no code implementations • 27 Mar 2024 • Olov Holmer, Mattias Krysander, Erik Frisk
The results also show that randomly resampling the dataset on each epoch is an effective way to reduce the size of the training data.
no code implementations • 27 Mar 2024 • Olov Holmer, Erik Frisk, Mattias Krysander
In this paper, a family of neural network-based survival models is presented.
no code implementations • 27 Dec 2023 • Fatemeh Hashemniya, Arvind Balachandran, Erik Frisk, Mattias Krysander
The findings indicate that the default sensor setup is insufficient for achieving complete fault isolability.
no code implementations • 8 May 2023 • Arman Mohammadi, Theodor Westny, Daniel Jung, Mattias Krysander
Data-driven modeling and machine learning are widely used to model the behavior of dynamic systems.
no code implementations • 1 Feb 2023 • Olov Holmer, Erik Frisk, Mattias Krysander
Due to the complex behavior of system degradation, data-driven methods are often preferred, and neural network-based methods have been shown to perform particularly very well.
no code implementations • 30 Mar 2022 • Erik Jakobsson, Erik Frisk, Mattias Krysander, Robert Pettersson
In this work Time Series Classification techniques are investigated, and especially their applicability in applications where there are significant differences between the individuals where data is collected, and the individuals where the classification is evaluated.
no code implementations • 4 Sep 2020 • Narges Mohammadi Sarband, Ema Becirovic, Mattias Krysander, Erik G. Larsson, Oscar Gustafsson
The energy consumption is about 300 nJ/detection for the fast projected gradient algorithm using 256 iterations, leading to a convergence close to the theoretical.