http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Suman Kalyan Sardar(수만 칼얀 사르다르),Naveen Kumar(나빈 쿠마르),Seul Chan Lee(이슬찬) 대한인간공학회 2021 대한인간공학회 학술대회논문집 Vol.2021 No.11
Objective: The purpose of this study is to evaluate the importance of major research areas by identifying different machine learning techniques that influence key research fields on Human Status Detection (HSD). Background: HSD is concerned with the study of human-system interactions that uses theory, concepts, data, and techniques to design in order to improve human well-being and total performance. The basic premise of HSD is that effective performance comes from user-centered design and a comprehensive understanding of the user’s skills, needs, and preferences. Several machine learning algorithms have been used in the literature to measure the cognitive and physical workload status of the users. Method: In this research, PRISMA model has been applied to gather articles from three databases namely, ScienceDirect, IEEE Xplore, and Association for Computing Machinery (ACM). Sixteen keywords has been selected for collecting the articles from the databases. The following criterion is considered to develop protocol: (1) inclusion/exclusion criteria, (2) study selection, (3) data extraction, (4) data synthesis. Results: A total number of 82 articles were identified using an iterative collaboration of 80 keyword combinations addressing issues in different physical workloads and cognitive loads. A list of important occurrences was identified that may have an impact on the publication pattern. Conclusion: Recent publications on human status detection appear to be primarily concerned with cognitive load whereas previous articles were on detecting physical workload. Application: This study helps domain researchers to identify HSD techniques for their experimental studies.