An Novel Versatile Inspiring Wavelet Transform and Resilient Direct Neural Network Classification Techniques for Monitoring Brain Activity System Based on EEG Signal

The human brain is an essential skill to find the erroneous behaviors accordingly to keep a record of events. Electrophysiological and neuroimaging studies have demonstrated a variety of brain functionalities for a peculiarity of intuition. Meanwhile, specific Brain Activity Recognition has been reported for potential applications as a feature of performance monitoring. However, the choice of features, classification procedures as well as the single-trial processes, optimum performance are investigated fully. In addition to being an assistant (brain-computer interface), BCIs are now offered a wide range of applications. BC's can also benefit from user-intelligent state embracing their remarkable change and insight. In this work, an advanced approach for the detection of Human activity in EEG. The proposed versatile Inspiring wavelet transformation (VIWT) are applied to minimize the dimensionality of the EEG data signal with a Resilient Direct Neural Network (RDNN) are employed for the classification technique. In this system processes to applying VIWT which decomposes the EEG signal within its sub-bands to extract energy ratio from the wavelet coefficients. Beside to extract some statistical features from the original signal, unless the system uses the classification rules to identify a particular function, to extract the RDNN classification process as input. The performance is assessed by the classification of sensitivity, specificity, and accuracy. The Experimental results show with RDNN classification with VIWT technique provides with an accuracy of 98.6%. The evaluation of the patient's health and raise the living standards of a practical assessment is implemented in a credible proposition.