CISeD-Research Centre in Digital Services, Polytechnic Institute of Viseu, 3504-510 Viseu, Portugal.
Sensors (Basel). 2022 Mar 29;22(7):2617. doi: 10.3390/s22072617.
Precision nutrition is a popular eHealth topic among several groups, such as athletes, people with dementia, rare diseases, diabetes, and overweight. Its implementation demands tight nutrition control, starting with nutritionists who build up food plans for specific groups or individuals. Each person then follows the food plan by preparing meals and logging all food and water intake. However, the discipline demanded to follow food plans and log food intake results in high dropout rates. This article presents the concepts, requirements, and architecture of a solution that assists the nutritionist in building up and revising food plans and the user following them. It does so by minimizing human-computer interaction by integrating the nutritionist and user systems and introducing off-the-shelf IoT devices in the system, such as temperature sensors, smartwatches, smartphones, and smart bottles. An interaction time analysis using the keystroke-level model provides a baseline for comparison in future work addressing both the use of machine learning and IoT devices to reduce the interaction effort of users.
精准营养是一个备受关注的电子健康话题，涉及多个群体，如运动员、痴呆症患者、罕见病患者、糖尿病患者和超重人群。其实施需要严格的营养控制，首先由营养师为特定群体或个人制定饮食计划。然后，每个人根据饮食计划准备餐食并记录所有食物和水分的摄入。然而，遵循饮食计划和记录食物摄入的要求导致高辍学率。本文介绍了一种解决方案的概念、要求和架构，该方案可以帮助营养师制定和修改饮食计划，帮助用户遵循这些计划。通过集成营养师和用户系统并在系统中引入现成的物联网设备，如温度传感器、智能手表、智能手机和智能瓶，来最小化人机交互，从而实现这一目标。使用按键级模型进行交互时间分析，为未来使用机器学习和物联网设备来减少用户交互工作量的工作提供了一个基准。
