Investigation of Epileptic Seizure Signatures Classification in EEG Using Supervised Machine Learning Algorithms
Bibliographic record
Abstract
Epilepsy is one of the earnest neurological disorders that require further social attention. Based on the International League Against Epilepsy (ILAE), which classifies the epilepsy term as a number of several seizures that occur in the brain. Electroencephalography (EEG) is considered our brain window to the electrical activity. It is a significant device used for diagnosing multiple brain disorders such as Epilepsy. Moreover, this study used data from Temple University Hospital Seizure Corpus (TUH), which represents an accurate description of the clinical cases for five types of epileptic seizures. Initially, to extract information from EEG signals, three types of feature extraction have been used namely Fast Fourier Transform, Entropy, and Approximate Entropy. Due to the high degree of variance of EEG signals, we implemented a band-pass filter to divide the signals into sub-bands called delta rhythm (0.1 - 4Hz), theta rhythm (5 -9Hz), alpha rhythm (10 - 14Hz), beta rhythm (15- 31Hz), and gamma rhythm (32-100). The feature extraction outcome underwent normalization techniques and was used as input for the classifiers. Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB), and K-Nearest Neighbor (KNN) classifier have implemented in order to classify (1) second epoch length window. In the first scenario, we applied the FFT features to the classifiers, the results showed that SVM obtained the highest value compared to the other classifiers with 96% accuracy, whereas KNN was 92% and the DT and NB were 76% and 67%, respectively. The second scenario was applying entropy features to the classifiers, the results of classification were 91% for SVM and 88% for KNN, while the DT and NB were 76% and 67%, respectively. The last scenario was ApEn, which shows that SVM still gains the highest value, which was 83%, and 76% for KNN, where the DT and NB were 65% and 69%, respectively. From the aforementioned results, we deduced that SVM achieved the best accuracy when applied with the three feature extractions.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".