| Project/Area Number |
17K00400
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Life / Health / Medical informatics
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
Morita Hiroyoshi 電気通信大学, 大学院情報理工学研究科, 教授 (80166420)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
太田 隆博 長野県工科短期大学校, 情報技術科, 教授 (60579001)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 心電図 / 不整脈 / 反辞書 / 極小禁止語 / 反辞書状態遷移確率モデル / 異常データ検出 / 心室性期外収縮 / 状態遷移確率モデル / PVC / ECG / 有限状態確率モデル / 量子化モデル / 瞬時圧縮率 / 健康情報 / 生体信号 / 異常波形検出 / 反辞書確率モデル |
|---|
| Outline of Final Research Achievements |
In response to the demand of ECG continuous monitoring and hidden arrhythmia detection systems with small wireless sensor attached on human body surface, a coding method is presented and implemented to memory constrained device. The proposed model is constructed based on antidictionary database that efficiently represents any patterns which never appear on a given data sequence and is suited to detect arrhythmia that rarely occurs on ECG data. As the results obtained through this research project, we have established 1) system implementation and evaluation, 2) to increase types of arrhythmia to be detected, 3) reliable communication system with a new coding modulation which can adapt to communication between a small sensor and a relay router, and 4) performance improvement of antidictionary probability model which is a basis of the detection system.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究成果は，これまでデータ圧縮の観点から研究が進められてきた反辞書符号化法において中心的な役割を果たす反辞書確確率モデルを適切に用いれば，心電図データに突発的に発生する不整脈(隠れ不整脈)の検知に有効であることを実証したことと，同時に，心電図データの差分化・量子化を行うことにより検知システムをスマフォ端末への実装を可能にした点にある．心電センサとスマフォ端末間のネットワーク通信や検知能力には改善の余地が残されているものの，それらの改良がさらに進めば，日常生活を送る中で心疾患の早期発見に役立ち，利用者のOoL向上に寄与するものと期待される．
|
