Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021 |
| Pages | 324-328 |
| Number of pages | 5 |
| ISBN (electronic) | 978-1-6654-1627-6 |
| Publication status | Published - 2021 |
Publication series
| Name | Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021 |
|---|
Abstract
In modern manufacturing environments huge amount of sensor data from machines have to be analyzed in the time domain. Applications for process control are to observe the stability, to predict behavior of mechanical components or to detect abnormal behavior of the manufacturing process. For that, time series forecasting is important to make manual or automated decisions. In this paper, we introduce a preprocess method which we call 'temporal resolution warping' (TRW). It is used for signal pre-And post-processing before and after applying the neural network. Thus, the computation complexity of the used network is reduced by compressing the time series in a certain way. We will show the computation reduction capability of our approach. For verification of our approach feed forward and convolution neural networks with residual layers are used to forecast reference time series of different applications. We will demonstrate that the training is speed up more than 26% with our pre-and post-processing technique.
Keywords
- multi-horizon forecasting, time series forecasting
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021. 2021. p. 324-328 (Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A New Preprocessing Approach to Reduce Computational Complexity for Time Series Forecasting with Neuronal Networks: Temporal Resolution Warping.
AU - Kellermann, Christoph
AU - Neumann, Eric
AU - Ostermann, Jörn
PY - 2021
Y1 - 2021
N2 - In modern manufacturing environments huge amount of sensor data from machines have to be analyzed in the time domain. Applications for process control are to observe the stability, to predict behavior of mechanical components or to detect abnormal behavior of the manufacturing process. For that, time series forecasting is important to make manual or automated decisions. In this paper, we introduce a preprocess method which we call 'temporal resolution warping' (TRW). It is used for signal pre-And post-processing before and after applying the neural network. Thus, the computation complexity of the used network is reduced by compressing the time series in a certain way. We will show the computation reduction capability of our approach. For verification of our approach feed forward and convolution neural networks with residual layers are used to forecast reference time series of different applications. We will demonstrate that the training is speed up more than 26% with our pre-and post-processing technique.
AB - In modern manufacturing environments huge amount of sensor data from machines have to be analyzed in the time domain. Applications for process control are to observe the stability, to predict behavior of mechanical components or to detect abnormal behavior of the manufacturing process. For that, time series forecasting is important to make manual or automated decisions. In this paper, we introduce a preprocess method which we call 'temporal resolution warping' (TRW). It is used for signal pre-And post-processing before and after applying the neural network. Thus, the computation complexity of the used network is reduced by compressing the time series in a certain way. We will show the computation reduction capability of our approach. For verification of our approach feed forward and convolution neural networks with residual layers are used to forecast reference time series of different applications. We will demonstrate that the training is speed up more than 26% with our pre-and post-processing technique.
KW - multi-horizon forecasting
KW - time series forecasting
UR - http://www.scopus.com/inward/record.url?scp=85124148774&partnerID=8YFLogxK
U2 - 10.1109/ISCSIC54682.2021.00065
DO - 10.1109/ISCSIC54682.2021.00065
M3 - Conference contribution
SN - 978-1-6654-1628-3
T3 - Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021
SP - 324
EP - 328
BT - Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021
ER -