Input quality aware convolutional LSTM networks for virtual marine sensors

TY - JOUR

T1 - Input quality aware convolutional LSTM networks for virtual marine sensors

AU - Oehmcke, Stefan

AU - Zielinski, Oliver

AU - Kramer, Oliver

PY - 2018/1/31

Y1 - 2018/1/31

N2 - The harsh environmental conditions in a marine area make continuous observations of it challenging. To temporally or permanently replace faulty hardware sensors, reliable virtual sensors are getting more and more important. This paper introduces a deep learning architecture for a marine virtual sensor application that is able to utilize input quality information. We propose a novel input quality based dropout layer to take advantage of Information about the quality of the input sensors. The virtual sensor models are built upon convolutional and recurrent long short-term memory layers. We apply a time dimensionality reduction method called exPAA that retains finer details from recent values, but past information with less details are also available to the model. As interpretable reliability is important virtual sensors, we include predictive uncertainty based on dropout and Monte Carlo predictions into our neural network. Experimental results show that we perform better than the baseline and our input quality based dropout layer improves on these results even further. We also provide insights on the learned uncertainty intervals as well as the utilized linear and non-linear correlations of the first convolutional layer.

AB - The harsh environmental conditions in a marine area make continuous observations of it challenging. To temporally or permanently replace faulty hardware sensors, reliable virtual sensors are getting more and more important. This paper introduces a deep learning architecture for a marine virtual sensor application that is able to utilize input quality information. We propose a novel input quality based dropout layer to take advantage of Information about the quality of the input sensors. The virtual sensor models are built upon convolutional and recurrent long short-term memory layers. We apply a time dimensionality reduction method called exPAA that retains finer details from recent values, but past information with less details are also available to the model. As interpretable reliability is important virtual sensors, we include predictive uncertainty based on dropout and Monte Carlo predictions into our neural network. Experimental results show that we perform better than the baseline and our input quality based dropout layer improves on these results even further. We also provide insights on the learned uncertainty intervals as well as the utilized linear and non-linear correlations of the first convolutional layer.

KW - Coastal observatory

KW - Convolutional LSTM

KW - Dropout

KW - Time series

KW - Uncertainty prediction

KW - Virtual sensor

UR - http://www.scopus.com/inward/record.url?scp=85036617467&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2017.11.027

DO - 10.1016/j.neucom.2017.11.027

M3 - Journal article

AN - SCOPUS:85036617467

SN - 0925-2312

VL - 275

SP - 2603

EP - 2615

JO - Neurocomputing

JF - Neurocomputing

ER -