AN efficient deep learning with an optimization framework to analyse the eeg signals

Electroencephalogram (EEG) signals can offer a mode to communicate with the humans and outside world. Also, the human brain is negatively affected the mental illness such as depression, stress, overthinking, and feelings. Therefore, stress rate is recognized by studying EEG signals but it has the issue for analysing the stress rate because of redundant noise present in the EEG signal. This technique is independent of the human body peripherals like muscle tissue and nerves. Moreover, brain-controlled devices are advanced technology to control a lot of mental feelings and control severe brain actions like stress, heavy emotion, etc. With this advanced innovation, EEG signal processing plays an important role in the brain-computer interface. This paper introduced a novel Convolution Network with bat Optimization (CN-BO) framework to identify the stress level of the human brain. At the same time, different processing techniques are incorporated into this research to differentiate the stress state. Consequently, the proposed model implementation is done with the help of the MATLAB platform. At last, the key metrics of the developed CN-BO strategy is validated with conventional techniques in terms of Signal to Noise Ratio (SNR), Mean Square Error (MSE), and computation time.