Development of an intelligent selection method for reminiscence contents in dementia care
| Project/Area Number |
16K12566
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Learning support system
|
|---|
| Research Institution | Kagawa University (2017-2019)
Kansai University of Social Welfare (2016) |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
中島 智晴 大阪府立大学, 人間社会システム科学研究科, 教授 (20326276)
山本 美輪 鳥取大学, 医学部, 教授 (70353034)
武智 尚子 香川大学, 医学部, 助教 (60839869)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 認知症ケア / 回想法 / 人工知能 / コンテンツ自動生成 / 自動生成システム / 感情認識 / 回想法コンテンツ |
|---|
| Outline of Final Research Achievements |
The purpose of this study is to develop an artificial intelligence system that does not rely only on the experience of the caregivers who selects useful presentation contents used in the reminiscence method for dementia patients to stabilize mental status and improve cognitive function (Butler R N,1963).
In this study, we improved with an artificial intelligence technique that reproduced the method of content selection that has been performed by the experts of practical reminiscence. We adopted information recommendation as an algorithmic method and worked on creating an information infrastructure for robots to present contents. Furthermore, the information recommendation algorithm selects an appropriate recollection content from our content database, and we have automated the flow in which the robot presents the selected contents.
|
| Academic Significance and Societal Importance of the Research Achievements |
回想法は高齢者に過去を想起して語ってもらうことで，認知機能・心理的安定を導き出す効果的な援助であることから，その実施においては，対象のこれまでの背景や経験などに即した内容であることが効果につながる．一方，介護職の離職率の悪化など，回想法に関する知識や経験が豊富な人材確保が困難な現状があり，実施者の経験に頼らない効果的な回想法実施のためコンテンツを人工知能技術により自動選択するAI技術を開発した．
|
Report
(5 results)
Research Products
(8 results)
