Institute of Biomedical Engineering, University of Toronto, Toronto, ON M5S 3G9, Canada.
KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, ON M5G 2A2, Canada.
Sensors (Basel). 2022 Mar 18;22(6):2370. doi: 10.3390/s22062370.
Slip-resistant footwear can prevent fall-related injuries on icy surfaces. Winter footwear slip resistance can be measured by the Maximum Achievable Angle (MAA) test, which measures the steepest ice-covered incline that participants can walk up and down without experiencing a slip. However, the MAA test requires the use of a human observer to detect slips, which increases the variability of the test. The objective of this study was to develop and evaluate an automated slip detection algorithm for walking on level and inclined ice surfaces to be used with the MAA test to replace the need for human observers. Kinematic data were collected from nine healthy young adults walking up and down on ice surfaces in a range from 0° to 12° using an optical motion capture system. Our algorithm segmented these data into steps and extracted features as inputs to two linear support vector machine classifiers. The two classifiers were trained, optimized, and validated to classify toe slips and heel slips, respectively. A total of approximately 11,000 steps from 9 healthy participants were collected, which included approximately 4700 slips. Our algorithm was able to detect slips with an overall F score of 90.1%. In addition, the algorithm was able to accurately classify backward toe slips, forward toe slips, backward heel slips, and forward heel slips with F scores of 97.3%, 54.5%, 80.9%, and 86.5%, respectively.
防滑鞋可预防在冰面行走时的跌倒相关伤害。冬季鞋类防滑性能可通过最大可行角度 (MAA) 测试来测量，该测试测量参与者在不滑倒的情况下能够上下行走的最陡冰覆盖斜坡。然而，MAA 测试需要使用人工观察者来检测滑倒，这增加了测试的可变性。本研究的目的是开发和评估一种用于在水平和倾斜冰面行走的自动滑倒检测算法，以与 MAA 测试一起使用，从而取代对人工观察者的需求。运动学数据是从 9 名健康的年轻人在 0°到 12°的冰面上来回行走时使用光学运动捕捉系统收集的。我们的算法将这些数据分段为步骤，并提取特征作为两个线性支持向量机分类器的输入。这两个分类器经过训练、优化和验证，分别用于分类脚趾滑倒和脚跟滑倒。从 9 名健康参与者中总共收集了大约 11000 步，其中包括大约 4700 次滑倒。我们的算法能够以 90.1%的整体 F 分数检测到滑倒。此外，该算法还能够准确地分类向后脚趾滑倒、向前脚趾滑倒、向后脚跟滑倒和向前脚跟滑倒，F 分数分别为 97.3%、54.5%、80.9%和 86.5%。
