2023 Fiscal Year Final Research Report
Development of High-dimensional Body Activity Time Series Analysis Methods for Unobtrusive Sleep Monitoring
| Project/Area Number |
21K12040
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Kansai University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 睡眠計測 / 時空間データ解析 / 時系列解析 / パターン抽出 / 信号源分離 / 時系列クラスタリング / 異常検出 |
|---|
| Outline of Final Research Achievements |
In this study, we worked on developing unique data analysis technology to extract spatiotemporal patterns characterizing respiratory abnormalities during sleep from high-dimensional time series of body pressure distribution data captured using non-intrusive measurement. The efforts were divided into two main technological developments. One is the development of computational methods for estimating respiratory motion and its spatial distribution from body pressure time series, which separate blind signal sources from complex time series involving various types of body motion. The other is the development of computational methods for detecting abnormalities in respiratory motion waveforms, which extract respiratory motion patterns valuable for detecting abnormal events such as sleep apnea by applying change point detection and time series clustering methods.
|
| Free Research Field |
システム工学
|
| Academic Significance and Societal Importance of the Research Achievements |
日本人の5人に1人が睡眠に問題を抱えているといわれている．睡眠中は意識を喪失しているために異常が生じても自覚症状に乏しい．そのような睡眠中の異常に対する調査や処置効果の継続的確認の方法として，症状に関する情報が自然と収集されることが理想である．呼吸運動は複雑な様相を呈するため，パターン抽出と判別には高度なデータ処理が求められる．本研究の開発技術は，精緻な非干渉型の睡眠計測と呼吸異常の検出に貢献する．
|
