Modeling Student Collaboration Network to Enhance Student Interactions

The Covid-19 pandemic, as Henry Kissinger mentions, will not only "forever alter the world order,"but also potentially transform the ever-changing higher education world. The recent increase in technological innovations in information, communications, and computer technology has profoundly transformed traditional teaching-learning processes and peer-to-peer interactions for knowledge transfer. One such radical change in technology that researchers are continually working on is motivating collaborative learning and student interactions to improve their learning experiences. Collaborative Learning (CL), where students work in groups to achieve a specific learning objective, can facilitate a deep learning activity that promotes student participation. However, the potential of discussion forums is limited due to their unstructured nature in LMSs like Canvas.We propose and develop a structured discussion forum that can offer a platform to communicate and discuss problems and receive feedback, discuss solutions, and suggestions online. Students who participate in these discussion forums can benefit in multiple ways, including increased class preparedness and more active learning. The twofold objectives and outcomes include 1) analyzing discussion board data to reveal students' interaction and their degree of participation in the course, and 2) developing a toolset to draw useful inferences from such collaboration networks. Specifically, our schema-based model can help students visualize the discussion board networks creating an engaged learning environment. Furthermore, the model can help draw valuable inferences of the patterns of student interactions and assess student participation and belonging in the course with greater precision.This paper demonstrates a schema-based discussion board model that can allow researchers to collect better-formatted discussion data and more reliable information about the posts, such as the type of posts and the relationships of each post with others. The reimagined discussion boards include the ability to classify discussion posts using various parameters, visualize the posts' patterns of interactions, identify their relationships with other discussion posts, and precisely evaluate student participation in discussions to monitor the major topics of discussion. We believe that the result of increased participation in discussions with other students will have the effect of increasing students' sense of belonging to the community of scholars. © 2022 IEEE.

SensMask: An intelligent mask for assisting patients during COVID-19 emergencies

A new pandemic disease named as novel corona virus disease (COVID-19) was discovered during end of 2019 in Wuhan city of China and was quickly spread throughout the globe. But, till now no medicine is available to fight against the infection caused by the disease. The infection may also be transmitted easily from person to person through highly infectious nasal droplets when a healthy person comes in contact with a distance of less than 1m from the affected person. The doctors, physicians as well as nurses consult the patients very closely to assess the health conditions of the affected persons and there is a great chance that they may carry infection from them. In this work, we have proposed an intelligent mask to assist COVID-19 patients/doctors/nurses with an innovative SensMask to address this issue. This mask contains GPS sensor, IR proximity sensor, walk sensor and FS5 sensor. All patients need to wear this mask to observe the health details. Such sensors monitor health data from patients and send it to the cloud through the home/hospital-based local cloudlet. The cloudlet information is used by physicians for further diagnosis of patients. This proposed approach was simulated and the results obtained indicate that it helps in maximizing throughput and reduced delay. © 2021 Instituto Politecnico Nacional. All rights reserved.

Application of deep learning strategies to assess COVID-19 patients

The recently identified viral disease caused by the coronavirus is named as COVID-19. Many COVID-19-affected patients develop mild to severe respiratory failure and heal without specific intervention. Older persons and individuals with serious medical problems such as cardiovascular disease, asthma, chronic respiratory disorders and cancer continue to experience extreme disease. Throughout the battle against coronavirus, there were several studies about the use of AI. A global overview of the deep learning strategies, which have been used until now, and the potential course of study, is quite relevant in the present scenarios. Thus, it is very much essential to study and analyse the AI techniques available in the literature to be utilized to assess COVID-19 patients. In this work, we have used deep learning strategies on both CT scan and X-ray images to assess COVID-19 patients. © Springer Nature Switzerland AG 2021.