A study of constructing multimodal emotion behavior corpus to improve dementia care

2015 Fiscal Year Final Research Report

• Project/Area Number: 25280038
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Multimedia database
• Research Institution: Shizuoka University
• Principal Investigator: TAKEBAYASHI YOICHI 静岡大学, 情報学部, 教授 (10345803)
• Co-Investigator(Kenkyū-buntansha): ISHIKAWA Shogo 静岡大学, 情報学部, 助教 (00626608) ; KIRIYAMA Shinya 静岡大学, 情報学部, 准教授 (20345804) ; HORIUCHI Hiroaki 静岡大学, 情報学部, 教授 (40221569) ; KITAZAWA Shigeyoshi 静岡大学, 情報学部, 教授 (00109018)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: 認知症コーパス / マルチモーダル / 知識構造

Outline of Final Research Achievements

1) We have developed a knowledge representation model in terms of intention and emotion. Focusing on the dementia care method by Humanitude, we have designed the model between care interactions. 2) We designed three layers for representing skills and named them “Intra-modality,” “Inter-modality” and “Multimodal-interaction.” We have developed a tool of multimodal behavior analysis based on the scheme to represent dementia care. These results are a part of the findings of empirical analysis of building human relationships. 3) We have developed a visualization system of dementia care skills based on multimodal communication features. We designed and filmed video contents demonstrating the extracted features. The results suggest that video contents with visualized data is useful for trainees when they are learning dementia care skills, and that it can give them awareness of the importance of communication techniques.

Free Research Field

ヒューマンインタフェース