Principal component analysis and functional regression are combined in a model to analyze a time series of pressure maps. The model is tested measuring the pressures over a chair seat while a subject performs a combination of simple movements. A sampling rate of 3 Hz is adequate for applying the model in sitting postures. The model is able to detect patterns of movement over time, although more variables are necessary if the movements produce similar pressure distributions.
Juan C. Chicote, Juan V. Durá, Juan M. Belda, and Rakel Poveda
Helios De Rosario, Juan Manuel Belda-Lois, Francisco Fos, Enrique Medina, Rakel Poveda-Puente, and Michael Kroll
The new generation of videogame interfaces such as Microsoft’s Kinect opens the possibility of implementing exercise programs for physical training, and of evaluating and reducing the risks of elderly people falling. However, applications such as these might require measurements of joint kinematics that are more robust and accurate than the standard output given by the available middleware. This article presents a method based on particle filters for calculating joint angles from the positions of the anatomical points detected by PrimeSense’s NITE software. The application of this method to the measurement of lower limb kinematics reduced the error by one order of magnitude, to less than 10°, except for hip axial rotation, and it was advantageous over inverse kinematic analysis, in ensuring a robust and smooth solution without singularities, when the limbs are out-stretched and anatomical landmarks are aligned.
Juan V. Durá, Juan M. Belda, Rakel Poveda, Álvaro Page, José Laparra, José Das, Jaime Prat, and Ana C. García
The effect of walking velocity on force platform measures is examined by means of functional regression and nonfunctional regression analyses. The two techniques are compared using a data set of ground reaction forces. Functional data analysis avoids the need to identify significant points, and provides more information along the waveform.