Research On Deep Learning Classification Algorithm For Detecting Neuropsychiatric Disorder Disease Of Motor Symptoms

Deep learning(DL)is the main focal point to the researcher because of its great assistance in the medical healthcare system.Researchers engage in the study of DL based models and wireless signal technology to develop the healthcare systems for detecting neuropsychiatric disorder.In this research,we present the convolutional neural network(CNN),which is a DL based model to classify images and convenient wireless sensing technology to detect tic disorder.Capturing wireless channel state information(WCSI)in the presence of human gestures and classify using the CNN model to detect distinct disorders is the primary idea of this study.Tic disorder is a neuropsychiatric disorder where motor and vocal are two features.Both features divided into simple and complex groups based on complexity,where each group contains several symptoms.The study carried out on WCSI-based data of symptoms of both groups of motor features and trained the CNN model.VGG-16 architecture used in a parallel manner to build the CNN model to classify captured WCSI-based image converted data.We divided the dataset into train,validation,and test and the experimental result shows that our designed CNN model achieved satisfying accuracy results in classification,and the test accuracy result is 98.98%.