Disorder Detection on EEG Signals and Brain Images Using a Hybrid Approach of Combining the Convolutional Neural Network and Artificial Neural Network (CANN)

Managing brain illnesses effectively requires early and precise diagnosis, which presents major obstacles to health care. Electroencephalography (EEG) signals are a vital source of data for identifying these conditions. In this work, we present a novel hybrid method-convolutional and artificial neural network (CANN)-for utilizing EEG inputs to identify brain abnormalities. Convolutional neural networks (CNNs) are good at extracting spatial features from EEG data, and artificial neural networks (ANNs) are good at collecting temporal dependencies. These two capabilities are combined in the CANN model. To maximize the search performance and optimize the network parameters, we use a multi-stage learning technique. Experimental results on benchmark EEG datasets show the superior performance of the proposed CANN approach compared to individual CNN and ANN models, achieving increased accuracy, sensitivity, and specificity in brain anomaly detection. The proposed hybrid approach is evaluated on publicly available EEG datasets for various brain diseases including epilepsy, Alzheimer’s disease, and attentiondeficit/hyperactivity disorder (ADHD). The results of this study highlight the potential of the hybrid CNN-ANN approach to detect brain disorders, paving the way for more accurate and reliable diagnostic tools in the field of neurology and neuropsychiatry