Recurrent neural networks and exponential PAA for virtual marine sensors

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Recurrent neural networks and exponential PAA for virtual marine sensors. / Oehmcke, Stefan; Zielinski, Oliver; Kramer, Oliver.

2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. s. 4459-4466 7966421.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Oehmcke, S, Zielinski, O & Kramer, O 2017, Recurrent neural networks and exponential PAA for virtual marine sensors. i 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings., 7966421, Institute of Electrical and Electronics Engineers Inc., s. 4459-4466, 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, USA, 14/05/2017. https://doi.org/10.1109/IJCNN.2017.7966421

APA

Oehmcke, S., Zielinski, O., & Kramer, O. (2017). Recurrent neural networks and exponential PAA for virtual marine sensors. I 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings (s. 4459-4466). [7966421] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2017.7966421

Vancouver

Oehmcke S, Zielinski O, Kramer O. Recurrent neural networks and exponential PAA for virtual marine sensors. I 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. s. 4459-4466. 7966421 https://doi.org/10.1109/IJCNN.2017.7966421

Author

Oehmcke, Stefan ; Zielinski, Oliver ; Kramer, Oliver. / Recurrent neural networks and exponential PAA for virtual marine sensors. 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. s. 4459-4466

Bibtex

@inproceedings{147bf009ab9b49faa646791e1592fbfa,
title = "Recurrent neural networks and exponential PAA for virtual marine sensors",
abstract = "Virtual sensors are getting more and more important as replacement and quality control tool for expensive and fragile hardware sensors. We introduce a virtual sensor application with marine sensor data from two data sources. The virtual sensor models are built upon recurrent neural networks (RNNs). To take full advantage of past data, we employ the time dimensionality reduction method piecewise approximate aggregation (PAA). We present an extension of this method, called exponential PAA (ExPAA) that pulls finer details from recent values, but preserves less exact information about the past. Experimental results demonstrate that RNNs benefit from this extension and confirm the stability and usability of our virtual sensor models over a five-month period of multivariate marine time series data.",
author = "Stefan Oehmcke and Oliver Zielinski and Oliver Kramer",
year = "2017",
month = jun,
day = "30",
doi = "10.1109/IJCNN.2017.7966421",
language = "English",
pages = "4459--4466",
booktitle = "2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",
note = "2017 International Joint Conference on Neural Networks, IJCNN 2017 ; Conference date: 14-05-2017 Through 19-05-2017",

}

RIS

TY - GEN

T1 - Recurrent neural networks and exponential PAA for virtual marine sensors

AU - Oehmcke, Stefan

AU - Zielinski, Oliver

AU - Kramer, Oliver

PY - 2017/6/30

Y1 - 2017/6/30

N2 - Virtual sensors are getting more and more important as replacement and quality control tool for expensive and fragile hardware sensors. We introduce a virtual sensor application with marine sensor data from two data sources. The virtual sensor models are built upon recurrent neural networks (RNNs). To take full advantage of past data, we employ the time dimensionality reduction method piecewise approximate aggregation (PAA). We present an extension of this method, called exponential PAA (ExPAA) that pulls finer details from recent values, but preserves less exact information about the past. Experimental results demonstrate that RNNs benefit from this extension and confirm the stability and usability of our virtual sensor models over a five-month period of multivariate marine time series data.

AB - Virtual sensors are getting more and more important as replacement and quality control tool for expensive and fragile hardware sensors. We introduce a virtual sensor application with marine sensor data from two data sources. The virtual sensor models are built upon recurrent neural networks (RNNs). To take full advantage of past data, we employ the time dimensionality reduction method piecewise approximate aggregation (PAA). We present an extension of this method, called exponential PAA (ExPAA) that pulls finer details from recent values, but preserves less exact information about the past. Experimental results demonstrate that RNNs benefit from this extension and confirm the stability and usability of our virtual sensor models over a five-month period of multivariate marine time series data.

UR - http://www.scopus.com/inward/record.url?scp=85031043285&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2017.7966421

DO - 10.1109/IJCNN.2017.7966421

M3 - Article in proceedings

AN - SCOPUS:85031043285

SP - 4459

EP - 4466

BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017

Y2 - 14 May 2017 through 19 May 2017

ER -

ID: 223196201