[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

Scientific analysis supports sports players for improving their play styles and forms. The player's motions in an actual sport are so fast and spatial that the physical motions need to be measured with high temporal resolution in three dimensions for analysis. Widely used motion capture system requires number of optical markers attached on the body surface, which might constrain the natural motion for the sport play. This research proposes a 3D measurement method of sport motion without disturbing the player, using a stereo pair of high-speed cameras and model matching approach.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

This paper describes the design, implementation and testing of a near real-time vision system, which facilitates the immersion into a 360 degree environment. It details the mechanical device, which is based around multiple camera's of various resolutions and types, which are implemented, in part, on a reconfigurable network of general purpose FPGA processors. The paper gives performance figures gained both from vision network tests on the Unmanned Aerial Vehicle platform alone and from closed loop tests on the entire FPGA system using visual feedback from actual flight tests.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

In this paper, a novel method is proposed for detection of signals from the observation data corrupted by nonstationary random noise. Key approach is to estimate time-varying coefficients related as nonstationarity from the observation data and the observation data is transformed to stationarity process. As a method of signal detection, stationarity test is employed. Several numerical simulations show that our proposed method is effective to detect signals.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

The use of soft computing techniques such as neural networks and fuzzy engineering in the financial market has recently become one of the most exciting and promising application areas. In this paper, we propose a new decision support system (DSS) for dealing stocks which impropves the traditional technical analysis by using neural networks. In the proposed system, neural networks are utilized in order to predict the "Golden cross" ("Dead Cross") several weeks before it occurs.Computer simulation results concerning the dealings of the Nikkei-225 and several individual stocks confirm the effectiveness of the proposed DSS.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

At preset research and development, the rescue and search robot were introduced mainly about the special project for earthequake disaster mitigation in urban areas. Smart house and symbiosis of robot and human described in this paper. The assistant system of search and rescue activities for home was by adopting the concept of smart house and symbiosis with robot. The flow of rescue activities used the symbiosis type rescue robot by the assistant system of search and rescue activities for home was considered. The rescue and search activities support system for home consists with various sensors, interphone type rescue robot and home networks and the database system.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

The aim of this study is to develop a simulator enabling a palpation skill for identifying tumor region. Shape perception is significant in a situation of indirect touch for the aim. Friction forces make an important role considering a foregoing report. This paper proposes a friction model, which gives stable and proper friction forces proportional to normal forces in a situation of indirect touch. The results of experiments indicated that the proposed friction model enhanced accuracy of indirect perception of convex shape.

View full abstract

[in Japanese]

View full abstract