A channel-wise attention-based representation learning method for epileptic seizure detection and type classification

Baghdadi, Asma; Fourati, Rahma; Aribi, Yassine; Daoud, Sawsan; Dammak, Mariem; Mhiri, Chokri; Chabchoub, Habib; Siarry, Patrick; Alimi, Adel M.

doi:10.1007/s12652-023-04609-6

Cited by 11 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This path involves flipping the input data and applying a windowing technique to divide the input into smaller segments. These segments are then independently processed by an LSTM TimeDistributed layer, followed by channel-wise attention, inspired by [58], to enable the model to focus on the most relevant information. The attended signals are then passed through a simple LSTM layer with 64 neurons and a dense layer.…”

Section: Proposed Deep Learning Modelmentioning

confidence: 99%

“…Early stopping was used as a method of regularization technique to prevent overfitting. It monitors the validation loss and suspends training when there is no improvement over 10 consecutive epochs [28,58]. The effectiveness and reliability of performance rely on having a balance between a model's learning capacity as well as its generalizability [53].…”

Section: Model Architecture and Training Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Detection of Abnormal EEG Signals Using WaveNet and LSTM

Albaqami

Hassan

Datta

2023

Sensors

View full text Add to dashboard Cite

Neurological disorders have an extreme impact on global health, affecting an estimated one billion individuals worldwide. According to the World Health Organization (WHO), these neurological disorders contribute to approximately six million deaths annually, representing a significant burden. Early and accurate identification of brain pathological features in electroencephalogram (EEG) recordings is crucial for the diagnosis and management of these disorders. However, manual evaluation of EEG recordings is not only time-consuming but also requires specialized skills. This problem is exacerbated by the scarcity of trained neurologists in the healthcare sector, especially in low- and middle-income countries. These factors emphasize the necessity for automated diagnostic processes. With the advancement of machine learning algorithms, there is a great interest in automating the process of early diagnoses using EEGs. Therefore, this paper presents a novel deep learning model consisting of two distinct paths, WaveNet–Long Short-Term Memory (LSTM) and LSTM, for the automatic detection of abnormal raw EEG data. Through multiple ablation experiments, we demonstrated the effectiveness and importance of all parts of our proposed model. The performance of our proposed model was evaluated using TUH abnormal EEG Corpus V.2.0.0. (TUAB) and achieved a high classification accuracy of 88.76%, which is higher than in the existing state-of-the-art research studies. Moreover, we demonstrated the generalization of our proposed model by evaluating it on another independent dataset, TUEP, without any hyperparameter tuning or adjustment. The obtained accuracy was 97.45% for the classification between normal and abnormal EEG recordings, confirming the robustness of our proposed model.

show abstract

Section: Proposed Deep Learning Modelmentioning

confidence: 99%

Section: Model Architecture and Training Detailsmentioning

confidence: 99%