Epileptic Seizure Detection with Hybrid Time-Frequency EEG Input: A Deep Learning Approach

Pan, Yayan; Zhou, Xiaoyu; Dong, Fanying; Wu, Jian-Xiang; Xu, Yongan; Zheng, Shilian

doi:10.1155/2022/8724536

Cited by 9 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And the transfer learning method was used by Ein Shoka et al [25] for sensitivity, specificity, and accuracy are 88.89%, 84.21%, and 86.11%, respectively. For the Bonn dataset, the specificity obtained by the proposed method is superior to all works [39,40,43,47,49,50]. Li et al [39] designed a unified temporal-spectral squeeze-and-excitation network for classification task, achieving an accuracy of 99.8%.…”

Section: Discussionmentioning

confidence: 89%

Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals

Sun,

Liu,

2024

Journal of Sensors

View full text Add to dashboard Cite

Epilepsy, a neurological disease associated with seizures, affects the normal behavior of human beings. The unpredictability of epileptic seizures has caused great obstacles to the treatment of the disease. The automatic seizure detection method based on electroencephalogram (EEG) can assist experts in predicting seizures to improve treatment efficiency. Epileptic seizure detection cannot be achieved accurately using the single-view characteristics of the signals. Moreover, manual feature extraction is a time-consuming task. To design a high-performance seizure identification method, automatic learning of multi-view features becomes an indispensable part for seizure detection. Therefore, the paper proposes a multi-input deep feature learning networks (MDFLN) model, which comprehensively considers the features from the time domain and the time–frequency (TF) domain for EEG signals. The MDFLN model automatically extracts the feature information of the signals through deep learning networks. Then, the bidirectional long short-term memory (BLSTM) network is used to distinguish seizure and nonseizure events. Furthermore, the effectiveness of the proposed network structure is verified in two public datasets. The experimental results demonstrate that the classification accuracy of the proposed method based on multi-view features is at least 2.2% higher than the single-view features. The MDFLN achieves better performance on CHB-MIT and Bonn datasets with accuracy of 98.09% and 98.4%, respectively. The fine-tuned model with the validation set also improves the classification performance. Compare with the state-of-the-art seizure detection methods, the multi-input deep learning network has superior competence with high sensitivity on the CHB-MIT dataset. The proposed automatic seizure detection method can reduce time consumption and effectively assist experts in the clinical diagnosis and treatment.

show abstract

Section: Discussionmentioning

confidence: 89%

Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals

Sun,

Liu,

2024

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…The majority of research is focused on separating epileptic seizures from regular seizures. Wavelet transforms are employed to enhance classification, and hypothetical testing is utilized to optimize the subset of features 15 . With the appropriate data augmentation, the classifier's computational complexity can be reduced.…”

Section: Introductionmentioning

confidence: 99%

“…Wavelet transforms are employed to enhance classification, and hypothetical testing is utilized to optimize the subset of features. 15 With the appropriate data augmentation, the classifier's computational complexity can be reduced. Moreover, research is progressing on predicting epileptic seizures, which is thought to be a more difficult issue.…”

Section: Introductionmentioning

confidence: 99%

A novel finite spectral entropy: Gated term memory unit recursive network integrated with Ladybug Beetle Optimization algorithm for epileptic seizure detection

Golla,

Maloji

2023

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Professional medical experts use a visual electroencephalography (EEG) signal for epileptic seizure detection, although this method is time‐consuming and highly subject to bias. The majority of previous epileptic detection techniques have poor efficiency, detection performance and also which are unsuited to handle large datasets. In order to solve the aforementioned issues and to assist medical professionals with an advanced technology, a computerized epileptic seizure detection system is essential. Therefore, the proposed work intends to design an automated detection tool for predicting an epileptic seizure from EEG signals. For this purpose, a novel non‐linear feature analysis and deep learning algorithms are deployed in this work. Initially, the signal decomposition, filtering and artifacts removal operations are carried out with the use of finite Haar wavelet transformation technique. After that, the finite spectral entropy (FSE) based feature extraction model has been used to extract the time, frequency, and time‐frequency features from the normalized signal. Consequently, the novel gated term memory unit recursive network (GTRN) model is employed to predict the given EEG signal as whether healthy or seizure affected including the class with high accuracy. During this process, the recently developed Ladybug Beetle Optimization (LBO) algorithm is used to compute the logistic sigmoid function based on the solution. The purpose of using this algorithm is to simplify the process of classification with increased seizure prediction accuracy and performance. Moreover, the standard and popular benchmark EEG datasets are used to validate and test the results of the proposed FSE‐GTRN‐LBO mechanism. By leveraging the finite Haar wavelet transformation and FSE‐based feature extraction, we can efficiently process EEG signals. The utilization of the GTRN model enables accurate classification of healthy and seizure‐affected EEG data. To optimize the classification process further, we integrate the LBO algorithm, streamlining the computation of the logistic sigmoid function. Through comprehensive validation on standard EEG datasets, our proposed FSE‐GTRN‐LBO mechanism achieves outstanding seizure prediction accuracy and performance, surpassing existing state‐of‐the‐art techniques.

show abstract

“…However, deep learning methods often require large-scale datasets to support model training, and the performance of the model may be significantly affected when training samples are insufficient [14,15]. Building large-scale epilepsy datasets entails collecting a large number of EEG signals from patients during epileptic seizures, which is costly.…”

mentioning

confidence: 99%

Channel swapping of EEG signals for deep learning‐based seizure detection

Pan,

Dong,

Yao

et al. 2024

Electronics Letters

Self Cite

View full text Add to dashboard Cite

The purpose of epilepsy detection is to determine whether epilepsy has occurred by analysing the patient's electroencephalogram (EEG) signals. Compared to traditional methods, epilepsy detection methods based on deep learning have achieved significant improvements in detection accuracy. However, when the number of training samples is limited, the model's detection performance often significantly declines. To address this issue, here a sample enhancement method based on electroencephalogram signal channel swapping is proposed. This method generates new electroencephalogram samples by exchanging electroencephalogram sequences from different channels, thereby expanding the training set and improving epilepsy detection accuracy in few‐shot scenarios. Experiments using the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB‐MIT) dataset show that for training sets with 100, 500, and 1000 samples, detection accuracy improves from 0.6797 to 0.7789, 0.6952 to 0.8210, and 0.7273 to 0.8517, respectively. Compared to the sliding window method, the proposed method demonstrates higher accuracy in extreme low sample sizes. Combining both methods can further enhances detection performance, showing an improvement of approximately 8% across various configurations.

show abstract

Epileptic Seizure Detection with Hybrid Time-Frequency EEG Input: A Deep Learning Approach

Cited by 9 publications

References 26 publications

Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals

Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals

A novel finite spectral entropy: Gated term memory unit recursive network integrated with Ladybug Beetle Optimization algorithm for epileptic seizure detection

Channel swapping of EEG signals for deep learning‐based seizure detection

Contact Info

Product

Resources

About