An artificial neural network model of energy expenditure using. nonintegrated acceleration signals
An artificial neural network model of energy expenditure using. nonintegrated acceleration signals
复制标题
DOI：
10.1152/japplphysiol.00429.2007
复制
发表时间：
2007-10-01
影响因子：
3.3
通讯作者：
Chen, Kong Y.
中科院分区：
文献类型：
--
作者：
Rothney, Megan P.;Neumann, Megan;Chen, Kong Y.
加速度计是一种很有前途的工具，用于表征自由生活中的身体活动模式。迄今为止，其广泛使用的主要限制是在估计能量消耗（EE）方面缺乏精度，这可能归因于过度简化的时间积分加速度信号和随后使用的线性回归模型用于EE估计。在这项研究中，我们收集了双轴原始（32 Hz）的加速度信号在髋关节之间的关系，并在102名健康成人使用EE数据收集了近24小时，在室内热量计作为参考标准。从每1分钟的加速度数据中，我们提取了10个我们认为有可能表征EE强度的信号特征（特征）。利用这些数据，我们开发了一个前馈/反向传播人工神经网络（ANN）模型与一个隐藏层（12 X 20 X I节点）。ANN的结果进行了比较，估计使用ActiGraph监视器，单轴加速度计，和IDEEA监视器，一个阵列的五个加速度计。在完成训练和验证（排除一个受试者）后，ANN显示出显著降低的平均绝对误差（0.29 +/- 0. 10 kcal/min）、均方误差（0.23 +/- 0.14 kcal（2）/min（2））和总EE差异（21 +/- 115 kcal/d），与IDEA（P < 0.01）和ActiGraph加速计回归模型（P < 0.001）相比。因此，人工神经网络与原始加速度信号相结合是一个很有前途的方法，身体加速度到EE的链接。需要进一步验证，以了解自由生活条件下不同的身体活动类型的模型的性能。
Accelerometers are a promising tool for characterizing physical activity patterns in free living. The major limitation in their widespread use to date has been a lack of precision in estimating energy expenditure (EE), which may be attributed to the oversimplified time-integrated acceleration signals and subsequent use of linear regression models for EE estimation. In this study, we collected biaxial raw (32 Hz) acceleration signals at the hip to develop a relationship between acceleration and minute-to-minute EE in 102 healthy adults using EE data collected for nearly 24 h in a room calorimeter as the reference standard. From each 1 min of acceleration data, we extracted 10 signal characteristics (features) that we felt had the potential to characterize EE intensity. Using these data, we developed a feed-forward/back-propagation artificial neural network (ANN) model with one hidden layer (12 X 20 X I nodes). Results of the ANN were compared with estimations using the ActiGraph monitor, a uniaxial accelerometer, and the IDEEA monitor, an array of five accelerometers. After training and validation (leave-one-subject out) were completed, the ANN showed significantly reduced mean absolute errors (0.29 +/- 0. 10 kcal/min), mean squared errors (0.23 +/- 0.14 kcal(2)/min(2)), and difference in total EE (21 +/- 115 kcal/day), compared with both the IDEEA (P < 0.01) and a regression model for the ActiGraph accelerometer (P < 0.001). Thus ANN combined with raw acceleration signals is a promising approach to link body accelerations to EE. Further validation is needed to understand the performance of the model for different physical activity types under free-living conditions.