A novel flexible data analytics model for leveraging the efficiency of smart education

Conventional educational systems have been uplifted for their efficiency using information and communication technologies in a pervasive manner. The information accumulated from the students, environments, and observations increases data exchanged in the smart education platform. The challenging aspect is the data correlation and its correctness in delivering interactive educational services. Because of addressing the correctness issue, this article proposes a Flexible Observation Data Analytics Model (FODAM). The proposed model relies on the session requirement for extracting useful information. The correctness of the information is verified at the interaction level without losing any tiny observation data. In this model, regressive learning is used for the progressive identification of required data. This learning relies on session requirements and the discreteness of the observed data. The progressive training thwarts the discreteness to provide reliable and non-interrupting educational data for the interacting members. The proposed model's performance is verified using the metrics delay, efficiency, interrupts, and information rate.