The food industry makes an effort for development of food products to satisfy various needs of consumers. They must evaluate foods from various viewpoints to satisfy the sensibility of consumers: a physical characteristic, a chemical, nourishment, price, seasoning, temperature, etc. To secure reproducibility by evaluating the features of the food product quantitatively and objectively is useful to establish the manufacturing method of the food product. We pay attention to the food index that the quantitative and objective evaluation with the machinery has not been carried out although the panel test has been carried out, and suggest a new method to mechanize this. We focus on chewy texture that are important property to decide the taste, and suggest a method to check hard/soft distribution in an elastic food. In this article, we explain an application method of the new technique for an example by the design of rice noodle.

抄録全体を表示

The market of e-book has been growing fast and showing a great potential recently. However, the traditional printed books are still predominating the major market. Most people still prefer printed book despite e-book's advantages. In this study, we conducted an experiment involving 34 participants to determine the difference between e-book and printed book in terms of user experience. We hypothesized that different contents would influence the result, therefore we chose two different genres of books: magazine and the Japanese comic book - manga. Participants were asked to read on E-Reader and printed book, then asked to evaluate their experience using questionnaire. ANOVA, Wilcoxon signed-rank test, multiple regression analysis and principal component analysis were conducted to analyze the difference between each group and correlative factors that affected overall evaluation. The result indicated that printed books were rated higher than e-books, and manga was more applicable to e-book than magazine.

抄録全体を表示

Recently there is a growing need for affect-awareness in computer games. In-game emotion recognition, however, requires applying costly feature extraction methods and/or labor-demanding annotation of large datasets. To make emotion recognition cost-efficient, this study proposes (A) a social relations-directing, “emotion-sensitive” dialogue act model consisting of social acts, and (B) an approach for emotion recognition, utilizing the association strength ratio of emotion types and the proposed acts. In the study, five Japanese in-game dialogues were tagged with labels of emotion types and of social acts. Emotion type-social act co-occurrence was analyzed, and the corresponding association strength ratios were computed. In a validation experiment, the proposed approach was tested, enhancing a baseline emotion classifier's recognition accuracy by 8%.

抄録全体を表示