Chun Keum San, Jeong Hyoyoung, Adaimi Rebecca, Thomaz Edison
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:4361-4364. doi: 10.1109/EMBC44109.2020.9175949.
Recent work in Automated Dietary Monitoring (ADM) has shown promising results in eating detection by tracking jawbone movements with a proximity sensor mounted on a necklace. A significant challenge with this approach, however, is that motion artifacts introduced by natural body movements cause the necklace to move freely and the sensor to become misaligned. In this paper, we propose a different but related approach: we developed a small wireless inertial sensing platform and perform eating detection by mounting the sensor directly on the underside of the jawbone. We implemented a data analysis pipeline to recognize eating episodes from the inertial sensor data, and evaluated our approach in two different conditions: in the laboratory and in naturalistic settings. We demonstrated that in the lab (n=9), the system can detect eating with 91.7% precision and 91.3% recall using the leave-one-participant-out cross-validation (LOPO-CV) performance metric. In naturalistic settings, we obtained an average precision of 92.3% and a recall of 89.0% (n=14). These results represent a significant improvement (>10% in F1 score) over state-of-the-art necklace-based approaches. Additionally, this work presents a wearable device that is more inconspicuous and thus more likely to be adopted in clinical applications.
近期在自动饮食监测（ADM）方面的工作通过使用安装在项链上的接近传感器跟踪颌骨运动，在饮食检测方面显示出了有前景的结果。然而，这种方法面临的一个重大挑战是，自然身体运动引入的运动伪影会导致项链自由移动，传感器出现错位。在本文中，我们提出了一种不同但相关的方法：我们开发了一个小型无线惯性传感平台，并通过将传感器直接安装在颌骨下方来进行饮食检测。我们实现了一个数据分析管道，以从惯性传感器数据中识别饮食事件，并在两种不同条件下评估了我们的方法：在实验室和自然环境中。我们证明，在实验室环境下（n = 9），使用留一参与者交叉验证（LOPO - CV）性能指标，该系统检测饮食的精度为91.7%，召回率为91.3%。在自然环境中，我们获得了92.3%的平均精度和89.0%的召回率（n = 14）。这些结果相对于基于项链的现有方法有了显著改进（F1分数提高超过10%）。此外，这项工作展示了一种更不引人注意的可穿戴设备，因此更有可能在临床应用中被采用。
