2017 Fiscal Year Final Research Report
Health score prediction from sensor based behavior pattern analysis
| Project/Area Number |
25700026
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (A)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Research Field |
Intelligent robotics
|
|---|
| Research Institution | Tokyo Institute of Technology (2016-2017)
The University of Tokyo (2013-2015) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2018-03-31
|
| Keywords | 実世界情報処理 / 行動センシング / 統計的行動情報処理 / 機械学習 / センサシステム |
|---|
| Outline of Final Research Achievements |
The scores of health state for elderly people are needed as the expression of the change of patient state or as information for medical decision-making. The health assessment for elderly people is surveyed by questionnaires; however, the execution rate is still low due to the cost of the surveys. It is prominent if capturing the behavior of elderly people continuously and pervasively is realized to understand one’s health condition. However, no technologies on capturing one’s behavior precisely and continuously are established. In this research, we developed a unified methodology towards quantitative and automatic assessment of elderly people via innovative IoT technology. In the project, we developed automated system for behavior sensing and its recognition techniques (e.g. indoor localization from wireless signals), feasibility study with subjects of elderly people, and robust statistical techniques for the issue of health score prediction from the behavior data.
|
| Free Research Field |
実世界情報処理
|
