An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer
An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer
复制标题
DOI：
10.1152/japplphysiol.00465.2009
复制
发表时间：
2009-10-01
影响因子：
3.3
通讯作者：
Freedson, Patty
中科院分区：
文献类型：
--
作者：
Staudenmayer, John;Pober, David;Freedson, Patty
Staudenmayer J、Pober D、Crouter S、Bassett D、Freedson P。一种人工神经网络，用于估计身体活动能量消耗并根据加速度计识别身体活动类型。 J Appl Physiol 107: 1300-1307, 2009。首次发表于 2009 年 7 月 30 日； doi:10.1152/japplphyol.00465.2009.-本次调查的目的是开发和测试两个人工神经网络 (ANN)，以应用于使用常用的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 (MET)，第二个 ANN 模型确定活动类型。受试者（n = 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、中等和剧烈强度，每项活动持续 10 分钟。共有三种不同的活动菜单，每个菜单都有 20 名参与者完成。连续测量耗氧量（单位：ml.kg(-1).min(-1)），并用第4-9分钟的平均值代表每次活动的耗氧量。为了计算 MET，将活动耗氧量除以 3.5 ml.kg(-1).min(-1) (1 MET)。使用 Actigraph 模型 7164 逐秒收集加速度计数据。为了进行分析，我们使用计数分布（一分钟逐秒计数的第 10、25、50、75 和 90 个百分位数）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。为了检查模型性能，我们使用了留一法交叉验证技术。 MET 的均方根误差的 ANN 预测为 1.22 MET（置信区间：1.14-1.30）。对于活动类型的预测，人工神经网络在 88.8% 的时间内正确分类活动类型（置信区间：86.4-91.2%）。活动类型为低水平活动、运动、剧烈运动和家庭活动/其他活动。这种应用 ANN 处理 Actigraph 加速度计数据的新方法很有前景，并表明我们可以使用 ANN 分析程序成功估计活动 MET 并识别活动类型。
Staudenmayer J, Pober D, Crouter S, Bassett D, Freedson P. An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. J Appl Physiol 107: 1300-1307, 2009. First published July 30, 2009; doi:10.1152/japplphysiol.00465.2009.-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.kg(-1).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.kg(-1).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.