著者

萩原 広道 水谷 天智 山本 寛樹 阪上 雅昭

出版者

日本認知科学会

雑誌

認知科学 (ISSN:13417924)

巻号頁・発行日

vol.30, no.4, pp.499-514, 2023-12-01 (Released:2023-12-15)

参考文献数

52

---

This study aimed to explore young children’s vocabulary development using a machine learning technique, variational autoencoder (VAE). The VAE is an unsupervised neural network that maps high-dimensional input data onto a dimension-reduced latent space and then regenerates the data. The complex input features could be visualized in a low-dimensional latent space while maintaining its interpretability. We used parent-reported questionnaire data extracted from a publicly available database, involving American young children (

著者

北尾 浩和 来田 宣幸 深田 智 中本 隆幸 小島 隆次 萩原 広道 野村 照夫

出版者

Japan Society of Kansei Engineering

雑誌

日本感性工学会論文誌 (ISSN:18845258)

巻号頁・発行日

pp.TJSKE-D-17-00039, (Released:2018-02-27)

参考文献数

26

---

The purpose of this research is to estimate quantitatively by using jump motion as a base material as the basic research about the effect the difference in the linguistics movement instructions on a performance. The effect of five instructions (“A: big jump.”, “B: jump after deeply bended knees.”, “C: highly jump.”, “D: maximum jump.”, “E: jump to touch the ceiling.”) on jump height was analyzed using KINECT. Result, the height of jump was E > D > C> B > A. In order to create high jump, it was found the instruction such as E, with the target point in the external of body was useful. In addition, as attention focused on the part instructed as the effect of the instruction focusing on the explicit of body part like B, it was suggested the attentiveness to other parts and the timing of the operation may be delayed. Instructions like D didn't lead to a high jump because the image of movement was ambiguous.

著者

萩原広道

出版者

写

巻号頁・発行日

vol.[10],

著者

萩原広道

出版者

写

巻号頁・発行日

vol.[20],