Complex feature analysis of center of pressure signal for age-related subject classification

Materials and Methods: The elderly individuals’ behavior during standing and how demanding such a task is for them, is still unknown. We  recorded the center of pressure (COP) position of   12 elder and 15 young participants while they were standing for 30 seconds. Then an analysis  was performed to find the most appropriate and discriminative features for the elderly and young posture signals discrimination. Features were selected in frequency and time domain. Largest Lyapunov exponents of the COP signals were also computed to show the impact of chaotic behavior in static balance characterization relative to age.

Results: Working in frequency domain is preferred to time domain analysis and largest Lyapunov exponent of the posture signal can be representatively used for COP signal discrimination between the two classes of   subjects.

Conclusion: In investigation and analysis of static balance for elders and unhealthy participants the signal of COP can be studied in chaotic domain beside frequency domain. Extraction of features from both chaotic and frequency domains significantly improves the discrimination rate of balance signals in age-related    classes.