no code implementations • 11 May 2023 • Philipp Sepin, Jana Kemnitz, Safoura Rezapour Lakani, Daniel Schall
In this work, we present an extensive comparison of the clustering algorithms K-means clustering, OPTICS, and Gaussian mixture model clustering (GMM) applied to statistical features extracted from the time and frequency domains of vibration data sets.
no code implementations • 21 Apr 2023 • Viktorija Pruckovskaja, Axel Weissenfeld, Clemens Heistracher, Anita Graser, Julia Kafka, Peter Leputsch, Daniel Schall, Jana Kemnitz
Data-driven machine learning is playing a crucial role in the advancements of Industry 4. 0, specifically in enhancing predictive maintenance and quality inspection.
no code implementations • 14 Oct 2022 • Stephanie Holly, Robin Heel, Denis Katic, Leopold Schoeffl, Andreas Stiftinger, Peter Holzner, Thomas Kaufmann, Bernhard Haslhofer, Daniel Schall, Clemens Heitzinger, Jana Kemnitz
In this work, we present an autoencoder based end-to-end workflow for anomaly detection suitable for multivariate time series data in large industrial cooling systems, including explained fault localization and root cause analysis based on expert knowledge.
no code implementations • 23 Sep 2022 • Clemens Heistracher, Stefan Stricker, Pedro Casas, Daniel Schall, Jana Kemnitz
We propose a new sampling strategy, called smart active sapling, for quality inspections outside the production line.
no code implementations • 15 Oct 2021 • Stephanie Holly, Thomas Hiessl, Safoura Rezapour Lakani, Daniel Schall, Clemens Heitzinger, Jana Kemnitz
In this work, we investigated the impact of different hyperparameter optimization approaches in an FL system.
no code implementations • 8 Oct 2021 • Clemens Heistracher, Anahid Jalali, Axel Suendermann, Sebastian Meixner, Daniel Schall, Bernhard Haslhofer, Jana Kemnitz
The increasing deployment of low-cost IoT sensor platforms in industry boosts the demand for anomaly detection solutions that fulfill two key requirements: minimal configuration effort and easy transferability across equipment.
no code implementations • 7 Oct 2021 • Jana Kemnitz, Thomas Bierweiler, Herbert Grieb, Stefan von Dosky, Daniel Schall
Further, we investigate the model performance on different pumps from the same type compared to those from the training data.
no code implementations • 14 May 2020 • Thomas Hiessl, Daniel Schall, Jana Kemnitz, Stefan Schulte
Federated Learning (FL) is a very promising approach for improving decentralized Machine Learning (ML) models by exchanging knowledge between participating clients without revealing private data.
no code implementations • 24 Jul 2018 • Jana Kemnitz, Christian F. Baumgartner, Wolfgang Wirth, Felix Eckstein, Sebastian K. Eder, Ender Konukoglu
In this work we propose a cost function which allows integration of multiple datasets with heterogeneous label subsets into a joint training.