著者
坂本 真樹 小野 正理 清水 祐一郎
出版者
一般社団法人 人工知能学会
雑誌
人工知能学会全国大会論文集 第26回全国大会(2012)
巻号頁・発行日
pp.2N1OS8c2, 2012 (Released:2018-07-30)

病気の症状はしばしば「ずきずき」といったオノマトペで直感的に表現される.痛みの強さに比べ,痛みの質は定量化が難しいとされてきた.痛みの量と質の両者を表現できるオノマトペは,電子化されてきた医療への導入が期待される.本研究では,オノマトペの音韻特性と医療用尺度の印象評価値の関係を特定する被験者実験によりデータベースを作成し,オノマトペによって表される症状を定量的に推定し出力するシステムを作成した.
著者
渡邊 淳司 加納 有梨紗 坂本 真樹
出版者
Japan Society of Kansei Engineering
雑誌
日本感性工学会論文誌 (ISSN:18840833)
巻号頁・発行日
vol.13, no.2, pp.353-359, 2014 (Released:2014-04-30)
参考文献数
35
被引用文献数
6 2

Although human beings are capable of discerning a variety of textures through the sense of touch, there is as yet no consensus as to how best to classify those textures. To resolve this problem, we proposed a novel method of categorizing tactile textures using onomatopoeic words in Japanese. Based on the impressions they evoke, onomatopoeic words pertaining to tactile sensations are distributed on a two-dimensional space, making it possible to visualize how different tactile sensations are related to one another. Combining the results obtained with the subjects' evaluations of the materials touched in terms of how pleasant or unpleasant they find those materials, this paper attempts to visualize on a two-dimensional space the relationship between the pleasantness/unpleasantness associated with the materials and the tactile sensations that they evoke.
著者
鍵谷 龍樹 白川 由貴 土斐崎 龍一 渡邊 淳司 丸谷 和史 河邉 隆寛 坂本 真樹
出版者
一般社団法人 人工知能学会
雑誌
人工知能学会論文誌 (ISSN:13460714)
巻号頁・発行日
vol.30, no.1, pp.237-245, 2015-01-06 (Released:2015-01-06)
参考文献数
25
被引用文献数
1

We feel some liquids such as honey or oil more viscous than others like water. Viscosity perception is frequently expressed by onomatopoeia, a set of words that are often used to express sensory experiences in Japanese. For example, we would say honey is “toro-toro” or oil is “doro-doro”. In this paper we investigated the associations between phonemes of Japanese onomatopoeia for expressing viscosity and subjective evaluations of viscosity. Specifically, we performed psychological experiments where participants watched some static images and dynamic images. Participants were asked to express the visual sensations by onomatopoeia and rate the degree to which they felt the objects viscous. This experiment was aimed at specifying the systematic association between phonemes of Japanese onomatopoeic words and viscous evaluations. Our results showed the existence of some associations between the phonemes of the words for expressing the sensation and the evaluations of viscosity and showed the possibility to construct a system to recommend viscosity animations by onomatopoeia. The system proposed in this paper recommends viscosity animations consistent with onomatopoetic expressions based on Japanese sound symbolism. Our system comprises a user interface module, an onomatopoeia parsing module, and a database. Our system can evaluate the subtle difference in viscosity feelings expressed by onomatopoeic words which are different in phonemes.
著者
上田 祐也 清水 祐一郎 坂口 明 坂本 真樹
出版者
特定非営利活動法人 日本バーチャルリアリティ学会
雑誌
日本バーチャルリアリティ学会論文誌 (ISSN:1344011X)
巻号頁・発行日
vol.18, no.4, pp.455-463, 2013

In medical interviews, Japanese patients often use onomatopoeia such as "zuki-zuki" and "gan-gan" to express their pains or medical conditions. Using onomatopoeia when expressing pain enables simpler and more direct expressions than normal language as well as expresses the quantity (level/intensity) and quality (location/depth) of the pain. However, the subtle differences in characteristics of pain (such as quality), for example between "zeh-zeh" and "zero-zero", are difficult to grasp accurately. Although grasping these differences accurately is said to be critical, it depend on the level of skill of a doctor. So in this study, we constructed a system which supports communication between patients and doctors by evaluating meanings expressed by onomatopoeia. When a user inputs Japanese onomatopoeia, our system estimates quantities and qualities of pains using the relationships between the sounds used in the onomatopoeia and meanings expressed by 35 rating scales such as "sharp - dull", "strong - weak", and "deep - shallow". Visualizing of pains will help to compare between conventional onomatopoeic words such as "zeh-zeh" and novel words such as "zero-zero".
著者
飯場 咲紀 志賀 彩乃 坂本 真樹
出版者
人工知能学会
雑誌
人工知能学会全国大会論文集 (ISSN:13479881)
巻号頁・発行日
vol.26, 2012

本研究では,「ふわふわ」といった触覚を表すオノマトペのイメージに適した色彩推定システムを提案する.オノマトペを構成する音韻を基に,オノマトペの印象を感性評価尺度で定量化し,同じ感性評価尺度で印象を評価した色彩との類似度を算出する.システムによる推定色彩がオノマトペのイメージに適しているかを検証し,本システムの評価を行った.ユーザの所望する質感と色が調和した素材提案システムへの可能性を示唆する.
著者
土斐崎 龍一 清水 祐一郎 坂本 真樹
出版者
人工知能学会
雑誌
人工知能学会全国大会論文集 (ISSN:13479881)
巻号頁・発行日
vol.26, 2012

毎年約10万件以上の商標が国内で新規登録されており,新奇性のあるブランドネームの開発は年々難しくなっている.本研究は,ブランドネームの音象徴を被験者実験により調査し,ブランドネームが人に喚起する印象の予測値を定量的に出力するシステムを開発した.このシステムを用いることで,ユーザが付加したいイメージに即したブランドネームの提案が可能となり,企業において創造的なブランドネームの開発支援が期待できる.