{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360580240162714496.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.24963/ijcai.2019/378"}}],"dc:title":[{"@value":"Outlier Detection for Time Series with Recurrent Autoencoder Ensembles"}],"description":[{"type":"abstract","notation":[{"@value":"<jats:p>We propose two solutions to outlier detection in time series based on recurrent autoencoder ensembles. The solutions exploit autoencoders built using sparsely-connected recurrent neural networks (S-RNNs). Such networks make it possible to generate multiple autoencoders with different neural network connection structures. The two solutions are ensemble frameworks, specifically an independent framework and a shared framework, both of which combine multiple S-RNN based autoencoders to enable outlier detection.  This ensemble-based approach aims to reduce the effects of some autoencoders being overfitted to outliers, this way improving overall detection quality. Experiments with two large real-world time series data sets, including univariate and multivariate time series, offer insight into the design properties of the proposed frameworks and demonstrate that the resulting solutions are capable of outperforming both baselines and the state-of-the-art methods.</jats:p>"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380580240162714499","@type":"Researcher","foaf:name":[{"@value":"Tung Kieu"}],"jpcoar:affiliationName":[{"@value":"Department of Computer Science, Aalborg University, Denmark"}]},{"@id":"https://cir.nii.ac.jp/crid/1380580240162714497","@type":"Researcher","foaf:name":[{"@value":"Bin Yang"}],"jpcoar:affiliationName":[{"@value":"Department of Computer Science, Aalborg University, Denmark"}]},{"@id":"https://cir.nii.ac.jp/crid/1380580240162714498","@type":"Researcher","foaf:name":[{"@value":"Chenjuan Guo"}],"jpcoar:affiliationName":[{"@value":"Department of Computer Science, Aalborg University, Denmark"}]},{"@id":"https://cir.nii.ac.jp/crid/1380580240162714496","@type":"Researcher","foaf:name":[{"@value":"Christian S. Jensen"}],"jpcoar:affiliationName":[{"@value":"Department of Computer Science, Aalborg University, Denmark"}]}],"publication":{"prism:publicationName":[{"@value":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"}],"dc:publisher":[{"@value":"International Joint Conferences on Artificial Intelligence Organization"}],"prism:publicationDate":"2019-08","prism:startingPage":"2725","prism:endingPage":"2732"},"reviewed":"false","createdAt":"2019-07-28","modifiedAt":"2019-07-28","relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360864737224427392","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Profiling of kidney involvement in systemic lupus erythematosus by deep learning using the National Database of Designated Incurable Diseases of Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1390017193115991168","@type":"Article","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Reconstructive reservoir computing for anomaly detection in time-series signals"}]},{"@id":"https://cir.nii.ac.jp/crid/2051433317038755712","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Deep learning analysis of clinical course of primary nephrotic syndrome : Japan Nephrotic Syndrome Cohort Study (JNSCS)"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.24963/ijcai.2019/378"},{"@type":"CROSSREF","@value":"10.1587/nolta.15.183_references_DOI_IqjFcZhHpTdwQScdu0CTHsUPvuz"},{"@type":"CROSSREF","@value":"10.1007/s10157-022-02256-3_references_DOI_IqjFcZhHpTdwQScdu0CTHsUPvuz"},{"@type":"CROSSREF","@value":"10.1007/s10157-023-02337-x_references_DOI_IqjFcZhHpTdwQScdu0CTHsUPvuz"}]}