Datum
2023-12-30Schlagwort
004 Informatik Maschinelles LernenNeuronales NetzDatenReflexionsspektroskopieDatenverarbeitungSupplement
doi:10.48662/daks-40Metadata
Zur Langanzeige
Aufsatz
Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features
Zusammenfassung
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 if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, 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 directly without additional preprocessing or augmentation 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 a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI.
Zitierform
In: International Journal on Advances in Intelligent Systems Vol. 16 / Nr. 3&4 (2023-12-30) , S. 43-50 ; eissn:1942-2679Zusätzliche Informationen
Artikel auch zu finden unter: https://www.iariajournals.org/intelligent_systems/Zitieren
@article{doi:10.17170/kobra-2024042910096,
author={Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard},
title={Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features},
journal={International Journal on Advances in Intelligent Systems},
year={2023}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2023$n2023 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/15738 3000 Magnussen, Birk Martin 3010 Stern, Claudius 3010 Sick, Bernhard 4000 Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features / Magnussen, Birk Martin 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/15738=x R 4204 \$dAufsatz 4170 5550 {{Maschinelles Lernen}} 5550 {{Neuronales Netz}} 5550 {{Daten}} 5550 {{Reflexionsspektroskopie}} 5550 {{Datenverarbeitung}} 7136 ##0##http://hdl.handle.net/123456789/15738
2024-04-30T15:05:59Z 2024-04-30T15:05:59Z 2023-12-30 doi:10.17170/kobra-2024042910096 http://hdl.handle.net/123456789/15738 Artikel auch zu finden unter: https://www.iariajournals.org/intelligent_systems/ eng Urheberrechtlich geschützt https://rightsstatements.org/page/InC/1.0/ machine learning neural nets continuous kernel irregularly sampled data reflection spectroscopy 004 Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features Aufsatz 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 if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, 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 directly without additional preprocessing or augmentation 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 a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI. open access Magnussen, Birk Martin Stern, Claudius Sick, Bernhard doi:10.48662/daks-40 Maschinelles Lernen Neuronales Netz Daten Reflexionsspektroskopie Datenverarbeitung publishedVersion eissn:1942-2679 Nr. 3&4 International Journal on Advances in Intelligent Systems 43-50 Vol. 16 false
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden:
:Urheberrechtlich geschützt