| Project/Area Number |
21K11335
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 59020:Sports sciences-related
|
|---|
| Research Institution | Ochanomizu University |
|---|
Principal Investigator |
tripette julien お茶の水女子大学, 文理融合 AI・データサイエンスセンター, 准教授 (30747481)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
オベル加藤 ナタナエル お茶の水女子大学, 基幹研究院, 講師 (10749659)
中潟 崇 国立研究開発法人医薬基盤・健康・栄養研究所, 国立健康・栄養研究所 身体活動研究部, 研究員 (40736865)
太田 裕治 お茶の水女子大学, 基幹研究院, 教授 (50203807)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2024)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2023: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2022: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2021: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | physical activity / activity tracker / IMU sensor / smart shoe / behavior recognition / machine learning / sensing technology / smartshoes / energy expenditure / activity recognition |
|---|
| Outline of Research at the Start |
Wearable devices able to quantify daily physical activity have been proved effective to help people develop active and healthy lifestyles. Recently, commercial activity trackers became increasingly popular among the general public, but scientific evidences have suggested predictions could be significantly inaccurate in several situations. In this research, we want to take advantage of the current advances in wearable sensing technology to develop a pervasive multi sensor activity tracking system able to evaluate accurately physical behaviors in a wide range of daily life situations.
|
| Outline of Final Research Achievements |
This research aimed to develop a multi-sensor network using activity trackers for the accurate assessment of physical behavior. Data were collected from IMU sensors worn on the wrist and hip, placed in the back trouser pocket, and from smart shoe devices. The IMU sensors provided information similar to that obtained from conventional activity trackers and smartphones, including accelerometer, gyroscope, and barometer data. The smart shoes supplied plantar pressure data.
Data from the first experiment were processed using machine learning techniques to develop algorithms capable of recognizing 11 sedentary and locomotive behaviors, achieving up to 88% accuracy. The second experiment incorporated smart shoe devices and focused on a subset of locomotive activities: walking, running, kickboard riding, and skateboarding. Kickboard and skateboard activities were recognized with 100% precision, enabling the development of activity-specific energy expenditure estimation algorithms.
|
| Academic Significance and Societal Importance of the Research Achievements |
定期的な身体活動は、健康的なライフスタイルの重要な要素として知られており、代謝異常や心血管疾患の予防、さらに健康的な加齢や精神的健康の維持に寄与します。近年では、ウェアラブルデバイスの普及により、人々は自らの身体行動に関するフィードバックを得やすくなり、よりアクティブな生活習慣の定着が期待されています。本研究は、身体行動を高精度で評価する手法の開発を通じて、定期的な身体活動への参加促進を目指すものです。
|
