Details
| Original language | English |
|---|---|
| Title of host publication | 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (electronic) | 9781665497947 |
| ISBN (print) | 978-1-6654-9795-4 |
| Publication status | Published - 2022 |
| Event | 2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022 - Lisbon, Portugal Duration: 13 Jul 2022 → 15 Jul 2022 |
Publication series
| Name | International Conference on Control, Automation and Diagnosis |
|---|---|
| ISSN (Print) | 2767-987X |
| ISSN (electronic) | 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.
Keywords
- dynamic horizon forecast, multi-horizon forecasting, time series forecasting
ASJC Scopus subject areas
- Engineering(all)
- Electrical and Electronic Engineering
- Engineering(all)
- Mechanical Engineering
- Engineering(all)
- Safety, Risk, Reliability and Quality
- Mathematics(all)
- Control and Optimization
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Science Applications
Cite this
- 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).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › 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 -