IEEE J Biomed Health Inform. 2023 Aug;27(8):3878-3888. doi: 10.1109/JBHI.2023.3276629. Epub 2023 Aug 7.
Automated detection of intake gestures with wearable sensors has been a critical area of research for advancing our understanding and ability to intervene in people's eating behavior. Numerous algorithms have been developed and evaluated in terms of accuracy. However, ensuring the system is not only accurate in making predictions but also efficient in doing so is critical for real-world deployment. Despite the growing research on accurate detection of intake gestures using wearables, many of these algorithms are often energy inefficient, impeding on-device deployment for continuous and real-time monitoring of diet. This article presents a template-based optimized multicenter classifier that enables accurate intake gesture detection while maintaining low-inference time and energy consumption using a wrist-worn accelerometer and gyroscope. We designed an Intake Gesture Counter smartphone application (CountING) and validated the practicality of our algorithm against seven state-of-the-art approaches on three public datasets (In-lab FIC, Clemson, and OREBA). Compared with other methods, we achieved optimal accuracy (81.60% F1 score) and very low inference time (15.97 msec per 2.20-sec data sample) on the Clemson dataset, and among the top performing algorithms, we achieve comparable accuracy (83.0% F1 score compared with 85.6% in the top performing algorithm) but superior inference time (13.8x faster, 33.14 msec per 2.20-sec data sample) on the In-lab FIC dataset and comparable accuracy (83.40% F1 score compared with 88.10% in the top-performing algorithm) but superior inference time (33.9x faster, 16.71 msec inference time per 2.20-sec data sample) on the OREBA dataset. On average, our approach achieved a 25-hour battery lifetime (44% to 52% improvement over state-of-the-art approaches) when tested on a commercial smartwatch for continuous real-time detection. Our approach demonstrates an effective and efficient method, enabling real-time intake gesture detection using wrist-worn devices in longitudinal studies.
使用可穿戴传感器自动检测摄入动作一直是研究的关键领域，有助于深入了解并干预人们的饮食习惯。已经开发并评估了许多算法，主要关注其准确性。然而，确保系统不仅能够准确预测，而且效率高，这对于实际部署至关重要。尽管使用可穿戴设备准确检测摄入动作的研究越来越多，但这些算法通常效率低下，阻碍了在设备上部署以连续实时监测饮食。本文提出了一种基于模板的优化多中心分类器，该分类器使用腕戴式加速度计和陀螺仪，在保持低推断时间和低能耗的同时，实现准确的摄入动作检测。我们设计了一个摄入动作计数器智能手机应用程序（CountING），并使用三个公共数据集（实验室 FIC、克莱姆森大学和 OREBA）中的七个最先进的方法验证了我们算法的实用性。与其他方法相比，我们在克莱姆森数据集上实现了最佳的准确性（81.60%F1 得分）和非常低的推断时间（15.97 毫秒/每 2.20 秒数据样本），在表现最好的算法中，我们实现了可比的准确性（83.0%F1 得分，而表现最好的算法为 85.6%），但推断时间更快（快 13.8 倍，33.14 毫秒/每 2.20 秒数据样本），在实验室 FIC 数据集上，我们实现了可比的准确性（83.40%F1 得分，而表现最好的算法为 88.10%），但推断时间更快（快 33.9 倍，16.71 毫秒推断时间/每 2.20 秒数据样本）。在 OREBA 数据集上，我们的方法在平均测试 25 小时的电池寿命（比最先进的方法提高 44%到 52%），在商业智能手表上进行连续实时检测时，我们的方法显示出了一种有效且高效的方法。
