Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (elektronisch) | 9781665497947 |
| ISBN (Print) | 978-1-6654-9795-4 |
| Publikationsstatus | Veröffentlicht - 2022 |
| Veranstaltung | 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022 - Lisbon, Portugal Dauer: 13 Juli 2022 → 15 Juli 2022 |
Publikationsreihe
| Name | International Conference on Control, Automation and Diagnosis |
|---|---|
| ISSN (Print) | 2767-987X |
| ISSN (elektronisch) | 2767-9896 |
Abstract
Artificial neural networks (ANNs) have achieved many successes in time series forecasting. The shortcomings of them are a fixed forecast horizon and an increasing inaccuracy for multi-step forecast techniques to extend the forecast horizon. We embed temporal resolution warping into an ANN to provide a dynamic forecast horizon, excluding multi-step forecasts. The ANN is improved to recognize different representations of patterns by mapping spacial frequencies to new frequencies according to their relevance in time. We demonstrate the drastically improvement in forecast accuracy on different datasets. In comparison to the multi-step approach, we achieve a constant accuracy for extending the forecast horizon.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
- Ingenieurwesen (insg.)
- Maschinenbau
- Ingenieurwesen (insg.)
- Sicherheit, Risiko, Zuverlässigkeit und Qualität
- Mathematik (insg.)
- Steuerung und Optimierung
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Angewandte Informatik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022. Institute of Electrical and Electronics Engineers Inc., 2022. ( International Conference on Control, Automation and Diagnosis).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Prediction of variable forecast horizons with artificial neural networks by embedding the temporal resolution warping
AU - Kellermann, Christoph
AU - Neumann, Eric
AU - Ostermann, Joern
N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the Federal Ministry for Economic Affairs and Climate Action (BMWK), Germany, within the framework of the IIP-Ecosphere project.
PY - 2022
Y1 - 2022
N2 - Artificial neural networks (ANNs) have achieved many successes in time series forecasting. The shortcomings of them are a fixed forecast horizon and an increasing inaccuracy for multi-step forecast techniques to extend the forecast horizon. We embed temporal resolution warping into an ANN to provide a dynamic forecast horizon, excluding multi-step forecasts. The ANN is improved to recognize different representations of patterns by mapping spacial frequencies to new frequencies according to their relevance in time. We demonstrate the drastically improvement in forecast accuracy on different datasets. In comparison to the multi-step approach, we achieve a constant accuracy for extending the forecast horizon.
AB - Artificial neural networks (ANNs) have achieved many successes in time series forecasting. The shortcomings of them are a fixed forecast horizon and an increasing inaccuracy for multi-step forecast techniques to extend the forecast horizon. We embed temporal resolution warping into an ANN to provide a dynamic forecast horizon, excluding multi-step forecasts. The ANN is improved to recognize different representations of patterns by mapping spacial frequencies to new frequencies according to their relevance in time. We demonstrate the drastically improvement in forecast accuracy on different datasets. In comparison to the multi-step approach, we achieve a constant accuracy for extending the forecast horizon.
KW - dynamic horizon forecast
KW - multi-horizon forecasting
KW - time series forecasting
UR - http://www.scopus.com/inward/record.url?scp=85137774690&partnerID=8YFLogxK
U2 - 10.1109/ICCAD55197.2022.9853884
DO - 10.1109/ICCAD55197.2022.9853884
M3 - Conference contribution
AN - SCOPUS:85137774690
SN - 978-1-6654-9795-4
T3 - International Conference on Control, Automation and Diagnosis
BT - 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022
Y2 - 13 July 2022 through 15 July 2022
ER -