Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
Online ISSN : 1881-7203
Print ISSN : 1347-7986
ISSN-L : 1347-7986
Volume 28 , Issue 1
Showing 1-16 articles out of 16 articles from the selected issue
Regular
Original Papers
  • Isao HAYASHI, Shinji TSURUSE
    2016 Volume 28 Issue 1 Pages 501-510
    Published: February 15, 2016
    Released: February 26, 2016
    JOURNALS FREE ACCESS
    Brain-computer interface (BCI) and brain-machine interface (BMI) technologies have recently entered the research limelight. In many such systems, external computers and machines are controlled by brain activity signals measured using near-infrared spectroscopy (NIRS) or electroencephalograph (EEG) devices. In this paper, we propose a new boosting algorithm for BCI using a possibilistic data interpolation scheme. In our model, interpolated data is generated around classification errors using membership function, and the class attribute is decided by a rule with three kinds of criterions. By using the interpolated data, the discriminated boundary is shown to control the external machine effectively. We verify our boosting method with some numerical examples in which NIRS data is assumed to detect from subjects, and discuss the results.
    Download PDF (8561K)
  • Kazuki HAYAKAWA, Dai HASEGAWA, Hiroshi SAKUTA
    2016 Volume 28 Issue 1 Pages 511-521
    Published: February 15, 2016
    Released: February 26, 2016
    JOURNALS FREE ACCESS
    One of the most promising methods for drum training is through watching 3D model animation. We propose a drum training method through the utilization of a first-person 3D model animation program and examine the effects of presenting experts'eye movements on drum training. We evaluated learning efficacy through the use of a questionnaire and analyzed drum performances after a first-person 3D model animation was presented as a learning material. After comparing the results of the proposed method with the learning which took place after watching a model human performance, we found that the proposed method significantly increased learner self-efficacy and self-evaluation of the musical performances when compared with the other method. Moreover, the proposed method resulted in a decrease in the number of mistakes in the performances. Finally, the effects of presenting experts'eye movements in the animation model on learners were evaluated. These results also showed that learner self-efficacy and self-evaluation of the musical performances increased while the number of performance mistakes decreased.
    Download PDF (3082K)
  • Akira NOTSU, Hirokaz KAWAKAMI, Katsuhiro HONDA, Seiki UBUKATA
    2016 Volume 28 Issue 1 Pages 522-534
    Published: February 15, 2016
    Released: February 26, 2016
    JOURNALS FREE ACCESS
    The goal of this study was to develop the efficient optimization methods with roughly estimating the values in the areas and considering the exploration and exploitation in the optimization problem. First, we proposed Grid Area Search (GAS) algorithm as a base of our methods by upgrading the random search (RS) algorithm which is the simplest algorithm for the mathematical programming problem. Specifically, our methods convert the mathematical programming problem to the Multi-armed bandit problem by dividing search space. Therefore, it is assumed that the coordination of the exploration and exploitation can be introduced by the UCB algorithms. Then we also proposed UCB-GAS and UCT-GAS. We performed comparative experiments in continuous optimization problems to make sure its convergence speed.
    Download PDF (4058K)
  • Arnaud JORDAN, Kenji ARAKI
    2016 Volume 28 Issue 1 Pages 535-555
    Published: February 15, 2016
    Released: February 26, 2016
    JOURNALS FREE ACCESS
    This article presents an innovative dialogue agent designed for textual casual chatting, which can handle any language. The system acquires knowledge from a non-annotated corpus and then represents all the language aspects as a graph. Using graph traversal, the system generates one or several outputs corresponding to the user's input. Moreover, it uses graph clustering to generate word categories without using any grammar information, and finally uses these to generate more various responses. In addition, all the operations are processed in parallel, making the system able to process any input in real-time, as in human conversations. Since the system accepts any kind of input, it can also be considered to be naturally multimodal. We carried out experiments in Chinese, English, French, Japanese and Korean, and obtained results comparable to a more language-specific multilingual system. Although the current system deals only with a limited corpus and as a consequence only handles simple dialogues, we demonstrate that with further interaction and language samples it is able to adapt to more sophisticated dialogues.
    Download PDF (1228K)
feedback
Top