Parallel coordinate plotting is an established data visualization technique that provides means for graphing and exploring multidimensional relational datasets on a two-dimensional display. Each vertical axis represents the range of values for one attribute, and each data tuple appears as a connected path traveling left-to-right across the plot, connecting attribute values for that tuple on the vertical axes. Parallel coordinate plots look like timedomain audio signal waveforms, and they can be translated into audio signals through straightforward mapping algorithms. This study looks at three data sonification algorithms, sonification being the mapping of data into sounds for perceptual exploration, similar to uses of data visualization. Sound-response survey results and subsequent analyses reveal that the most direct method for mapping parallel coordinates of data tuples to audio waveforms is the most accurate for generating sounds that listeners can use to classify data. Future work has begun on improving the accuracy of this audio waveform-based, timbral approach to classifying data.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Proceedings of the 31st Annual Spring Conference of the Pennsylvania Computer and Information Science Educators (PACISE) Kutztown University of PA, Kutztown, PA, April 1-2, 2016. This won the Best Faculty Paper award.