Visualisation of Parallel Data Streams with Temporal Mosaics

Abstract

Despite its popularity and widespread use, timeline visualisation suffers from shortcomings which limit its use for displaying multiple data streams when the number of streams increases to more than a handful. This paper presents the TemporalMosaic technique for visualisation of parallel time-based streams which addresses some of these shortcomings. Temporal mosaics provide a compact way of representing parallel streams of events by allocating a fixed drawing area to time intervals and partitioning that area according to the number of concurrent events. A user study is presented which compares this technique to a standard timeline representation technique in which events are depicted as horizontal bars and multiple streams are drawn in parallel along a vertical axis. Results of this user study show that users of the temporal mosaic visualisation perform significantly better at detecting concurrency, interval overlaps and inactivity than users of standard timelines.