College Students’ Blended Online Examination Acceptance During the COVID-19 Epidemic

To meet the assessments requirements during the COVID-19 epidemic, many schools adopted the large-scale blended online examination, in which teachers invigilate through online video and students answer questions with pen and paper. Exploring the factors that influence students’ acceptance of the blended online examination will help the exam service understand the characteristics of students’ adoption and provide better support for staffs. It will help teachers and parents to assist students to take the blended examination and maintain the traditional exam atmosphere that will facilitate students’ learning performance and effectiveness. In this study, a questionnaire survey and structural equation method were adopted to explore the influence of perceived ease of use, perceived usefulness, social presence, place presence, and social influence on learners’ acceptance of blended online examination. Data analysis of 760 college students who underwent a blended online examination showed that perceived ease of use had a significant negative direct impact on exam acceptability and overall had a significant negative impact. Perceived usefulness, social presence, and social influence have significant positive effects on exam acceptability and social presence and social influence also have significant positive effects indirectly by influencing perceived usefulness. Finally, the limitations of this study are discussed, and the implications and future direction are put forward. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Enhancing decision making with deep reinforcement learning in a context of novel coronavirus outbreak: An example in emergency department

Physicians in hospitals are expected to improve treatment outcome and reduce health care costs. Information systems have been widely adopted in hospitals but not been properly integrated to provide information for decision support. The objective of this research is trying to validate the feasibility of enhancing hospital resource planning system in decision support by utilizing data stored in multiple systems in the hospital with a deep reinforcement learning approach to assist medical practitioner making a more accurate and efficient decision. Following the Design Science Research Method, this research is going to build an artefact to utilize data from electronic health record (EHR) and hospital resource planning (HRP) to provide medical decision support in the emergency department setting. © 2020 ACM.