Assessing and enhancing the utility of low-cost activity and location sensors for exposure studies
Assessing and enhancing the utility of low-cost activity and location sensors for exposure studies
复制标题
DOI：
10.1007/s10661-018-6537-2
复制
发表时间：
2018-03-01
影响因子：
3
通讯作者：
Sarigiannis, D.
中科院分区：
文献类型：
--
作者：
Asimina, Stamatelopoulou;Chapizanis, D.;Sarigiannis, D.
如今，随着移动的技术的进步以及“麻烦”概念的引入，为暴露研究提供了新的动力。由于解决与环境压力因素有关的健康后果至关重要，因此改进暴露评估方法至关重要。为了实现这一目标，在希腊的两个主要城市（雅典，塞萨洛尼基）进行了一项试点研究，调查了商业上可用的健身监测器和移动应用程序的适用性，以跟踪人们的位置和活动，以及使用先进的建模技术预测所遇到的位置的类型。在这项研究的框架内，21人正在使用Fitbit Flex活动跟踪器，温度记录器和智能手机上的应用程序Moves App。为了验证上述设备，参与者还携带了活动记录仪（活动传感器）和GPS设备。从Fitbit Flex、温度记录器和GPS（速度）收集的数据被用作人工神经网络（ANN）模型的输入参数，用于预测位置类型。数据分析显示，与Fitbit Flex和Actigraph相比，Moves App往往低估了每日步数，而与专用GPS相比，Moves App以合理的准确度预测了个人的运动轨迹。最后，在大多数情况下，人工神经网络成功地预测了遇到的位置。
Nowadays, the advancement of mobile technology in conjunction with the introduction of the concept of exposome has provided new dynamics to the exposure studies. Since the addressing of health outcomes related to environmental stressors is crucial, the improvement of exposure assessment methodology is of paramount importance. Towards this aim, a pilot study was carried out in the two major cities of Greece (Athens, Thessaloniki), investigating the applicability of commercially available fitness monitors and the Moves App for tracking people's location and activities, as well as for predicting the type of the encountered location, using advanced modeling techniques. Within the frame of the study, 21 individuals were using the Fitbit Flex activity tracker, a temperature logger, and the application Moves App on their smartphones. For the validation of the above equipment, participants were also carrying an Actigraph (activity sensor) and a GPS device. The data collected from Fitbit Flex, the temperature logger, and the GPS (speed) were used as input parameters in an Artificial Neural Network (ANN) model for predicting the type of location. Analysis of the data showed that the Moves App tends to underestimate the daily steps counts in comparison with Fitbit Flex and Actigraph, respectively, while Moves App predicted the movement trajectory of an individual with reasonable accuracy, compared to a dedicated GPS. Finally, the encountered location was successfully predicted by the ANN in most of the cases.