Comparative evaluation of features and techniques for identifying activity type and estimating energy cost from accelerometer data.
Comparative evaluation of features and techniques for identifying activity type and estimating energy cost from accelerometer data.
复制标题
对识别活性类型和加速度计估计能量成本的特征和技术的比较评估。
DOI：
10.1088/0967-3334/37/3/360
复制
发表时间：
2016-03
影响因子：
3.2
通讯作者：
Strath SJ
中科院分区：
文献类型：
--
作者：
Kate RJ;Swartz AM;Welch WA;Strath SJ
可穿戴加速度计可用于客观地评估身体活动。然而，这种评估的准确性取决于用来处理从加速度计获得的时间序列数据的基本方法。已经提出了几种方法，使用这些数据来识别身体活动的类型并估计其能量成本。大多数较新的方法采用一些机器学习技术沿着适当的功能来表示时间序列数据。本文实验比较了几个这些技术和功能的146名受试者做八个不同的身体活动戴在臀部加速度计的大数据集。除了基于统计的特征之外，还评估了基于距离的特征和直接来自时间序列的简单离散特征。在体力活动类型识别任务上，结果表明，使用更多的特征显着提高结果。机器学习技术的选择也很重要。然而，在能源成本估计任务中，特征选择和机器学习技术的影响较小。在这项任务中，专门为每种类型的体力活动训练的单独的能量成本估计模型被发现比为所有类型的体力活动训练的单个模型更准确。
Wearable accelerometers can be used to objectively assess physical activity. However, the accuracy of this assessment depends on the underlying method used to process the time series data obtained from accelerometers. Several methods have been proposed that use this data to identify the type of physical activity and estimate its energy cost. Most of the newer methods employ some machine learning technique along with suitable features to represent the time series data. This paper experimentally compares several of these techniques and features on a large dataset of 146 subjects doing eight different physical activities wearing an accelerometer on the hip. Besides features based on statistics, distance based features and simple discrete features straight from the time series were also evaluated. On the physical activity type identification task, the results show that using more features significantly improve results. Choice of machine learning technique was also found to be important. However, on the energy cost estimation task, choice of features and machine learning technique were found to be less influential. On that task, separate energy cost estimation models trained specifically for each type of physical activity were found to be more accurate than a single model trained for all types of physical activities.
登录
查看更多内容
影响因子：
3.4
作者：
Lin, Jessica;Khade, Rohan;Li, Yuan
通讯作者：
Li, Yuan
影响因子：
3.3
作者：
Crouter, SE;Clowers, KG;Bassett, DR
通讯作者：
Bassett, DR
DOI：
10.1097/00005768-200009001-00002
发表时间：
2000-09-01
期刊：
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE
影响因子：
--
作者：
Hendelman, D;Miller, K;Freedson, P
通讯作者：
Freedson, P
DOI：
10.1109/titb.2007.899496
发表时间：
2008-01-01
影响因子：
--
作者：
Ermes, Miikka;Parkka, Juha;Korhonen, Ilkka
通讯作者：
Korhonen, Ilkka
影响因子：
4.8
作者：
Kate, Rohit J.
通讯作者：
Kate, Rohit J.