2025-02-21 ノースカロライナ州立大学 (NC State)
<関連情報>
- https://news.wsu.edu/news/2025/02/21/researchers-make-up-for-missing-data-in-wearable-health-monitoring-sensors/
- https://www.ijcai.org/proceedings/2024/807
ウェアラブルヘルスアプリケーションにおけるエネルギー効率に優れた欠損データのインピュテーション: 分類器を意識した統計的アプローチ
Energy-Efficient Missing Data Imputation in Wearable Health Applications: A Classifier-aware Statistical Approach
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence Published:2024
DOI:https://doi.org/10.24963/ijcai.2024/807
Wearable devices are being increasingly used in high-impact health applications including vital sign monitoring, rehabilitation, and movement disorders. Wearable health monitoring can aid in the United Nations social development goal of healthy lives by enabling early warning, risk reduction, and management of health risks. Health tasks on wearable devices employ multiple sensors to collect relevant parameters of user’s health and make decisions using machine learning (ML) algorithms. The ML algorithms assume that data from all sensors are available for the health monitoring tasks. However, the applications may encounter missing or incomplete data due to user error, energy limitations, or sensor malfunction. Missing data results in significant loss of accuracy and quality of service. This paper presents a novel Classifier-Aware iMputation (CAM) approach to impute missing data such that classifier accuracy for health tasks is not affected. Specifically, CAM employs unsupervised clustering followed by a principled search algorithm to uncover imputation patterns that maintain high accuracy. Evaluations on seven diverse health tasks show that CAM achieves accuracy within 5% of the baseline with no missing data when one sensor is missing. CAM also achieves significantly higher accuracy compared to generative approaches with negligible energy overhead, making it suitable for wide range of wearable applications.
