TIE-EEGNet: Temporal Information Enhanced EEGNet for Seizure Subtype Classification

Peng, Ruimin; Zhao, Changming; Jiang, Jun; Kuang, Guangtao; Cui, Yuqi; Xu, Yifan; Du, Hao; Shao, Jianbo; Wu, Dongrui

doi:10.1109/tnsre.2022.3204540

Cited by 30 publications

(23 citation statements)

References 52 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed EEG-LSTMNet is compared to that of the state-of-theart model described in [25], both of which classify eight seizure types. The proposed model in [25] comprises three blocks, block one with temporal and depthwise convolutional layers, block two with a separable, depthwise convolutional layer and a subsequent point-wise convolutional layer, and block three with a single fully connected layer that is connected to a SoftMax activation function. The proposed EEG-LSTMNet outperforms this model in adopting two average pooling layers to compute the average value for the patches of a feature map to create a down-sampled (pooled) feature map.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…Unlike the single fully connected classification layer in [25], the proposed EEG-LSTMNet adopts two fully connected layers; the first layer is a time-distributed dense layer, while the second one is connected to a SoftMax function and includes eight neurons. Both models adopt different databases; the suggested EEG-LSTMNet model adopts the TUH database, whereas [25] adopts both the TUSZ and CHSZ databases. The results of both models prove that our model outperforms with a 98.4% F1-score compared with the state-of-the-art model in [25], which achieved 67.2% Accuracy.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…It combines depthwise convolution and separable convolution, which capture the temporal and spatial filters as a substitution for the typical square convolution, reducing the number of parameters. However, the application of the EEGNet model to classify seizure types is limited in the literature, and there is only one available research study model by Peng et al [25]. The model was composed of three blocks.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Epileptic Seizure Types Using Multiscale Convolutional Neural Network and Long Short-Term Memory

Alshaya,

Hussain

2023

Mathematics

View full text Add to dashboard Cite

The accurate classification of seizure types using electroencephalography (EEG) signals plays a vital role in determining a precise treatment plan and therapy for epilepsy patients. Among the available deep network models, Convolutional Neural Networks (CNNs) are the most widely adopted models for learning and representing EEG signals. However, typical CNNs have high computational complexity, leading to overfitting problems. This paper proposes the design of two effective, lightweight deep network models; the 1D multiscale neural network (1D-MSCNet) model and the Long Short-term Memory (LSTM)-based compact CNN (EEG-LSTMNet) model. The 1D-MSCNet model comprises three modules: a spectral–temporal convolution module, a spatial convolution module, and a classification module. It extracts features from input EEG trials at multiple frequency/time ranges, identifying relationships between the spatial distribution of their channels. The EEG-LSTMNet model includes three convolutional layers, namely temporal, depthwise, and separable layers, a single LSTM layer, and two fully connected classification layers to extract discriminative EEG feature representations. Both models have been applied to the same EEG trials collected from the Temple University Hospital (TUH) database. Results revealed F1-score values of 96.9% and 98.4% for the 1D-MSCNet and EEG-LSTMNet, respectively. Based on the demonstrated outcomes, both models outperform related state-of-the-art methods due to their architectures’ adoption of 1D modules and layers that reduce the computational effort needed, solve the overfitting problem, and enhance classification efficiency. Hence, both models could be valuable additions for neurologists to help them decide upon precise treatments and drugs for patients depending on their type of seizure.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Epileptic Seizure Types Using Multiscale Convolutional Neural Network and Long Short-Term Memory

Alshaya,

Hussain

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…To alleviate the above problem, TL has been proposed to leverage data and knowledge from the source domains and handle the domain discrepancy. Unsupervised domain adaptation assumes the source domains are labeled, whereas the target domain is not, which is more suitable for new patient diagnostics [17]. Unsupervised domain adaptation approaches utilize the unlabeled target domain data during learning to better calibrate the algorithm under distribution shift.…”

Section: Tlmentioning

confidence: 99%

“…The public Helsinki University Hospital neonatal intensive care unit (NICU) dataset [36] and the CHSZ dataset [17] were used. Table 1 summarizes their main characteristics.…”

Section: Datasetsmentioning

confidence: 99%

Unsupervised domain adaptation for cross-patient seizure classification

Wang,

Zhang,

et al. 2023

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective. Epileptic seizure is a chronic neurological disease affecting millions of patients. Electroencephalogram (EEG) is the gold standard in epileptic seizure classification. However, its low signal-to-noise ratio, strong non-stationarity, and large individual difference nature make it difficult to directly extend the seizure classification model from one patient to another. This paper considers multi-source unsupervised domain adaptation for cross-patient EEG-based seizure classification, i.e. there are multiple source patients with labeled EEG data, which are used to label the EEG trials of a new patient. Approach. We propose an source domain selection (SDS)-global domain adaptation (GDA)-target agent subdomain adaptation (TASA) approach, which includes SDS to filter out dissimilar source domains, GDA to align the overall distributions of the selected source domains and the target domain, and TASA to identify the most similar source domain to the target domain so that its labels can be utilized. Main results. Experiments on two public seizure datasets demonstrated that SDS-GDA-TASA outperformed 13 existing approaches in unsupervised cross-patient seizure classification. Significance. Our approach could save clinicians plenty of time in labeling EEG data for epilepsy patients, greatly increasing the efficiency of seizure diagnostics.

show abstract

Subject-Independent Brain-Computer Interfaces: A Comparative Study of Attention Mechanism-Driven Deep Learning Models

Keutayeva,

Abibullaev

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

TIE-EEGNet: Temporal Information Enhanced EEGNet for Seizure Subtype Classification

Abstract: labelers. To relieve the burden on clinicians and improve the treatment efficiency, automated epilepsy diagnosis algorithms are desired.

Cited by 30 publications

References 52 publications

Classification of Epileptic Seizure Types Using Multiscale Convolutional Neural Network and Long Short-Term Memory

Classification of Epileptic Seizure Types Using Multiscale Convolutional Neural Network and Long Short-Term Memory

Unsupervised domain adaptation for cross-patient seizure classification

Subject-Independent Brain-Computer Interfaces: A Comparative Study of Attention Mechanism-Driven Deep Learning Models

Contact Info

Product

Resources

About