Explainable AI for sensor-based sorting systems
- 22 September 2022
- journal article
- research article
- Published by Walter de Gruyter GmbH in TM - Technisches Messen
- Vol. 90 (3) , 154-166
Abstract
Explainable artificial intelligence (XAI) can make machine learning based systems more transparent. This additional transparency can enable the use of machine learning in many different domains. In our work, we show how XAI methods can be applied to an autoencoder for anomaly detection in a sensor-based sorting system. The setup of the sorting system consists of a vibrating feeder, a conveyor belt, a line-scan camera and an array of fast-switching pneumatic valves. It allows the separation of a material stream into two fractions, realizing a binary sorting task. The autoencoder tries to mimic the normal behavior of the nozzle array and thus can detect abnormal behavior. The XAI methods are used to explain the output of the autoencoder. As XAI methods global and local approaches are used, which means we receive explanations for both a single result and the whole autoencoder. Initial results for both approaches are shown, together with possible interpretations of these results.Keywords
This publication has 25 references indexed in Scilit:
- iml: An R package for Interpretable Machine LearningJournal of Open Source Software, 2018
- Autoencoder-based network anomaly detection2018
- Neural Networks and Deep Learning2018
- An overview of the supervised machine learning methodsHORIZONS.B, 2017
- "Why Should I Trust You?"2016
- Euclidean Distance Matrices: Essential theory, algorithms, and applicationsIEEE Signal Processing Magazine, 2015
- Anomaly Detection with Score Functions Based on the Reconstruction Error of the Kernel PCA2014
- Machine Learning Techniques for Anomaly Detection: An OverviewInternational Journal of Computer Applications, 2013
- Anomaly detectionACM Computing Surveys, 2009
- 17. A Value for n-Person Games1953