One onomatopoeia word has plural senses. A modified verb of an onomatopoeia, which is clue to decide a meaning of onomatopoeia, is investigated in this paper. Modified verbs are extracted from sentences in the "local assembly corpus2010"(LAC2010). The sets of "onomatopoeia and modified verb"(O-MV sets) used with high frequency with asingle sense in the LAC2010 are examined by using two other corpuses. One is a same genre corpus, the "local assemblycorpus 2008-09" (LAC2008-09). The other is the corpus which includes various genres of documents, the BCCWJ. 99.4% of O-MV sets in the LAC2008-09 have a same sense with the LAC2010. A modified verb contributes to decide the sense of onomatopoeia among certain genre of documents. 78.0% of O-MV sets in the BCCWJ have a same sense with the LAC2010. Negative examples in the BCCWJ are mainly caused by (i)errors of dependency analysis, (ii)orthographical variants and (iii)implication of plural senses. Onomatopoeia's sense which is decided with modified verb is not depending on the genre of document. However, there are some biases in occurrence of modified verb among the genre of documents.
Recently, more educational-support robots, which support learning, are paid attention to. However, the problem of these robots is that a user loses his/her interest in them. To solve this problem, some studies which focus on a model of emotional expressions have been reported in Human-Agent-Interaction. The model of emotional expressions is defined as the agent expressing its emotion with autonomous emotions. Although these models have been shown to be beneficial for effective interaction between an agent and a human, no reports have addressed the educational-support robots using these models. Thus, this paper studies how learning effect of robot which expresses the emotion by using the model of emotional expressions can prompt learners in a collaborative learning.
Expression education that improves the imagination and communication skills of learners has been gaining acceptance. Educationis currently carried out in a "one-to-many" environment. Therefore, it is not clear whether each learner is able to achieve his/her educational objectives through expression education, because it requires a class environment in which a teacher can engage in one-on-one communication with a learner. In this paper, we propose a robot that can support expression education in a one-to-one environment. We conducted an experiment to verify the effectiveness of the robot.
It was attempted that by adding adjusting of evaluation criteria of the nectar source of the honey bee in the Bee Colony Optimization (BCO) algorithm the variety of solutions was maintained. The efficiency of solution search raised by improving good solutions without abandoning a few worthless solutions.
Recently, various robots trying to communicate with and support for human beings, for example, pet-type and service robots, have been increasing. It is required to realize smooth communication skills with human beings for the robots. In this research, we aim to realize Interactive Emotion Communication(Interactive Emotion Communication: IEC) -which is a bidirectional communication based on emotional behaviors between a human and a robot. IEC consists of three processes- (1)inferring human emotion, (2)generating robot emotion, and (3)expressing robot emotion. The purpose of IEC is to raise the personal a.nity which the robot gives to the human by interactive emotional behaviors. In our previous research, the authors have proposed the "Fuzzy Emotion Inference System(FEIS)". The FEIS particularly focuses only on the process of "human emotion inference" by analyzing the human body motion values based on Laban's theory. It measures the basic psychological value by fuzzy reasoning and infers the emotion based on Russell's circumplex model. The "human emotion inference" should be tightly related to the "expressing robot emotion", however, the conventional methods do not take it into account. This paper proposes "Recurrent Neural Network with Russell's Circumplex Model(RNNRCM)" -which introduces Russell's circumplex model to a Recurrent Neural Network that learns human emotion inference through motion and robot emotional motion generation bidirectionally. The RNNRCM realizesthe process of "recognizing human emotion" and "expressing robot emotion" in the IEC. We confirm the efficacy of the proposed method with experiments.
The Fuzzy-Set Concurrent Rating Method (FCR method) was developed to measure a subjects' attitude more naturally when compared to the traditional rating method. This paper uses set function representations to present the fundamental idea required to obtain integrated values and expression degrees of one's opinion. The obtained results are noted as FCR scores. The set functions consist of "positive", "negative", "both positive and negative", and "unknown" values. The integrated values of the FCR-method are the Shapley values of the set function. In addition, we present the method to analyze a pair confrontational FCR questions and show the main effect and the sub effect of the questions on the subject.
This paper discusses the relative rating method to check order relations onomatopoeias expressing pains. There already has been "Pair test", which is a frequently used relative rating method. Its precision is high, yet a burden on subjects is heavy. Therefore we suggested the new relative rating method that has light burden and named this method "Sorting test". Up to the present, many kinds of sorting algorithms have been invented. The Sorting test used "Quick sort", which is said to take the shortest time to sort among the sorting algorithms. So that, the Sorting test evaluates at a small comparison number of times. In addition, we suggested an idea to quantify order relations. The idea can quantify each experimental stimulus regardless of the number of experimental stimuli to compare. Therefore, the idea is able to adjust the number of experimental stimuli.
In this paper, we propose a new Traveling Salesman Problem (TSP) solver based on Particle Swarm Optimization (PSO) Algorithm. PSO is one of the optimization methods classified into swarm intelligence, and consists of particles. Particles interact and move through solution space to find a better solution. PSO can find a good solution in a short time compared with Genetic Algorithm (GA) in many real-valued optimization problems. Because TSP is a combinatorial optimization problem, we change two points of the original PSO for solving TSP. The first point is that the position of each particle is represented by a tour instead of a vector. The second is that particles move by using Insertion method. Insertion method is an operation to combine a tour and sub-paths of other two tour. We analyze relation between parameters and length of an obtained tour, and indicate a guide to adjust parameters. The performance comparison result shows that the proposed method can find a better solution than Simulated Annealing (SA) and GA.
In this paper, we consider multiobjectve two-person zero-sum games with fuzzy payoff matrices. In order to deal with fuzzy payoff matrices, the possibility measure concept for the fuzzy goals of each player is introduced. Under the assumption that each player adopts the most disadvantage strategy for the opponent player, a pessimistic Pareto optimal solution concept is defined for each player. It is shown that any pessimistic Pareto optimal solution can be obtained on the basis of linear programming techniques, even if the membership functions for not only the fuzzy goals of the player but also elements of the fuzzy payoff matrices are nonlinear. We propose an interactive algorithm based on linear programming techniques to obtain a pessimistic compromise solution from among pessimistic Pareto optimal solutions. A numerical example illustrates the interactive processes under a hypothetical player to show the efficiency of the proposed method.
P300 speller is a communication tool based on Brain Computer Interfaces (BCIs) which allow users to input letters only by thoughts. It uses P300, one of the event-related potential (ERP), as the target feature. In P300 speller, another person starts and closes the system. It is not convenient for a motor impaired user to need other's help at every occasion of switching. To solve this problem, an asynchronous P300 speller which can control ON/OFF automatically based on the user's intention of input is needed. In recent years, the intention classification method with additional pre-training has been proposed. In the additional pre-training, the classifier trains non-control state data which are recorded when the user does not have intension to input letters. However, in order to improve the performance of intention classification, the additional signal recording in several non-control states is needed, which could be burdens for the user. In this paper, we propose and study an intention classification method using only training data in which a user input letters and an asynchronous system in P300 speller based on the user's intention of input.