Linear and Non-linear Dimensionality-Reduction Techniques on Full Hand Kinematics

• Main Authors: Alexandra A. Portnova-Fahreeva, Fabio Rizzoglio, Ilana Nisky, Maura Casadio, Ferdinando A. Mussa-Ivaldi, Eric Rombokas
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2020-05-01
• Series: Frontiers in Bioengineering and Biotechnology
• Subjects: kinematics; neural networks; principal component analysis; dimensionality reduction; unsupervised learning; prosthetics
• Online Access: https://www.frontiersin.org/article/10.3389/fbioe.2020.00429/full

The purpose of this study was to find a parsimonious representation of hand kinematics data that could facilitate prosthetic hand control. Principal Component Analysis (PCA) and a non-linear Autoencoder Network (nAEN) were compared in their effectiveness at capturing the essential characteristics of a wide spectrum of hand gestures and actions. Performance of the two methods was compared on (a) the ability to accurately reconstruct hand kinematic data from a latent manifold of reduced dimension, (b) variance distribution across latent dimensions, and (c) the separability of hand movements in compressed and reconstructed representations derived using a linear classifier. The nAEN exhibited higher performance than PCA in its ability to more accurately reconstruct hand kinematic data from a latent manifold of reduced dimension. Whereas, for two dimensions in the latent manifold, PCA was able to account for 78% of input data variance, nAEN accounted for 94%. In addition, the nAEN latent manifold was spanned by coordinates with more uniform share of signal variance compared to PCA. Lastly, the nAEN was able to produce a manifold of more separable movements than PCA, as different tasks, when reconstructed, were more distinguishable by a linear classifier, SoftMax regression. It is concluded that non-linear dimensionality reduction may offer a more effective platform than linear methods to control prosthetic hands.