Automated EEG Epileptic Seizure Detection Exploiting Continuous Morlet Wavelet Transform Scalograms and Hybrid Deep Learning Models
Bibliographic record
Abstract
Epilepsy is a prevalent neurological disorder characterized by recurrent seizures, affecting millions of people worldwide. Accurate and timely detection of epileptic seizures is crucial for patient management and treatment. Traditional seizure detection methods are often time-consuming and require expert interpretation, leading to a growing interest in deep-learning techniques for efficient and accurate seizure detection. This study ventures into transforming an Electroencephalogram (EEG) signal dataset into Continuous Morlet Wavelet Transform (CMWT) scalograms of the signals processed into four distinct resolutions: 32x32, 48x48, 64x64, and 128x128. CMWT is a mathematical representation that offers a detailed time-frequency-based visualization of signals by decomposing the EEG signals into different frequency components and then visualizing their intensity with respect to time. Five hybrid models are developed and compared: a 3-layered 2D-Convolutional Neural Network (CNN) model, a transfer learning approach with the VGG16 and ResNet50 model, and two hybrid Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) models such as Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and CNN-LSTM-LSTM. These hybrid models are designed to leverage the strengths of both CNNs and RNNs for feature extraction and classification, respectively. The outcomes demonstrate that the VGG16 architectures with the input resolution 64x64, appear to be a promising choice, offering a harmonious blend of computational efficiency and model performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".