Reliability of 3D Depth Motion Sensors for Capturing Upper Body Motions and Assessing the Quality of Wheelchair Transfers.
Reliability of 3D Depth Motion Sensors for Capturing Upper Body Motions and Assessing the Quality of Wheelchair Transfers.
复制标题
DOI：
10.3390/s22134977
复制
发表时间：
2022-06-30
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
轮椅使用者在进行坐立-枢轴-转移（SPT）时必须使用适当的技术，以防止上肢疼痛和不适。目前分析SPT质量的方法包括TransKinect（机器学习（ML）模型的组合）和迁移评估工具（TAI），使用Microsoft Kinect V2自动对迁移质量进行评分。随着V2的停产，有必要确定其他商业传感器的兼容性。英特尔实感D435和微软Kinect Azure与V2进行了传感器间和传感器内可靠性的比较。还使用Azure进行了二次分析，以分析其使用用于预测传输质量的现有ML模型的性能。Azure和V2（n = 7; ICC = 0.63至0.92）的传感器内和传感器间可靠性高于RealSense和V2（n = 30; ICC = 0.13至0.7）。此外，V2和Azure都在ML结果上表现出高度一致性，但不是针对地面事实。因此，ML模型可能需要使用Azure进行重新训练，因为与V2相比，它被发现是一种更可靠和更强大的传感器，用于跟踪轮椅转移。
Wheelchair users must use proper technique when performing sitting-pivot-transfers (SPTs) to prevent upper extremity pain and discomfort. Current methods to analyze the quality of SPTs include the TransKinect, a combination of machine learning (ML) models, and the Transfer Assessment Instrument (TAI), to automatically score the quality of a transfer using Microsoft Kinect V2. With the discontinuation of the V2, there is a necessity to determine the compatibility of other commercial sensors. The Intel RealSense D435 and the Microsoft Kinect Azure were compared against the V2 for inter- and intra-sensor reliability. A secondary analysis with the Azure was also performed to analyze its performance with the existing ML models used to predict transfer quality. The intra- and inter-sensor reliability was higher for the Azure and V2 (n = 7; ICC = 0.63 to 0.92) than the RealSense and V2 (n = 30; ICC = 0.13 to 0.7) for four key features. Additionally, the V2 and the Azure both showed high agreement with each other on the ML outcomes but not against a ground truth. Therefore, the ML models may need to be retrained ideally with the Azure, as it was found to be a more reliable and robust sensor for tracking wheelchair transfers in comparison to the V2.
登录
查看更多内容
影响因子：
3
作者：
Ozsoy, Umut;Yildirim, Yilmaz;Suzen, Lutfiye Bikem
通讯作者：
Suzen, Lutfiye Bikem
DOI：
10.1007/s11227-021-04076-w
发表时间：
2022
期刊：
The Journal of supercomputing
影响因子：
--
作者：
Long C;Jo E;Nam Y
通讯作者：
Nam Y
DOI：
10.1179/1079026813z.000000000148
发表时间：
2013-03-01
期刊：
The journal of spinal cord medicine
影响因子：
--
作者：
通讯作者：
--
DOI：
10.1016/j.apmr.2016.03.026
发表时间：
2016-10-01
影响因子：
4.3
作者：
Hogaboom, Nathan S.;Worobey, Lynn A.;Boninger, Michael. L.
通讯作者：
Boninger, Michael. L.
影响因子：
2.4
作者：
Jimenez-Grande, David;Atashzar, S. Farokh;Falla, Deborah
通讯作者：
Falla, Deborah