3D visualization of temporal data: exploring Visual Attention and Machine Learning

Temporal data visualization supports planning and decision-making processes as it helps understanding patterns and relationships among time-based data. In many fields of study, users deal with a large volume of valuable information, which is usually analyzed based on temporal aspects. In this scenario, the use of three-dimensional space opens interesting opportunities in time representation, interpretation, and exploration of temporal data. Approaches based on Virtual Reality (VR) techniques are still underexplored to visualize temporal data, most of the times as an extension of the bi-dimensional space, although they can provide more natural interaction in real time. Visual Attention (VA) has grown in relevance in many study areas due to its ability to help humans explore a complex visual scene. Contributing to overcome the limited use of three-dimensional (3D) space in temporal data visualization, in this article, we present a VR approach named 3D Block(ARL) to support interactive visualization of temporal data. The environment is built based on VA concepts. Our approach uses a rule-based Machine Learning method, generating new ways to visualize temporal information in 3D environments. The results of two controlled experiments with volunteers shows that the visualizations generated by our approach had a good acceptance and were able to decrease the mistake rate while performing a specific task when compared to a traditional approach.