Recurrent neural networks and exponential PAA for virtual marine sensors

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

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.

OriginalsprogEngelsk
Titel2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
Antal sider8
ForlagInstitute of Electrical and Electronics Engineers Inc.
Publikationsdato30 jun. 2017
Sider4459-4466
Artikelnummer7966421
ISBN (Elektronisk)9781509061815
DOI
StatusUdgivet - 30 jun. 2017
Eksternt udgivetJa
Begivenhed2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, USA
Varighed: 14 maj 201719 maj 2017

Konference

Konference2017 International Joint Conference on Neural Networks, IJCNN 2017
LandUSA
ByAnchorage
Periode14/05/201719/05/2017
SponsorBrain-Mind Institute (BMI), Budapest Semester in Cognitive Science (BSCS), Intel

ID: 223196201