Artificial Intelligence enabled cognitive computer-centered digital analysis model for examination of the children’s mental health

Mental health plays an important role for how a person act, think and feel. Specially in the case of students it’s become very crucial and they suffer from various kind of mental disorders due to educational, emotional and societal pressure. This paper proposes an Artificial Intelligence enabled cognitive computer-centered digital analysis model for the examination of children’s mental health. The objective of children mental health analysis using vocal spectrogram, a pseudo-scientific technology, is to deduce deceit from mental health that is detected in the voice. With excessive stress being viewed as an indication of deceit, the technology seeks to distinguish between good mental health and bad mental health outputs in response to stimuli. In this study, we provide a Convolutional Neural network (CNN) based cognitive computer-based model for detecting children mental health based on speech cues and deep learning. Automatic children mental health detection is developing into an intriguing study topic since communication between intelligent systems and humans is demanded to happen more frequently. Although the level of particular hormones, like as cortisol, can be accurately measured to identify children’s mental health. Proposed CNN model validation is done using five different usability factors (learnability, efficiency, effectiveness, satisfaction and understandability) to assess its utility and effectiveness and the results of the initial tests indicate that the proposed model provides a promis- ing tool for the examination of children’s mental health. This paper also discusses how Reinforcement Learning (RL) and CNN algorithms can be used for continuous improvement of the proposed model.