Epileptic seizure detection: a comparative study between deep and traditional machine learning techniques
Autor: | L. A. Cacha, Rekha Sahu, Roman R. Poznanski, Satya Ranjan Dash, Shantipriya Parida |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Computer science
Machine learning computer.software_genre 050105 experimental psychology lcsh:RC321-571 Machine Learning 03 medical and health sciences Naive Bayes classifier 0302 clinical medicine Seizures Humans 0501 psychology and cognitive sciences AdaBoost lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry Epilepsy Artificial neural network business.industry General Neuroscience Deep learning 05 social sciences Brain Electroencephalography Signal Processing Computer-Assisted General Medicine Ensemble learning Random forest Support vector machine ComputingMethodologies_PATTERNRECOGNITION ROC Curve Gradient boosting Artificial intelligence business epilepsy|seizure|deep learning|artificial neural networks|neural signals|eeg signals|computer simulations computer 030217 neurology & neurosurgery |
Zdroj: | Journal of Integrative Neuroscience, Vol 19, Iss 1, Pp 1-9 (2020) |
Popis: | Electroencephalography is the recording of brain electrical activities that can be used to diagnose brain seizure disorders. By identifying brain activity patterns and their correspondence between symptoms and diseases, it is possible to give an accurate diagnosis and appropriate drug therapy to patients. This work aims to categorize electroencephalography signals on different channels' recordings for classifying and predicting epileptic seizures. The collection of the electroencephalography recordings contained in the dataset attributes 179 information and 11,500 instances. Instances are of five categories, where one is the symptoms of epilepsy seizure. We have used traditional, ensemble methods and deep machine learning techniques highlighting their performance for the epilepsy seizure detection task. One dimensional convolutional neural network, ensemble machine learning techniques like bagging, boosting (AdaBoost, gradient boosting, and XG boosting), and stacking is implemented. Traditional machine learning techniques such as decision tree, random forest, extra tree, ridge classifier, logistic regression, K-Nearest Neighbor, Naive Bayes (gaussian), and Kernel Support Vector Machine (polynomial, gaussian) are used for classifying and predicting epilepsy seizure. Before using ensemble and traditional techniques, we have preprocessed the data set using the Karl Pearson coefficient of correlation to eliminate irrelevant attributes. Further accuracy of classification and prediction of the classifiers are manipulated using k-fold cross-validation methods and represent the Receiver Operating Characteristic Area Under the Curve for each classifier. After sorting and comparing algorithms, we have found the convolutional neural network and extra tree bagging classifiers to have better performance than all other ensemble and traditional classifiers. |
Databáze: | OpenAIRE |
Externí odkaz: |