Environmental Research Laboratory, I.N.RA.S.T.E.S., NCSR "DEMOKRITOS", Athens, Greece.
Department of Applied Physics, Faculty of Physics, University of Athens, Athens, Greece.
Environ Monit Assess. 2018 Feb 20;190(3):155. doi: 10.1007/s10661-018-6537-2.
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.
如今，移动技术的进步与暴露组学概念的引入为暴露研究带来了新的活力。由于解决与环境应激相关的健康结果至关重要，因此改进暴露评估方法至关重要。为此，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追踪器和 Moves App 在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类型方面的适用性。在研究过程中，有 21 名参与者使用 Fitbit Flex 活动追踪器、温度记录器和智能手机上的 Moves App。为了验证上述设备，参与者还携带了 Actigraph（活动传感器）和 GPS 设备。将来自 Fitbit Flex、温度记录器和 GPS（速度）的数据用作人工神经网络 (ANN) 模型的输入参数，以预测位置类型。数据分析表明，与 Fitbit Flex 和 Actigraph 相比，Moves App 往往会低估日常步数，而 Moves App 则可以合理准确地预测个人的运动轨迹，与专用 GPS 相比。最后，ANN 在大多数情况下成功预测了遇到的位置。
