Epileptic seizure is popular neurological disease identified by concurrent seizures that requires careful categorization of seizure types: focal and generalized focal epileptic seizures so that to optimize therapy and management techniques. Accurate seizure diagnosis is especially crucial when evaluating patients for surgical intervention. This study uses machine learning approaches, namely ensemble methods such as the Rotation Forest classifier, to automatically categorize respective generalized focal category based on electroencephalography (EEG) signals. Before being analyzed, EEG data is preprocessed, which includes normalization and filtering. The results of ensemble rotation forest and other algorithms is evaluated using Accuracy, ROC AUC (Area under the Receiver Operating Characteristic curve). The research shows that our automated categorization system greatly improves diagnostic accuracy, allowing doctors to make faster and more precise judgements. This technique also minimizes the need for manual EEG signal interpretation, which improves overall patient care quality.