Abstract
Brain tumors present a significant health challenge, demanding early and accurate diagnostic methods. This study utilizes the EEG wave patterns for non-invasive brain tumor detection. This research study aims to analyze EEG data using Convolutional Neural Networks (CNNs) and Support Vector Machine (SVM) to identify the tumor-related wave patterns. The proposed methodology involves preprocessing EEG signals, extracting relevant features, and training both CNN and SVM models to classify normal and tumor-related EEG patterns. The interpretability techniques are also incorporated to interpret the neural signs contributing to tumor detection. This enhances the proposed model's transparency and establishes a connection between detected patterns and clinically relevant information. While recognizing the challenges such as data variability and the necessity for large, well-annotated datasets, this study highlights the potential of EEG-based detection method