CNN-PS: Electroencephalogram Classification of Brain States Using Hybrid Machine - Deep Learning Approach

Abstract

Electroencephalography (EEG) has been used for quite some time as a diagnostic technique in
neurology. The goal of this publication is to serve as a resource for researchers interested in applying deep learning
methods to EEG data. This paper proposes a unique Hybrid Machine-Deep Learning model that can learn and classify
EEG signals on its own. This method allows the model to classify EEG signals of varied sampling frequencies and
durations automatically. The proposed model used feature extraction methods from artificial design and performed
extensive tests with EEG data collected at varying sample rates to determine how well our suggested model
performed. The results show that the Hybrid Machine-Deep Learning strategy significantly improves performance,
leading to a remarkable 99.97% classification accuracy. Notably, this method performs exceptionally well when
labeling lower-frequency EEG signals (less than 4 Hz). The proposed model has improved consistency and
robustness, as shown by this study.