| Project/Area Number |
15H02698
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Information network
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
Kazuya Murao 立命館大学, 情報理工学部, 准教授 (50609295)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
寺田 努 神戸大学, 工学研究科, 教授 (70324861)
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥17,940,000 (Direct Cost: ¥13,800,000、Indirect Cost: ¥4,140,000)
Fiscal Year 2018: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2017: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2016: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2015: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
|
|---|
| Keywords | ユビキタスコンピューティング / センサ情報処理 / スマートホーム / 情報システム |
|---|
| Outline of Final Research Achievements |
With the development of ubiquitous technology, a space that can control devices according to human's behavior has appeared by placing sensors in the environment, and the importance of human activity recognition technology is increasing. In this work, inexpensive and small sensors are installed on non-electric appliances such as toilet paper holder, shower head, dining table to realize non-electronics sensorization, and systems for user identification and user state recognition by multivariate analysis and machine learning are constructed. The system does not use image recognition and voice processing, and does not require carrying or mounting of equipment, therefore, the psychological and physical burden imposed on the user by this system is small, and it is a highly sustainable system.
|
| Academic Significance and Societal Importance of the Research Achievements |
センサを用いた人物識別および状態推定では，画像や音声認識，RFIDタグなどのリッチな手法を用いることで利用者には普段一般の生活とは異なる環境を強いてきた．天井に疎に配置した赤外線センサと非電化製品の利用データから，センサデータ処理技術および機械学習技術を駆使することで利用者の負担を最大限抑制しつつ人物トラッキング，移動予測，状態推定を行い，住宅と住人を管理・制御する．住宅内の人の情報の取得，行動予測，状態推定から人間や空間へのフィードバックという機構を確立することは，今後ユビキタス技術を実世界において広く一般に普及させる原動力となるポテンシャルを秘めており，ビジネス面でのインパクトも大きい．
|
