We use explainable artificial intelligence (XAI) based on Explain Like I’m 5 (ELI5), Partial Dependency Plot box (PDPbox), and Skater to analyze diverse physical agricultural (agri-) worker datasets. We have developed various promising body-sensing systems to enhance agri-technical advancement, training and worker development, and security. This includes wearable sensing systems (WSSs) that can capture real-time three-axis acceleration and angular velocity data related to agri-worker motion by analyzing human dynamics and statistics in different agri-environments, such as fields, meadows, and gardens. After investigating the obtained time-series data using a novel program written in Python, we discuss our findings and recommendations with real agri-workers and managers. In this study, we use XAI and visualization to analyze diverse data of experienced and inexperienced agri-workers to develop an applied method for agri-directors to train agri-workers.
We have been developing various kinds of promising applied sensing systems to resolve difficulty in achieving agricultural advancement, technical tradition (teaching), and safety issues. Existing methods and systems are not enough to analyze human motion minutely, simply, and at low-cost. For the purpose, we have also been developing Wearable Sensing Systems (WSs), including advanced devices, to secure real-time data related to worker motion by analyzing human dynamics and statistics in rice fields, meadows, and gardens. We have obtained and observed those time-line data, computed by some statistical methods, discussed about them, and make some suggestions concerning them. Our plans would make it possible for us to improve worker agricultural skills and to enhance their safety level.
Abstract:In recent years, researchers and engineers have come together to develop diverse, applied, and practical sensing systems to solve the difficulties faced in the development of advanced support systems, technical teaching, and safety issues for physically challenged and elderly people. Following a sequence of studies developing promising systems that address a number of nursing challenges, the purpose of this prospective research was to develop effective systems and demonstrate their accuracy and utility for the aforementioned people. In this kinematic investigation, we develop a physical analysis system, which uses two video cameras to obtain visual data of physically challenged and elderly people from two directions (the subject's front and left). These systems use the OpenCV 2.4.9 package, including the library and header files, and programs originally written in Visual C++. This study examines the qualitative and quantitative characteristics and the unique parameters of (1) the main shaft (the principal axis of inertia) of the subject and the walking support system to highlight the differences between two frames using binary video data, and (2) coordinate values of characteristic points that are set automatically. Finally, we present the output values for the physical measurements obtained from various viewpoints. In future, these methods could be of practical use in providing alternative directions for developers and care managers to assess and treat users' conditions in both outdoor (e.g., playgrounds for the elderly) and indoor settings (e.g., hospitals).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.