A Systematic Literature Review on Machine Learning Algorithms for Human Status Detection

Abstract

Human status detection (HSD) is important to understand the status of users when interacting with various systems under different conditions. Recently, although various machine learning algorithms have been applied to analyze and detect human status, there are no guidelines to utilize machine learning algorithms to analyze physical, cognitive, and emotional aspects of human status. Therefore, this study aimed to investigate measures, tools, and machine learning algorithms for HSD by applying a systematic literature review method. We followed the preferred reporting items for systematic reviews and meta-analysis (PRISMA) model to answer three research questions related to the research objective. A total of 76 articles were identified using two hundred keyword combinations addressing topics under HSD in the fields of human factors and human-computer interaction (HCI). The results showed that research on HSD becomes important in industrial systems, focusing on how intelligent systems based on machine learning (ML) differ from earlier generations of automated systems, and what these differences necessarily imply for HCI to design and evaluation. The tools used to collect data for HSD on different parameters are broadly discussed. Recent HSD studies seem to focus on cognitive load and emotion, whereas prior studies have focused on the detection of physical effort. This research assists domain researchers in identifying HSD approaches using different ML algorithms that are suitable for use in their research.