Discriminative functional analysis of human movements

This paper investigates the use of statistical dimensionality reduction (DR) techniques for discriminative low dimensional embedding to enable affective movement recognition. Human movements are defined by a collection of sequential observations (time-series features) representing body joint angle or joint Cartesian trajectories. In this work, these sequential observations are modelled as temporal functions using B-spline basis function expansion, and dimensionality reduction techniques are adapted to enable application to the functional observations. The DR techniques adapted here are: Fischer discriminant analysis (FDA), supervised principal component analysis (PCA), and Isomap. These functional DR techniques along with functional PCA are applied on affective human movement datasets and their performance is evaluated using leave-one-out cross validation with a one-nearest neighbour classifier in the corresponding low-dimensional subspaces. The results show that functional supervised PCA outperforms the other DR techniques examined in terms of classification accuracy and time resource requirements.

► Dimensionality reduction (DR) techniques are adapted for functional movement datasets. ► Affective Movements are represented by functional features using basis function expansion. ► Functional DR is used to obtain low-dimensional embeddings for the affective movements. ► Variants of functional DR are compared using leave-one-out cross validation and 1NN classifier. ► Functional supervised PCA with Gaussian kernels achieves the best classification performance.