Short description

Sonification translates complex data streams into sound [1], allowing operators to detect patterns or anomalies through auditory signals [2]. By complementing traditional visual data analysis, sonification can help operators detect anomalies more effectively and reduce their cognitive load. This innovative approach promises to enhance the detection of grid anomalies while reducing operator fatigue [3].

We have datasets available that describe the Austrian high voltage power grid with lots of parameters, e.g. power production, power line loss, frequency, price, …

The aim is to create an audio performance out of this data that gives an impression on what happens in the grid at a specific moment in time and becoming aware of any anomalies that might be happening in real time.

Your Tasks

• Literature research
• Implementation of sonification algorithms
• Compose audio performance
• Evaluation and Documentation

Your Profile/Prerequisites

• Motivation and interest in the topic
• Artistic mind
• Background in Signal Processing and Machine Learning
• Strong programming background, ideally in Python or Julia

Contact:

Martin Hagmüller (hagmueller@tugraz.at or 0316/873 4377) Franz Pernkopf (pernkopf@tugraz.at or 0316/873 4446)

References

[1] G. Dubus and R. Bresin, “A Systematic Review of Mapping Strategies for the Sonification of Physical Quantities,” PLoS ONE, vol. 8, no. 12, p. e82491, Dec. 2013, doi: 10.1371/journal.pone.0082491.

[2] P. Cowden and L. Dosiek, “Auditory Displays of Electric Power Grids.” Jun. 2018. doi: 10.21785/icad2018.013.

[3] S. Lenzi, G. Terenghi, D. Meacci, A. Moreno Fernandez-de-Leceta, and P. Ciuccarelli, “The design of Datascapes: toward a design framework for sonification for anomaly detection in AI-supported networked environments,” Frontiers in Computer Science, vol. 5, Jan. 2024, doi: 10.3389/fcomp.2023.1254678.