In this paper, we study the postural behaviour of two categories of people: Post-CVA subjects suffering from cerebrovascular accident syndromes and healthy individuals under several levels of anterior–posterior and medial–lateral sinusoidal disturbances (0.1–0.5 Hz). These perturbations were produced from an omnidirectional platform called Isiskate. Afterwards, we have quantified seventy postural parameters, they were combined of linear stabilometric parameters and non-linear time dependent stochastic parameters using stabilogram diffusion analysis and some spectral attributes using power spectral density. The aim of our analysis is to reduce data dimensionality using principal component analysis (PCA). Furthermore, we proposed a new PCA-related criterion named: criterion of contribution in order to evaluate the contribution of every variable in the resulted system structure, and thus to eliminate the redundant postural characteristics. Afterwards, we highlighted some interesting distinctive parameters. The selected parameters were used thereafter in comparison between the studied groups. Finally, we created a classification model using support vector machines to distinguish stroke patients. Our proposed techniques help in understanding the human postural dynamics and facilitate the diagnosis of pathologies related to equilibrium which can be used to improve the rehabilitation services.

In this paper, different techniques of analysis have been used to study the effects of perturbations generated from a robotic mobile platform called Isiskate. These disturbances were applied on two categories of people: post-CVA subjects suffering from cerebrovascular accident and healthy individuals. Our aim is to analyze some assessment tools to distinguish between different postural behaviors. In relevant works, very few studies have addressed the use of nonlinear time-series methods in diagnosis of post-CVA pathological postural behavior. Furthermore, our tools are based on parametric and non-parametric identification procedures, that can yield to an insight on how to improve the examination time. As part of our analysis, the tests were established with several levels of sinusoidal vibrations, along the anterior–posterior (A/P) and medial–lateral (M/L) planes. The mobile platform allowed us to record a set of coordinates that includes center of pressure (COP) as a function of time. First, we have quantified some linear parameters and spectral characteristics using power spectral density (PSD). Thereafter, we have deduced stochastic parameters using stabilogram diffusion analysis (SDA), which revealed some interesting invariants. Then transfer functions between the platform velocity and COP trajectory were evaluated. They were carried out at frequencies from 0.1 Hz to 3.3 Hz. Furthermore, we accomplished a comparison of models based on both parametric and nonparametric identification methods. The combination of the proposed techniques has provided us an understanding of human control process by establishing a behavior model and helped us to distinguish patients with postural disorders. This improves postural analysis and facilitates the diagnosis of pathologies related to equilibrium which serves in rehabilitation.