In recent years, the Sustainable Development Goals (SDGs) have tended to attract attention. In Japan, Society 5.0 has been proposed as a vision that is linked to the achievement of the SDGs, and various organizations are promoting this vision. In particular, “i-Construction” is being promoted in the construction industry, and productivity is increasing as a result. Moreover, it is important for operators to have a sense of achievement and motivation for their work through their active operation. In this study, we propose a control system that automatically adjusts the assist rate according to the person in assist control. A control system that can adaptively adjust the assist rate is constructed by utilizing work data to evaluate the difference from the desired characteristics. The proposed method was implemented on a hydraulic excavator and its effectiveness was verified.

In this paper, we consider nonlinear system identification when a plant contains an integral characteristic. When the plant includes an integral characteristic, applying the DNN directly to nonlinear system identification may result in large differences between the response of the actual equipment and the response of the DNN model. In order to reduce response errors, we propose a method that adds a structure constraint represnting the integral characteristics to the DNN model. The effectiveness of the proposed method is verified using input-output data from a nonlinear simulation of a pneumatic vibration isolator that includes integral characteristics.

The risk of infectious diseases, such as the new coronavirus, has caused a major shift in employee work styles, and remote work appears to have taken hold. However, companies are moving back to office-based work. During this transitional period, we focus on communication networks within offices and propose a communication network detection method with area attributes using employee location data. We use Wi-Fi and information terminal communication logs to obtain the location information of all employees of the surveyed companies to secure data comprehensiveness. In addition, we propose a model to investigate the relationship between total communication network volume, location, and network centrality to employee performance. The results show that employees who frequently communicate with key persons in the organization in the conference room and around their desks have higher performance.

When playing a piece with a bowed string instrument, it is necessary to determine the bowing in advance. This requires knowledge of the piece and a lot of time to acquire the ability to determine the bowing. Therefore, it is difficult for beginners of such instruments to determine the bowing. In this paper, we propose a system that acquires bowing and acoustic information from performance videos of a stringed instrument such as a violin and automatically writes the bowing symbols on the sheet music. This system makes it easy to refer to the bowing of a skilled player and to compare the bowing of multiple players. We believe that this system will be useful for improving a player's skill in performance techniques and his/her comprehension of musical pieces. In a validation experiment, the proposed system was able to estimate the bowing of children's songs with an accuracy rate of more than 90%.