Progression‐Preserving Dimension Reduction for High‐Dimensional Sensor Data Visualization
Hyun-Jin Yoon, Cyrus Shahabi, Carolee Joyce Winstein, Jong‐Hyun Jang · ETRI Journal · 2013
This letter presents Progression-Preserving Projection, a dimension reduction technique that finds a linear projection that maps a high-dimensional sensor dataset into a two- or three-dimensional subspace with a particularly useful property for visual exploration. As a demonstration of its effectiveness as a visual exploration and diagnostic means, we empirically evaluate the proposed technique over a dataset acquired from our own virtual-reality-enhanced ball-intercepting training system designed to promote the upper extremity movement skills of individuals recovering from stroke-related hemiparesis.