Home // ICAS 2023, The Nineteenth International Conference on Autonomic and Autonomous Systems // View article
Authors:
Birk Martin Magnussen
Claudius Stern
Bernhard Sick
Keywords: machine learning; neural nets; continuous kernel; irregularly sampled data; reflection spectroscopy
Abstract:
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces a novel method utilizing continuous kernels for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data natively without additional preprocessing as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with individual failed components without the need for retraining.
Pages: 49 to 53
Copyright: Copyright (c) IARIA, 2023
Publication date: March 13, 2023
Published in: conference
ISSN: 2308-3913
ISBN: 978-1-68558-053-7
Location: Barcelona, Spain
Dates: from March 13, 2023 to March 17, 2023