Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA.
Sensors (Basel). 2024 Jun 16;24(12):3898. doi: 10.3390/s24123898.
Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.
日常生活活动 (ADL) 的监测在衡量和响应个人管理基本生理需求的能力方面发挥着重要作用。有效的 ADL 监测识别系统必须成功识别出自然发生且频率较低的活动。然而，现有的系统主要侧重于识别更可分离、更受控的活动类型，或者在活动发生更频繁的平衡数据上进行训练。在我们的工作中，我们研究了将机器学习应用于从完全自然环境中收集的不平衡数据集所面临的挑战。这项分析表明，结合预处理技术来提高召回率和后处理技术来提高精度，可以为 ADL 监测等任务生成更理想的模型。在使用真实数据的用户独立评估中，这些技术使刷牙、梳头、行走和洗手等任务的基于事件的 F1 得分为 0.9 以上。这项工作解决了机器学习中的基本挑战，这些系统需要解决这些挑战才能在现实世界中部署并可靠地工作。
