ABSTRACT
One of our greatest present challenges are designing vaccines against SARS COV2 and its variants. Rational vaccine design uses computational methods prior to development of a vaccine for testing in animals and humans the latest methods in rational vaccine design use machine learning techniques to predict binding affinity and antigenicity but offer the researchers only isolated stand-Alone tools. A difficulty that software engineers and data scientist face in development of tools for doctors and researchers is their lack of knowledge of the medical domain. This paper presents a set of domain model developed in collaboration between software engineers and a medical researcher in the process of building a tool scientists could use to predict binding affinity and antigenicity of potential designs of SARS COV2 vaccines. A domain model visualizes the real-world entities and their interrelationships, that together define the domain space. This domain model will be useful to other software engineers trying to predict other characteristics of vaccines, such as potential autoimmunity response. © 2021 IEEE.
ABSTRACT
During the Covid-19 pandemic crisis, the conventional learning process through face-to-face interactions between lecturers and students was suspended due to the implementation of the social restrictions policy by the government to control and reduce the spread of the coronavirus. At that time, the learning process was carried out online, the interaction between lecturers and students through internet communication media by utilizing applications via e-Iearning, google meetings, zoom, and so on. This study aims to develop a measurement model of self-efficacy, digital literacy, and metacognition in higher education and to develop a metacognitive structural model of undergraduate students in The Electrical Engineering Department (EED) Faculty of Engineering (FE) Unesa, and the structural model of metacognition of EED-FE Unesa students in online learning during the Covid-19 pandemic. The research design uses predictive methods to assess self-efficacy and digital literacy on metacognition in online learning. The instrument is validated by experts in the fields of vocational education, learning technology, and educational evaluation. Data collection techniques using survey methods with online communication. The research population is students of the EED-FE Unesa. The research sample was collected through stratified purposive sampling. The data analysis technique is a quantitative research approach that uses a structural equation model (SEM). The SEM design uses the analysis of two models, and there were the measurement model and the structural model. There are three latent variables of the measurement model, i.e., digital self-efficacy, digital literacy, and metacognition. The results showed that the measurement model was able to produce convergent validity, meaning that the items to measure the construct were valid. This means that the indicator variable is correlated with the latent variable. The structural model of metacognition fit with data. © 2021 IEEE.
ABSTRACT
The purpose of this study was to develop the 'Roomeet' communication tool for supporting the online learning management of teachers during the Covid-19 pandemic. The research design uses research and development. The data collection technique used a questionnaire, while the data analysis technique used descriptive statistics and qualitative data analysis, with steps of data reduction, data display, and data verification. The results showed that the 'Roomeet' communication tool has been successfully developed in the form of video conferencing tools with superior features, namely automatic presence. In addition, the 'Roomeet' communication tool is effective to support the online learning management of teachers, especially in administrating the presence and absence of students. Based on the findings, it is better to use the tool in the administration of the classroom. © 2021 IEEE.