c32ec1 ↗ - DOI:
- 10.1016/j.bspc.2023.104652 ↗
- Languages:
- English
- ISSNs:
- 1746-8094
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 2087.880400
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 26178.xml