Staudenmayer John, Pober David, Crouter Scott, Bassett David, Freedson Patty
Dept. of Mathematics and Statistics, Univ. of Massachusetts, Lederle Graduate Research Center, Amherst, MA 01003, USA.
J Appl Physiol (1985). 2009 Oct;107(4):1300-7. doi: 10.1152/japplphysiol.00465.2009. Epub 2009 Jul 30.
The aim of this investigation was to develop and test two artificial neural networks (ANN) to apply to physical activity data collected with a commonly used uniaxial accelerometer. The first ANN model estimated physical activity metabolic equivalents (METs), and the second ANN identified activity type. Subjects (n = 24 men and 24 women, mean age = 35 yr) completed a menu of activities that included sedentary, light, moderate, and vigorous intensities, and each activity was performed for 10 min. There were three different activity menus, and 20 participants completed each menu. Oxygen consumption (in ml x kg(-1) x min(-1)) was measured continuously, and the average of minutes 4-9 was used to represent the oxygen cost of each activity. To calculate METs, activity oxygen consumption was divided by 3.5 ml x kg(-1) x min(-1) (1 MET). Accelerometer data were collected second by second using the Actigraph model 7164. For the analysis, we used the distribution of counts (10th, 25th, 50th, 75th, and 90th percentiles of a minute's second-by-second counts) and temporal dynamics of counts (lag, one autocorrelation) as the accelerometer feature inputs to the ANN. To examine model performance, we used the leave-one-out cross-validation technique. The ANN prediction of METs root-mean-squared error was 1.22 METs (confidence interval: 1.14-1.30). For the prediction of activity type, the ANN correctly classified activity type 88.8% of the time (confidence interval: 86.4-91.2%). Activity types were low-level activities, locomotion, vigorous sports, and household activities/other activities. This novel approach of applying ANNs for processing Actigraph accelerometer data is promising and shows that we can successfully estimate activity METs and identify activity type using ANN analytic procedures.
本研究的目的是开发并测试两种人工神经网络（ANN），以应用于通过常用单轴加速度计收集的身体活动数据。第一个ANN模型估计身体活动代谢当量（METs），第二个ANN识别活动类型。受试者（24名男性和24名女性，平均年龄 = 35岁）完成了一系列活动，包括久坐、轻度、中度和剧烈强度活动，每项活动持续10分钟。共有三种不同的活动菜单，20名参与者完成了每种菜单。连续测量耗氧量（以毫升×千克⁻¹×分钟⁻¹为单位），并使用第4至9分钟的平均值来代表每项活动的耗氧成本。为了计算METs，将活动耗氧量除以3.5毫升×千克⁻¹×分钟⁻¹（1个MET）。使用Actigraph 7164型号加速度计每秒收集一次数据。在分析中，我们将计数分布（每分钟逐秒计数的第10、25、50、75和90百分位数）和计数的时间动态（滞后、一个自相关）作为ANN的加速度计特征输入。为了检验模型性能，我们使用了留一法交叉验证技术。ANN对METs的预测均方根误差为1.22 METs（置信区间：1.14 - 1.30）。对于活动类型的预测，ANN正确分类活动类型的时间占88.8%（置信区间：86.4 - 91.2%）。活动类型包括低强度活动、移动、剧烈运动以及家务活动/其他活动。这种将ANN应用于处理Actigraph加速度计数据的新方法很有前景，表明我们可以使用ANN分析程序成功估计活动METs并识别活动类型。
