Applying machine learning and deep learning algorithms to classify patients using EEG signals.
Master thesis
Permanent lenke
https://hdl.handle.net/11250/3084449Utgivelsesdato
2023Metadata
Vis full innførselSamlinger
- Studentoppgaver (TN-IDE) [823]
Beskrivelse
Full text not available
Sammendrag
This thesis investigates the potential of Event-Related Potentials (ERPs) for subject-groupclassification. The ERPs data from five distinct subject groups are analyzed to evaluatethe discriminatory power of ERPs in classifying subjects into specific groups. Machinelearning techniques, such as Random Forest, Gradient Boosting, K-Nearest Neighborclassifiers, and the EEGNet deep learning approach, are employed for classification. Theperformance of the models is evaluated using accuracy, precision, recall, and F1-scoremetrics. The Random Forest classifier achieves the highest accuracy of 92% by utilizingthe activity feature of standard stimuli as the input. Nonetheless, the Gradient Boostingand K-Nearest Neighbor classifiers also exhibit strong performance, with 89% and 88%accuracy, respectively, for this dataset.
Moreover, the precision, recall, and F1-score for these two approaches are also the highest.The K-Nearest Neighbor classifier achieves a precision of 98.8% for individuals withParkinson’s Disease. Similarly, it attains the highest recall rate of 97.6% for individualswith Dementia associated with Lewy Bodies. On the other hand, the Random Forestclassifier achieves the best F1-score of 97.2% for healthy control subjects.