Mining Gait Pattern for Clinical Locomotion Diagnosis Based on Clustering Techniques

Abstract

Abstract. Scientific gait (walking) analysis provides valuable information about an individual's locomotion function, in turn, to assist clinical diagnosis and prevention, such as assessing treatment for patients with impaired postural control and detecting risk of falls in elderly population. While several artificial intelligence (AI) paradigms are addressed for gait analysis, they usually utilize supervised techniques where subject groups are defined a priori. In this paper, we explore to investigate gait pattern mining with clustering-based approaches, in which k-means and hierarchical clustering algorithms are employed to derive gait pattern. After feature selection and data preparation, we conduct clustering on the constructed gait data model to build up pattern-based clusters. The centroids of clusters are then treated as the subject profiles to model the various kinds of gait pattern, e.g. normal or pathological. Experiments are undertaken to visualize the derived subject clusters, evaluate the quality of clustering paradigm in terms of silhouette and mean square error and compare the results with the discovery derived from hierarchy tree analysis. In addition, analysis conducted on test data demonstrates the usability of the proposed paradigm in clinical applications.

Identification of Knee Frontal Plane Kinematic Patterns in Normal Gait by Principal Component Analysis

“…15 Hierarchical c-means clustering algorithms were employed to derive gait patterns using temporalÀ distance parameters (stride length and step frequency/cadence). 17 Common clustering was used to classify spatiotemporal and kinematic data of patients following a stroke. 18 A c-means clustering method 19,20 and hierarchical clustering 16 have been applied on kinematic data to identify gait pattern deviations in children with cerebral palsy.…”

Inter-Individual Variability in Postural Control During External Center of Mass Stabilization

“…They were used to investigate variability in complex movements, such as walking and running ( Mulroy et al, 2003 ; Bartlett et al, 2014 ). Moreover, hierarchical clustering algorithms have been used for mining gait patterns based on stride length and step frequency ( Xu et al, 2006 ) and to investigate universal and individual characteristics of postural sway during quiet standing ( Yamamoto et al, 2015 ). Multivariate clustering techniques were used for discovering human balance patterns and finding the association between COP parameters and different demographic and health characteristics of the participants ( Malik and Lai, 2017 ).…”

Relevant Elderly Gait Features for Functional Fitness Level Grouping

“…Even though most of the gait pattern recognition investigation has been focused on supervised learning (Chau, 2001a) and (Chau, 2001b), some papers have reported the use of unsupervised learning techniques to investigate several gait characteristics. In (Xu et al, 2006), the authors tried to find underlying gait patterns among pathological and healthy gaits by applying k-means and hierarchical clustering algorithms (Jain and Dubes, 1988) to a series of features previously extracted. Cluster evaluation was done in terms of silhouette and mean square error (Halkidi et al, 2002).…”