Visual Data Exploration for Balance Quantification During Exergaming

Abstract

Recently, digital games controlled by real-time body movements (exergames) have been proposed as an innovative method to improve balance among older adults. One of the main challenges for exergames is to automatically quantify balance during game-play to adapt the game difficulty according to the skills of the player. Here we perform a multidimensional exploratory data analysis, using visualization and force plate data, to establish suitable measures for quantifying balance in real-time. Our visualizations provide quick insight and directions for further data exploration. They suggest that speed, curvature, the root mean square of the mediolateral displacement of the center of pressure, and a turbulence measure are the most promising measures for balance quantification. The next step is to apply the present techniques to data of whole body movements as recorded by devices such as Kinect, that are available for gameplay at home.