The increasing use of trajectory data and machine learning has advanced our understanding of human behavior. Specifically, in situations such as team sports, in which multiple players form a group and interact with each other, predicting performance using their trajectory data as input has been attracting attention. However, understanding the role and contributions of individuals in the group by a deep understanding of the whole trajectory has not yet been well-investigated. In this study, we propose a method to quantitatively evaluate the single player’s contribution based on a deep learning model that predicts shooting success from the trajectory data of all players and a ball, leveraging official data of a professional basketball league. We use the difference of two output values by the prediction model when the trajectory data of the target player is given or not given as the model inputs. Our evaluation using the professional basketball dataset for one season confirmed that the predictive model had an accuracy of AUC=0.92. We also confirmed that the scoring contribution of each player calculated from this predictive model was significantly correlated with an existing player’s overall performance metric (R = 0.37, p < 0.001). The results suggest that our proposed method could be a new method to quantify a player's contribution to the team performance from trajectory data only instead of conventional experience-based player performance metrics.

This paper presents field experiments on the downlink throughput performance of a 5G centimeter wave radio access system employing higher rank MIMO in a shopping mall environment and a long corridor environment. The shopping mall has complex reflection paths within its non-line-of-sight areas. The long corridor environment exhibits line-of-sight propagation with many reflection paths. The results show that the maximum throughput of more than 4.8 Gbps in downlink is achieved with 400 MHz spectrum bandwidth in 20% of the course in the shopping mall environment. Moreover, the maximum Rank-8 transmission of more than 9.6 Gbps in downlink can be achieved in the long corridor environment.

In this study, we perform a device evaluation from trial device production (a computer simulation) using technology CAD (TCAD) in an integrated circuit consistent education system, which consists of a series of processes: system design, semiconductor process, trial device production, and device evaluation. By changing the device parameters (kinds of material, film thickness, impurities density) of the semiconductor process, the simulation can more closely approximate the electrical property of the desired target performance. By integrating the simulation technology using TCAD with each piece of knowledge mastered by the integrated circuit consistent education system, which is currently under development, we are able to construct an education system that can be mastered not only for an integrated circuit for information processing but also for the semiconductor process and the global perspective of the device structure in a power device. Furthermore, the possibility of applicability to a new device structure and process development is shown by means of a simulation using TCAD in virtual processing conditions.

Real-time emergent stop walking motion is necessary for humanoid robots. We propose a new emergent stop method using modification criteria map. The stable gait change is generated by adjusting the amount of the ZMP modification according to the timing of stop command. The modified ZMP trajectory is given so that the humanoid robot can change the current motion without falling down. The modification criteria are defined from the relation between the predicted ZMP trajectory using a preview controller and the support polygon. The preview controller employs table-cart model and it derives center of mass (CoM) trajectory from ZMP reference in real-time. We make the map of relation among the ZMP modification length, the modification timing and the timing of the stop command for stable gait modification. The robot can execute the best motion referring to the predefined map. In this method, the humanoid robot can stop immediately within one step or zero step to avoid a collision, if humans or objects appeared unexpectedly in front of the walking humanoid robot. The stop motion is typically divided two phase: single leg support phase and double leg support phase. In the single leg support phase, the next landing position and timing are decided according to command time of the stop signal. In the double leg support phase, the humanoid robot can stop anytime without changing standing position. The validity of the proposed method is confirmed by experiment using a humanoid robot HRP-2.

An ultra-small, low-power sensor-net module called ZN1 is developed. ZN1 integrates MCU, ZigBee RF into an ultra-small 15 -- 15-mm module with an ultra-low standby current less than 1 μA. The and highly reliable operation for more than 15 years of the ZN1 enable low-cost practical application-specific sensor nodes for HVAC, structure monitoring, office management, security, medicine, and healthcare. We describe architecture and technologies for developing the ZN1 module. Moreover, we demonstrate two applications that we developed simultaneously: food sanitation and home healthcare. We also show results of the ZN1 module evaluation and discuss reliability of the ZN1.

This paper describes a real-time gait change for a walking humanoid robot. We propose a control method to change the gait motion by modifying a pre-defined zero moment point (ZMP) trajectory in real time. The stable gait change is generated by adjusting the amount of the ZMP modification according to the timing of stop command. The modified ZMP trajectory is given so that the humanoid robot can change the current motion without falling down. The modification criteria is defined from the relation between the predicted ZMP trajectory using a preview controller and the support polygon. The preview controller employs table-cart model and it derives center of mass (CoM) trajectory from ZMP reference in real-time. We make the map of relation between the ZMP modification and the timing of command for stable gate modification. The robot executes the best motion referring to the map. In this method, the humanoid robot can stop immediately within one step to avoid a collision, if humans or objects appeared unexpectedly in front of the walking humanoid robot. The stop motion is typically divided two mode; single leg stop motion and double leg stop motion. The stop mode and the next landing position are decided according to the command time of the stop signal. The validity of the proposed method is confirmed by experiment using a humanoid robot HRP-2

It is very important to improve software quality using program analysis and measurement tools and the SQA (Software Quality Assurance) method at the appropriate points during the process of development. In many development departments, there is often not enough time to evaluate and use the tools and the SQA method or to accumulate the know-how for effective use. This paper describes the support activity of a software quality analysis and measurement service which is performed by our laboratory team within the company as a third-party independent staff group. We call this activity HQC (High Quality software creation support virtual Center). The purpose of this activity is as follows. First we improve the software quality engineering process in the development department, for example, we help them to increase efficiency of review or testing. To accomplish this, we use program static analysis tools to detect fault-prone software components. Next we assist in starting their own self-improvement process. In addition, we provide service activity to many development departments concurrently. We have been making progress with these activities, and some development departments have begun to establish improvement processes themselves.