We developed an MR-based system to enhance safety education for hazard prediction in off-site training by generating and visualizing digital twins of laborers. This system focuses on digitizing full-body movements, particularly foot movements and postures, to identify unsafe behaviors during training. Through trials with Vietnamese technical intern trainees, the system effectively identified these issues, highlighting its potential to improve safety training by providing detailed feedback on unsafe behaviors.

While the use of XR in public space design is advancing, requirement elicitation remains challenging. In this study, we developed a system that helps users learn requirement elicitation perspectives from the design activities of others. The system includes two main functions. The first is the "design activity corpus creation function", which tags behavioral data from design activities with a focus on requirement elicitation. The second is the "design activity corpus visualization function", which visualizes the design activities of others. This paper describes the system in detail.

Artisans and athletes have the tacit knowledge, such as skills and tips that their bodies have learnt. These skills usually require a long apprenticeship. We thought the TF-IDF could be used to visualize tendency and frequency of mistakes made by beginners and investigated whether the TF-IDF could be used from data on past Sakan work.

Squat training is highly effective for improving lower limb muscle function. However, when this type of training is performed alone without a personal trainer or physical therapist, it can lead to inefficiencies and injuries among trainees. Thus, we aim to develop a system that provides visual and real-time feedback on the correct posture of a lone squat trainee using pose estimation. In this study, we propose a function that demonstrates the correct posture for each squatting discipline in the form of a line-segment posture representation and warns the trainee when he/she assumes an incorrect posture. Squatting motion in the sagittal plane was captured using a camera connected to a personal computer, and the coordinates of the acromion, hip, knee, and ankle joints were detected using MoveNet. The joint angles were calculated from the detected coordinates and the correct posture was determined according to the individual's body shape. The color of the formed line-segment posture representation changed to indicate the difference between the trainees’ actual and correct postures. In future research, we plan to assess the displacement of key points detected by MoveNet using optical technologies to confirm the reliability of this system’s pose estimation. Afterwards, we will evaluate the effectiveness of this system in determining whether a trainee can move appropriately.

This paper shows ICT operational models to view the actual usage of teachers' desk systems (TDS). The TDS which consist of several ICT devices have been developed and installed to give effective lectures in classrooms of our university. In this study, authors construct ICT operational models from the execution logs of the TDS, and then discuss the adequacy of their specifications and application which is implied by the models.

Double-unders is one of interesting physical skills combining multiple primitive motions of different frequencies. This paper discusses an analyzing method of trajectory on hand-motion in double-unders. It also tackles to design an environment for the staged learning in acquisition process of the skill. We focus on the radius of motion-trajectory of the hand and spatial positions of moving hand. We measure some parameters relating to the hand-motions, and observe relative hand positions to the body. Then, we observe the difference of them between persons who have acquired the skill and others who have not acquired the skill yet. As a result, it has clarified that our proposal relating to the hand-motions is not irrelevant to success or failure of double-unders.

This paper describes the environment of the remote training-support for runners with wireless sensor. The system provides the visualization to a remote advisor about their running-form and feedback function to them by using their kinetic feature of arm swing at the real-time. In particular, 3D-acceleration sensor catches repeats of arm swing. Sensors transmit such information to the remote server on the Web. The advisor can observe runners’ condition by way of waveform changes as graphic reports. Moreover, runners can receive several advices as alarms from the advisor. We have designed and implemented our proposal.