• Journal of Computing Science and Engineering
• /
• v.10 no.3
• /
• pp.75-84
• /
• 2016

Medical cyber-physical systems (MCPS) integrate sensors, actuators, and software to improve patient safety and quality of healthcare. These systems introduce major challenges to safety analysis because the patient's physiology is complex, nonlinear, unobservable, and uncertain. To cope with the challenge that unidentified physiological parameters may exhibit short-term variances in certain clinical scenarios, we propose a novel run-time predictive safety monitoring technique that leverages a maximal model coupled with online training of a computational virtual subject (CVS) set. The proposed monitor predicts safety-critical events at run-time using only clinically available measurements. We apply the technique to a surgical glucose control case study. Evaluation on retrospective real clinical data shows that the algorithm achieves 96% sensitivity with a low average false alarm rate of 0.5 false alarm per surgery.

• International Journal of Advanced Culture Technology
• /
• v.8 no.3
• /
• pp.186-191
• /
• 2020

Artificial Intelligence (AI) technology is used in a variety of fields because it can make inferences and plans through learning processes. In the field of coding technologies, AI has been introduced as a tool for personalized and customized education to provide new educational environments. Also, it can be used as a virtual assistant in coding operations for easier and more efficient coding. Currently, as coding education becomes mandatory around the world, students' interest in programming is heightened. The purpose of coding education is to develop the ability to solve problems and fuse different academic fields through computational thinking and creative thinking to cultivate talented persons who can adapt well to the Fourth Industrial Revolution era. However, new non-computer science major students who take software-related subjects as compulsory liberal arts subjects at university came to experience many difficulties in these subjects, which they are experiencing for the first time. AI based coding technologies can be used to solve their difficulties and to increase the learning effect of non-computer majors who come across software for the first time. Therefore, this study examines the current state of AI based coding technologies and suggests the direction of future coding education.

• Journal of The Korean Association of Information Education
• /
• v.22 no.2
• /
• pp.223-230
• /
• 2018

Software education will be implemented in elementary, middle and high schools from the 2018 school year. One of the core contents of software education is algorithm education. As with other subjects, algorithmic education can also be seen as the success of students' initiative. And students' initiative learning can lead to increasing students' interest and commitment. In this paper, I propose the concept of software battle by applying sports games to algorithm education. The software battle defined that the programmed objects play to solve a given problem without human intervention in the virtual world. This can be applied to various topics. In this paper, I tried to apply it to sorting numbers which is a representative subject of algorithm education. The results of applying the algorithm education to the software battles showed a positive response, although the students felt the unfamiliar side. This indicates that the software battle can be used as one of the various education methods.

• Journal of The Korean Association of Information Education
• /
• v.25 no.3
• /
• pp.547-555
• /
• 2021

The purpose of this study is to develop a Goldberg device-based software(SW) convergence Education tool. The 2015 revised curriculum emphasizes convergence with various subjects for effective SW education. In particular, physics is often used as a material for SW convergence education because it is closely related to computational thinking such as sequential movement, quantification of energy and simulation. In this study, we developed an educational program based on the Goldberg device that utilizes physical knowledge, concepts and manipulation. In order to verify the effectiveness of the program, the survey questions were developed through Delphi verification and a basic satisfaction survey was conducted based on this. As a result, the developed program can be effectively used as a program for SW convergence education.