Significant Features for Human Activity Recognition Using Tri-Axial Accelerometers.
Significant Features for Human Activity Recognition Using Tri-Axial Accelerometers.
复制标题
DOI：
10.3390/s22197482
复制
发表时间：
2022-10-02
期刊：
影响因子：
--
通讯作者：
Nuseibeh B
中科院分区：
文献类型：
--
作者：
Bennasar M;Price BA;Gooch D;Bandara AK;Nuseibeh B
使用可穿戴传感器的活动识别对于各种应用来说已经变得必不可少。三轴加速度计是应用最广泛的活动识别传感器。尽管已经使用了各种特征来捕获模式并对加速度计信号进行分类以识别活动，但对于选择最佳特征还没有达成共识。减少特征数目可以降低计算成本和复杂度，提高分类器的性能。本文确定了对不同人类活动具有显著区分能力的信号特征。研究了传感器放置位置、采样频率和活动复杂度对所选特征的影响。从四个公开可用的数据集的加速度计信号中提取了193个信号特征的综合列表，其中包括以前从未用于活动识别的特征。使用联合互信息最大化(JMIM)方法来衡量特征重要性。确定了所有数据集的共同显著特征。结果表明，传感器放置位置不会显著影响识别性能，也不会影响显著的特征子集。结果还表明，在较高的采样频率下，与信号的重复性和规律性有关的特征具有较高的识别力。
Activity recognition using wearable sensors has become essential for a variety of applications. Tri-axial accelerometers are the most widely used sensor for activity recognition. Although various features have been used to capture patterns and classify the accelerometer signals to recognise activities, there is no consensus on the best features to choose. Reducing the number of features can reduce the computational cost and complexity and enhance the performance of the classifiers. This paper identifies the signal features that have significant discriminative power between different human activities. It also investigates the effect of sensor placement location, the sampling frequency, and activity complexity on the selected features. A comprehensive list of 193 signal features has been extracted from accelerometer signals of four publicly available datasets, including features that have never been used before for activity recognition. Feature significance was measured using the Joint Mutual Information Maximisation (JMIM) method. Common significant features among all the datasets were identified. The results show that the sensor placement location does not significantly affect recognition performance, nor does it affect the significant sub-set of features. The results also showed that with high sampling frequency, features related to signal repeatability and regularity show high discriminative power.
登录
查看更多内容
影响因子：
1
作者：
Glowinski, Sebastian;Ptak, Mariusz
通讯作者：
Ptak, Mariusz
DOI：
10.3390/s151229858
发表时间：
2015-12-11
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Attal F;Mohammed S;Dedabrishvili M;Chamroukhi F;Oukhellou L;Amirat Y
通讯作者：
Amirat Y
DOI：
10.3390/s140304239
发表时间：
2014-03-04
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Bersch SD;Azzi D;Khusainov R;Achumba IE;Ries J
通讯作者：
Ries J
DOI：
10.1007/978-3-540-24646-6_1
发表时间：
2004-01-01
期刊：
PERVASIVE COMPUTING, PROCEEDINGS
影响因子：
--
作者：
Bao, L;Intille, SS
通讯作者：
Intille, SS
影响因子：
3.7
作者：
Capela NA;Lemaire ED;Baddour N
通讯作者：
Baddour N