Author(s): Pannee Suanpang, Pathanapong Pothipasa, Titiya Netwong
The stress on university students is a major contributor to the failure of their studies, caused by many reasons such as high competition, high expectations from parents, lack of adaptability, or unable to study in time of classes, these problems can be found in the following fields of students especially in engineering, medicine, nursing or public health. This issue needs more attention during the epidemic of COVID 19, The effect of staying at home (lock down) or study from home (SFH) using distance learning paradigm causing the stress of the learners to be higher than that of normal situations. This circumstantial might be leading student to develop stress which the recognizing the above problems, the aim of this paper is developed a conceptual framework for stress monitoring using the Internet of Things (IoT) technology and Extreme Learning Machine, in order to provide consultation and assisting science students to increase student retention rates and reduce the loss of graduate students. The experimental results showed that, the proposed framework was more accurate than the Support Vector Machine and KNN respectively, with an accuracy of 93.54 percent with a sensitivity of 98.16 percent.