Feature selection for wearable smartphone-based human activity recognition with able bodied, elderly, and stroke patients.
Feature selection for wearable smartphone-based human activity recognition with able bodied, elderly, and stroke patients.
复制标题
DOI：
10.1371/journal.pone.0124414
复制
发表时间：
2015
期刊：
影响因子：
3.7
通讯作者：
Baddour N
中科院分区：
文献类型：
--
作者：
Capela NA;Lemaire ED;Baddour N
使用可穿戴传感器的人类活动识别（HAR）是一个不断增长的领域，有可能为康复专家提供有关患者移动性的有价值信息。带有加速度计和陀螺仪传感器的智能手机是一种方便、微创和低成本的移动监测方法。HAR系统通常预处理原始信号，分割信号，然后提取要在分类器中使用的特征。特征选择是减少潜在的大数据维度并提供可行参数以实现活动分类的过程中的关键步骤。大多数HAR系统都是为单个研究小组定制的，包括唯一的数据集、类、算法和信号特征。这些数据集主要来自身体健全的参与者。在本文中，智能手机加速度计和陀螺仪传感器数据是从可以从人类活动识别中受益的人群中收集的：健全人，老年人和中风患者。从连续序列的41个流动性任务（18个不同的任务）的数据收集共44名参与者。计算了76个信号特征，并使用三种基于滤波器、独立于分类器的特征选择方法（Relief-F、基于相关性的特征选择、基于快速相关性的滤波器）选择这些特征的子集。然后使用三种通用分类器（朴素贝叶斯，支持向量机，j 48决策树）对特征子集进行评估。所有三个人群的共同特征都被确定，尽管中风人群亚组与健全人群和老年人群有一些差异。与三个分类器的评价表明，功能子集产生类似或更好的精度比整个功能集的分类。因此，由于这些特征子集是独立于分类器的，因此它们对于开发和改进跨人群和人群内的HAR系统应该是有用的。
Human activity recognition (HAR), using wearable sensors, is a growing area with the potential to provide valuable information on patient mobility to rehabilitation specialists. Smartphones with accelerometer and gyroscope sensors are a convenient, minimally invasive, and low cost approach for mobility monitoring. HAR systems typically pre-process raw signals, segment the signals, and then extract features to be used in a classifier. Feature selection is a crucial step in the process to reduce potentially large data dimensionality and provide viable parameters to enable activity classification. Most HAR systems are customized to an individual research group, including a unique data set, classes, algorithms, and signal features. These data sets are obtained predominantly from able-bodied participants. In this paper, smartphone accelerometer and gyroscope sensor data were collected from populations that can benefit from human activity recognition: able-bodied, elderly, and stroke patients. Data from a consecutive sequence of 41 mobility tasks (18 different tasks) were collected for a total of 44 participants. Seventy-six signal features were calculated and subsets of these features were selected using three filter-based, classifier-independent, feature selection methods (Relief-F, Correlation-based Feature Selection, Fast Correlation Based Filter). The feature subsets were then evaluated using three generic classifiers (Naïve Bayes, Support Vector Machine, j48 Decision Tree). Common features were identified for all three populations, although the stroke population subset had some differences from both able-bodied and elderly sets. Evaluation with the three classifiers showed that the feature subsets produced similar or better accuracies than classification with the entire feature set. Therefore, since these feature subsets are classifier-independent, they should be useful for developing and improving HAR systems across and within populations.
登录
查看更多内容
影响因子：
3.2
作者：
Del Rosario, Michael B.;Wang, Kejia;Redmond, Stephen J.
通讯作者：
Redmond, Stephen J.
影响因子：
9.9
作者：
Barra, J.;Oujamaa, L.;Perennou, D.
通讯作者：
Perennou, D.
影响因子：
2.3
作者：
Khan, Adil Mehmood;Tufail, Ali;Laine, Teemu H.
通讯作者：
Laine, Teemu H.
影响因子：
2.2
作者：
Fulk GD;Sazonov E
通讯作者：
Sazonov E
影响因子：
6.7
作者：
Dijkstra, Baukje;Kamsma, Yvo;Zijlstra, Wiebren
通讯作者：
Zijlstra, Wiebren