The mental health management of college students is a challenging process due to its inconsistent variations and action-dependent observations. However, for personal and mental stability and psychological assessment of students, the inconsistent mental health is to be handled using a high precision computing system. This article introduces a Deliberate Management System (DMS) powered by the Internet of Things (IoT) concept for inconsistency reduction in the mental health data processing. The proposed system performs non-identical observation based on actions and non-action intervals for reducing inconsistencies. In the observation and processing, the IoT elements are employed for support, prediction, and representation. The representations are classified based on different observation data that are abnormal and are deviating from the non-identical intervals. In data processing, deep learning is employed for identifying non-identical to identical stream assimilations, preventing false rates. This learning is recurrently iterated post the assimilation interval for preventing a steep increase in mental data analysis. The proposed system’s performance is validated using accuracy, false rate, overhead, and time requirement.
Luo et al. (Sat,) studied this question.