Show simple item record

dc.contributor.advisorJenssen, Robert
dc.contributor.advisorBianchi, Filippo Maria
dc.contributor.authorChoi, Changkyu
dc.date.accessioned2019-03-07T11:12:01Z
dc.date.available2019-03-07T11:12:01Z
dc.date.issued2018-11-24
dc.description.abstractIn many applications, time series forecasting plays an irreplaceable role in time-varying systems such as energy markets, financial markets, and so on. Predicting the dynamic of time-varying systems is essential but is a difficult task because it depends on not only the nature of the system but also on external influences, such as environmental conditions and social and economic status. Recurrent Neural Networks (RNNs) are a special class of neural networks characterized by the recurrent internal connections, which enable to model the nonlinear dynamical system. Recently, they have been applied in the various forecasting tasks and reported that they outperform the forecast accuracy compared with conventional time series forecasting models. However, there is a limited study of time series forecasting using RNNs in the presence of missing data. In this thesis, we propose a novel model that utilize Dilated RNN(DRNN) and a modified attention mechanism, focusing on the problem of time series forecasting with missing data. The proposed model outperforms existing models such as AutoRegressive Integrated Moving Average(ARIMA) and Gated Recurrent Unit(GRU), with respect to the forecast accuracy on benchmark datasets. Besides, we provide a formal description of the learning procedure of RNNs, referred as truncated BPTT(k2, k1), and explain how to construct mini-batches of the training dataset for the forecasting tasks with RNNs, that has not been presented before this work. Discussions and future directions are suggested in five different perspectives at the end.en_US
dc.identifier.urihttps://hdl.handle.net/10037/14887
dc.language.isoengen_US
dc.publisherUiT Norges arktiske universiteten_US
dc.publisherUiT The Arctic University of Norwayen_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2018 The Author(s)
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/3.0en_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)en_US
dc.subject.courseIDFYS-3900
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation, visualization, signal processing, image processing: 429en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering, visualisering, signalbehandling, bildeanalyse: 429en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Algorithms and computability theory: 422en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Algoritmer og beregnbarhetsteori: 422en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427en_US
dc.titleTime Series Forecasting with Recurrent Neural Networks in Presence of Missing Dataen_US
dc.typeMaster thesisen_US
dc.typeMastergradsoppgaveen_US


File(s) in this item

Thumbnail
Thumbnail

This item appears in the following collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)