Graph-Informed Neural Networks with Green Anaconda Optimization Algorithm Based on Automated Classification of Condition of Mental Health Using Alpha Band EEG Signal

Mental Health Status (MHS) Using Alpha Band EEG Signal” is the process of evaluating and categorizing a person's mental state by examining the electroencephalogram (EEG) recording of their alpha wave activity, which usually occurs between 8 and 13 Hz. The goal of this method is to find alpha wave patterns that correspond, but the existing methods have IoT of disadvantages such as, low precision, low accuracy and high error rate. mental health issues. To overcome these problems, Graph-informed neural networks with Green Anaconda Optimization Algorithm (G-INN- GAOA) is proposed. In this, input data is taken from two dataset such as AVEC2013 and AVEC2014 datasets. It pre-processed data using Memory-Boosted Guidance Filtering (M-BGF), Following that, Next, the Alpha Band EEG Signal for Mental Health Status is the features extracted using One-Dimensional Spectrum (O-DS), Following that Feature selection using White Shark Optimizer (WSO) and classification Graph-informed neural networks (G-INN) and the optimization using Green Anaconda Optimization Algorithm (GAOA) for detecting the type of Mental Health Status and to find the Neutral, Focus, Relax for MHS. The introduced system is executed in python. The efficiency of the proposed BAQNN-SGA is analyzed using a datasets and attains 99.9% accuracy, 99.8% recall and attains better results compared with the existing methods. This indicates the approach's superior efficiency and potential for further development in the field.