Wyniki wyszukiwania - BazTech

1

Improvement of performance of Japanese P300 speller by using second display

Yamamoto Y., Yoshikawa T., Furuhashi T.

Journal of Artificial Intelligence and Soft Computing Research

|

2015

|

Vol. 5, No. 3

221--226

EN

Brain computer interface (BCI) is a system allows a user to control external devices or to communicate with other people using only his or her thoughts. The P300 speller is one such BCI in which users input letters. For inputting letters via the P300 speller, higher accuracy and shorter input times are needed, especially given densely populated display screens. We propose a new interface with a second display in the P300 speller that the user can switch to and from by selecting the “next” or “back” commands, therby reducing the density of displayed letters and improving the performance of the P300 speller. We show the comparison results in terms of accuracy and input times between the conventional interface and proposed interface.

2

An emotional expression model for educational-support robots

Jimenez F., Yoshikawa T., Furuhashi T., Kanoh M.

Journal of Artificial Intelligence and Soft Computing Research

|

2015

|

Vol. 5, No. 1

51--57

EN

With the growth of robot technology, robots that assist learning have attracted increasing attention. However, users tend to lose interest in educational-support robots. To solve this problem, we propose a model of emotional expression based on human-agent interaction studies. This model in which the agent autonomously expresses the user’s emotions establishes effective interactions between agents and humans. This paper examines the psychological effect of a robot that is operated by the model of emotional expressions and the role of this effect in prompting collaborative learning.

3

Effect of robot utterances using onomatopoeia on collaborative learning

Jimenez F., Kanoh M., Yoshikawa T., Furuhashi T., Nakamura T.

Journal of Artificial Intelligence and Soft Computing Research

|

2014

|

Vol. 4, No. 2

125--131

EN

We investigated the effect of robot’s utterances using onomatopoeia in collaborative learning. The robot was designed to provide encouragement using onomatopoeia when students are given problems to be solved issued by a learning system. Eight college students used a mathematics learning system with a robot for three weeks and then took exams. The results indicated that the robot using utterances with onomatopoeia could comfort learners more than the robot without onomatopoeia. It suggests that the robot that praises or comforts using onomatopoeia helps learners maintain their motivation in collaborative learning.

4

Stability analysis of fuzzy controll systems simplified as a discrete system

Hasegawa T., Furuhashi T.

Control and Cybernetics

|

1998

|

Vol. 27, no 4

565-577

EN

Fuzzy controls can describe control rules using fuzzy if-then rules and it can incorporate experts' control rules. It is, however, difficult to guarantee the stability of fuzzy control system. This paper presents a new method for stability analysis of fuzzy control system using petri nets. The proposed method crisply divides all of the input and output variables of the fuzzy controller and the fuzzy model of the controlled object. This crisp division makes the fired rules of the fuzzy controller and the fuzzy model, which have truth values greater then 0, be single each. These simplified fuzzy rules can be considered as discrete description of the controller and the controlled object. By approximating and the fuzzy control system as this discrete system, the system can be expressed by the petri nets. The proposed method describes the fuzzy control system using matrix based on a bipartite directed multigraph of the petri net, thereby enables to analyse the stability of the fuzzy control system. The analytic results using the petri nets have clear correspondence to the fired fuzzy rules. The dynamical behavior of the system are able to be understood easily. Simulation is done to verify the proposed stability analysis method.