This paper proposes an input device for video viewing. It serves as a joystick, while it is unfixed and portable. The authors made a prototype of this input device and carried out two experiments. The first experiment evaluated the recognition performance of users’ operation. The performance was qualified by precision and recall, and the result showed that the values of both of these two parameters had become high after repetitions of the operations by users. The second experiment performed a comprehensive evaluation of three input devices including the proposed one. The evaluation was based on NASA-TLX and Nielsen’s usability components, and the result showed that the proposed input device had high affective value and high learnability and that it is suitable for video viewing consequently.
In this paper, we describe a new type method to develop a new triage assisting device. We employ a piezoelectric element used for a buzzer. The pyroelectrics phenomenon of the device was applied to detect the respiration as a sensor and original buzzer function was used to generate alert sound signal as a actuator as well the respiration condition was optically shown by using high emission LED. We realized a triage assisting device based on a microprocessor and confirmed the validity. The device detects respiration with high S/N ratio and optically shows the respiration condition as well it generates alert sound signal when the respiration are abnormal condition.
In this study, we assembly the snake-like robot using ROBOTIS Bioloid and then we realize that the snake-like robot acquires the goal-oriented behavior by CPG and reinforcement learning. CPG (Central Pattern Generator) is a system generating the periodical motion patterns. We apply reinforcement learning to the snake-like robot in order to optimize the offset values of motors. The framework using CPG and reinforcement learning enables the acquisition of behavior knowledge based on physical characteristic of the assembled snake-like robot. Moreover, we realize the autonomous snake-like robot with Raspberry Pi and Web camera. The autonomous snake-like robot by itself can acquire the goal-oriented behavior.
In recent years, large amounts of data have accumulated that may contain new knowledge that will be useful for solving social problems or for creating new products. How to mine that data for information has become a challenge for people who are not used to or training in analyzing such data. In order to make such types of information accessible for mining to everyone, we have developed TETDM, total environment for text data mining. The system provides a generic environment for text mining that is useful not only for data analysts but also for people who do not usually analyze data.
In this study, three motivational game elements were incorporated into TETDM to facilitate and encourage its use for text mining by many people. Based on the experimental results, it was found that those game elements can encourage users and increase the use of the text data mining system.
Robots were used at the site of the World Trade Center disaster, and they are being used to explore the interior of the Fukushima Daiichi Nuclear Plant (FDNP). Robots will be used at the FDNP for the next few decades, until the nuclear reactor is finally decommissioned. Wired communications systems have been used to teleoperate robots in hazardous areas where humans cannot work. In this paper, we show the fluctuation of Wi-Fi power strength in a real environment and that the fluctuations utilization is one of the key points to be considered while developing rescue robots for disaster-prone areas. We propose a simulation environment that simulates the fluctuation of the Wi-Fi power strength with a database and evaluates the performance of the robot with unstable Wi-Fi connectivity.
We propose an automated method for predicting subject behaviors based on first-person vision in an area surrounding bookshelves. The proposal classifies each frame within a movie recorded using a head-mounted camera to the six primitive behaviors according to naive Bayes nearest-neighbor method (NBNN). A prediction experiment is conducted using two image sequences recorded by a head-mounted camera. The experimental results confirm that the average classification rates for NBNN with random sampling (including principal components analysis) are improved from 0.09 to 0.13 for one data set and from 0.03 to 0.08 for the other data set compared with the bag-of-features and support vector machine combination results.