Project/Area Number |
17K00783
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Clothing life/Dwelling life
|
Research Institution | Kanazawa University |
Principal Investigator |
Hidetaka Nambo 金沢大学, 電子情報通信学系, 准教授 (30322118)
|
Project Period (FY) |
2017-04-01 – 2020-03-31
|
Project Status |
Completed (Fiscal Year 2019)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
Keywords | 室内モニタリング / IoT / 植物センサ / 高齢化社会 / 植物生体電位 / センサネットワーク / エージェント / 位置・振る舞い推定 / センサエージェント |
Outline of Final Research Achievements |
In this study, we are focusing on the realize an indoor monitoring using plants. Previous results have shown that the area which plants can detect human movement is narrow. Therefore, in this study, we investigated an algorithm for monitoring by using multiple plants. Estimating each plant installed in the room, and aggregating the results. As a result of the study, it was found that CNN is effective as an estimation model and that it is better to estimate human movement by aggregating the measured data than by estimating individual plants. However, since aggregation has the disadvantage that it has problems on the increase of the number of plants or the computational cost. On the other hand, estimating individually has the advantage for such problems. However, it has the requirement to improve accuracy are needed in the future.
|
Academic Significance and Societal Importance of the Research Achievements |
高齢者社会の進行により、室内モニタリングの需要は高まっているが、センサによって監視されることへの心理的抵抗は高い。本研究では、植物をセンサとして用いることで、心理的な抵抗を減らした室内モニタリングの実現を目指している。現時点では、植物センサの性能は不十分であるため、精度の高い学習手法や複数のセンサを有効に組み合わせて利用する方法の検討を行った。研究成果は、植物を用いた実用的な室内モニタリングの実現の指針となり、さらなる高齢化社会に対して有効であると言える。
|