Aziz Wajid, Hussain Lal, Khan Ishtiaq Rasool, Alowibdi Jalal S, Alkinani Monagi H
Department of Computer & AI, College of Computer Science and Engineering (CCSE), University of Jeddah, P.O. Box 80327, Jeddah 21589, Saudi Arabia.
Department of Computer Science & IT, University of Azad Jammu and Kashmir, King Abdullah Campus, Muzaffarabad 13100, Pakistan.
Math Biosci Eng. 2020 Dec 10;18(1):495-517. doi: 10.3934/mbe.2021027.
The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinct age populations. Classification of normal, slow and fast walking is fundamental for understanding the effects of gait speed on the gait patterns and for proper evaluation of alternations associated with it. In this study, we extracted multimodal features such as time domain and entropy-based complexity measures from stride interval signals of healthy subjects moving with normal, slow and fast speeds. The classification between different gait speeds was performed using machine learning classifiers such as classification and regression tree (CART), support vector machine linear (SVM-L), Naïve Bayes, neural network, and ensemble classifiers (random forest (RF), XG boost, averaged neural network (AVNET)). The performance was evaluated in term of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), p-value, area under the receiver operating characteristic curve (AUC). To distinguish the slow and normal gait walking, the highest performance was yielded in terms of accuracy (100%), p-value (0.004), and AUC (1.00) using RF, XGB-L followed by XGB-Tree with accuracy (88%), p-value (0.04) and AUC (1.00). To classify the fast and normal walking, the highest performance was obtained with accuracy (88%), p-value (0.04) using XGB-L, XGB-Tree and AVNET. The highest AUC (0.94) was obtained using NB. To discriminate the fast and slow gait walking, the highest performance was obtained using SVM-R, NNET, RF, AVNET with accuracy (88%), p-value (0.04) and AUC (0.94) using RF and AUC (0.96) using XGB-L.
步速会影响不同年龄人群的步态模式（生物力学和时空参数）。对正常、慢速和快速行走进行分类，对于理解步速对步态模式的影响以及正确评估与之相关的变化至关重要。在本研究中，我们从以正常、慢速和快速速度行走的健康受试者的步幅间隔信号中提取了多模态特征，如基于时域和熵的复杂度度量。使用机器学习分类器进行不同步态速度之间的分类，如分类与回归树（CART）、支持向量机线性核（SVM-L）、朴素贝叶斯、神经网络以及集成分类器（随机森林（RF）、极端梯度提升（XG boost）、平均神经网络（AVNET））。根据准确率、灵敏度、特异性、阳性预测值（PPV）、阴性预测值（NPV）、p值、受试者工作特征曲线下面积（AUC）来评估性能。为区分慢速和正常步态行走，使用随机森林（RF）、极端梯度提升线性核（XGB-L）时，在准确率（100%）、p值（0.004）和AUC（1.00）方面表现最佳，其次是极端梯度提升树（XGB-Tree），准确率为88%，p值为0.04，AUC为1.00。为对快速和正常行走进行分类，使用极端梯度提升线性核（XGB-L）、极端梯度提升树（XGB-Tree）和平均神经网络（AVNET）时，准确率最高为88%，p值为0.04。使用朴素贝叶斯获得最高的AUC（0.94）。为区分快速和慢速步态行走，使用支持向量机径向基核（SVM-R）、神经网络（NNET）、随机森林（RF）、平均神经网络（AVNET）时表现最佳，随机森林的准确率为88%，p值为0.04，AUC为0.94，极端梯度提升线性核的AUC为0.96。
