Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Visualizing Neural Network Decisions for Industrial Sound Analysis

: Grollmisch, Sascha; Johnson, David; Liebetrau, Judith

Fulltext ()

SMSI 2020 - Sensor and Measurement Science International : Proceedings, 22-25 June 2020, Nuremberg, Germany, SMSI 2020 is cancelled due to COVID-19
Wunstorf: AMA Service, 2020
ISBN: 978-3-9819376-2-6
ISBN: 978-3-9819376-3-3
ISBN: 3-9819376-3-5
Conference "Sensor and Measurement Science International" (SMSI) <2020, Nuremberg/cancelled>
Conference Paper, Electronic Publication
Fraunhofer IDMT ()

Recent research has shown acoustic quality control using audio signal processing and neural networks to be a viable solution for detecting product faults in noisy factory environments. For industrial partners, it is important to be able to explain the network’s decision making, however, there is limited research on this area in the field of industrial sound analysis (ISA). In this work, we visualize learned patterns of an existing network to gain insights about the decision making process. We show that unwanted biases can be discovered, and thus avoided, using this technique when validating acoustic quality control systems.