FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891702854> ?p ?o ?g. }

• W2891702854 abstract "With the advent of Big Data, nowadays in many applications databases containing large quantities of similar time series are available. Forecasting time series in these domains with traditional univariate forecasting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks (RNNs), and in particular Long Short-Term Memory (LSTM) networks, have proven recently that they are able to outperform state-of-the-art univariate time series forecasting methods in this context when trained across all available time series. However, if the time series database is heterogeneous, accuracy may degenerate, so that on the way towards fully automatic forecasting methods in this space, a notion of similarity between the time series needs to be built into the methods. To this end, we present a prediction model that can be used with different types of RNN models on subgroups of similar time series, which are identified by time series clustering techniques. We assess our proposed methodology using LSTM networks, a widely popular RNN variant. Our method achieves competitive results on benchmarking datasets under competition evaluation procedures. In particular, in terms of mean sMAPE accuracy, it consistently outperforms the baseline LSTM model and outperforms all other methods on the CIF2016 forecasting competition dataset." @default.
• W2891702854 created "2018-09-27" @default.
• W2891702854 creator A5010495833 @default.
• W2891702854 creator A5040800662 @default.
• W2891702854 creator A5086783701 @default.
• W2891702854 date "2017-10-09" @default.
• W2891702854 modified "2023-09-22" @default.
• W2891702854 title "Forecasting Across Time Series Databases using Recurrent Neural Networks on Groups of Similar Series: A Clustering Approach" @default.
• W2891702854 cites W123217851 @default.
• W2891702854 cites W129305155 @default.
• W2891702854 cites W1501500081 @default.
• W2891702854 cites W1536447791 @default.
• W2891702854 cites W1607713496 @default.
• W2891702854 cites W1674799117 @default.
• W2891702854 cites W179875071 @default.
• W2891702854 cites W1894414046 @default.
• W2891702854 cites W1964892656 @default.
• W2891702854 cites W1988115241 @default.
• W2891702854 cites W1989280111 @default.
• W2891702854 cites W1995875735 @default.
• W2891702854 cites W1999273940 @default.
• W2891702854 cites W2011227258 @default.
• W2891702854 cites W2015393497 @default.
• W2891702854 cites W2016210396 @default.
• W2891702854 cites W2026430219 @default.
• W2891702854 cites W2030888282 @default.
• W2891702854 cites W2038849095 @default.
• W2891702854 cites W2042506099 @default.
• W2891702854 cites W2045199291 @default.
• W2891702854 cites W2046356540 @default.
• W2891702854 cites W2048665112 @default.
• W2891702854 cites W2048695473 @default.
• W2891702854 cites W2056742598 @default.
• W2891702854 cites W2064675550 @default.
• W2891702854 cites W2097747115 @default.
• W2891702854 cites W2103496339 @default.
• W2891702854 cites W2104908927 @default.
• W2891702854 cites W2107878631 @default.
• W2891702854 cites W2110242546 @default.
• W2891702854 cites W2110485445 @default.
• W2891702854 cites W2116512828 @default.
• W2891702854 cites W2119608925 @default.
• W2891702854 cites W2136848157 @default.
• W2891702854 cites W2141173017 @default.
• W2891702854 cites W2142338071 @default.
• W2891702854 cites W2143612262 @default.
• W2891702854 cites W2145856394 @default.
• W2891702854 cites W2149905014 @default.
• W2891702854 cites W2152209375 @default.
• W2891702854 cites W2153787847 @default.
• W2891702854 cites W2154326182 @default.
• W2891702854 cites W2165466912 @default.
• W2891702854 cites W2168020168 @default.
• W2891702854 cites W2168431040 @default.
• W2891702854 cites W2184254008 @default.
• W2891702854 cites W2260161590 @default.
• W2891702854 cites W2278984902 @default.
• W2891702854 cites W2404614201 @default.
• W2891702854 cites W2417021467 @default.
• W2891702854 cites W2513383847 @default.
• W2891702854 cites W2546314413 @default.
• W2891702854 cites W2557283755 @default.
• W2891702854 cites W2564701384 @default.
• W2891702854 cites W2593696568 @default.
• W2891702854 cites W2798058877 @default.
• W2891702854 cites W2811189031 @default.
• W2891702854 cites W2811507150 @default.
• W2891702854 cites W2949888546 @default.
• W2891702854 cites W2950121804 @default.
• W2891702854 cites W2950182411 @default.
• W2891702854 cites W3122024901 @default.
• W2891702854 hasPublicationYear "2017" @default.
• W2891702854 type Work @default.
• W2891702854 sameAs 2891702854 @default.
• W2891702854 citedByCount "2" @default.
• W2891702854 countsByYear W28917028542019 @default.
• W2891702854 countsByYear W28917028542020 @default.
• W2891702854 crossrefType "posted-content" @default.
• W2891702854 hasAuthorship W2891702854A5010495833 @default.
• W2891702854 hasAuthorship W2891702854A5040800662 @default.
• W2891702854 hasAuthorship W2891702854A5086783701 @default.
• W2891702854 hasConcept C119857082 @default.
• W2891702854 hasConcept C124101348 @default.
• W2891702854 hasConcept C143724316 @default.
• W2891702854 hasConcept C144133560 @default.
• W2891702854 hasConcept C147168706 @default.
• W2891702854 hasConcept C151406439 @default.
• W2891702854 hasConcept C151730666 @default.
• W2891702854 hasConcept C154945302 @default.
• W2891702854 hasConcept C161584116 @default.
• W2891702854 hasConcept C162853370 @default.
• W2891702854 hasConcept C166957645 @default.
• W2891702854 hasConcept C199163554 @default.
• W2891702854 hasConcept C205649164 @default.
• W2891702854 hasConcept C2779343474 @default.
• W2891702854 hasConcept C41008148 @default.
• W2891702854 hasConcept C50644808 @default.
• W2891702854 hasConcept C73555534 @default.
• W2891702854 hasConcept C86251818 @default.
• W2891702854 hasConcept C86803240 @default.

• next