Reactive Hand Movements from Arm Kinematics and EMG Signals Based on Hierarchical Gaussian Process Dynamical Models

Author(s):  
Nick Taubert ◽  
Jesse St. Amand ◽  
Prerana Kumar ◽  
Leonardo Gizzi ◽  
Martin A. Giese
Author(s):  
Nobuhiko Yamaguchi ◽  

Gaussian Process Dynamical Models (GPDMs) constitute a nonlinear dimensionality reduction technique that provides a probabilistic representation of time series data in terms of Gaussian process priors. In this paper, we report a method based on GPDMs to visualize the states of time-series data. Conventional GPDMs are unsupervised, and therefore, even when the labels of data are available, it is not possible to use this information. To overcome the problem, we propose a supervised GPDM (S-GPDM) that utilizes both the data and their corresponding labels. We demonstrate experimentally that the S-GPDM can locate related motion data closer together than conventional GPDMs.


Author(s):  
Muriel Lang ◽  
Martin Kleinsteuber ◽  
Oliver Dunkley ◽  
Sandra Hirche

2019 ◽  
Vol 20 (5) ◽  
pp. 1803-1814 ◽  
Author(s):  
Raul Quintero Minguez ◽  
Ignacio Parra Alonso ◽  
David Fernandez-Llorca ◽  
Miguel Angel Sotelo

Sign in / Sign up

Export Citation Format

Share Document