Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204321804> ?p ?o ?g. }
- W3204321804 abstract "Heterogeneity and irregularity of multi-source data sets present a significant challenge to time-series analysis. In the literature, the fusion of multi-source time-series has been achieved either by using ensemble learning models which ignore temporal patterns and correlation within features or by defining a fixed-size window to select specific parts of the data sets. On the other hand, many studies have shown major improvement to handle the irregularity of time-series, yet none of these studies has been applied to multi-source data. In this work, we design a novel architecture, PIETS, to model heterogeneous time-series. PIETS has the following characteristics: (1) irregularity encoders for multi-source samples that can leverage all available information and accelerate the convergence of the model; (2) parallelised neural networks to enable flexibility and avoid information overwhelming; and (3) attention mechanism that highlights different information and gives high importance to the most related data. Through extensive experiments on real-world data sets related to COVID-19, we show that the proposed architecture is able to effectively model heterogeneous temporal data and outperforms other state-of-the-art approaches in the prediction task." @default.
- W3204321804 created "2021-10-11" @default.
- W3204321804 creator A5000564739 @default.
- W3204321804 creator A5001295407 @default.
- W3204321804 creator A5039040673 @default.
- W3204321804 creator A5090893421 @default.
- W3204321804 date "2021-12-01" @default.
- W3204321804 modified "2023-10-18" @default.
- W3204321804 title "PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Series" @default.
- W3204321804 cites W2121536973 @default.
- W3204321804 cites W2133470535 @default.
- W3204321804 cites W2178310074 @default.
- W3204321804 cites W2210833864 @default.
- W3204321804 cites W2282571455 @default.
- W3204321804 cites W2594685110 @default.
- W3204321804 cites W2754125139 @default.
- W3204321804 cites W2807748885 @default.
- W3204321804 cites W2885195348 @default.
- W3204321804 cites W2901533061 @default.
- W3204321804 cites W2943128471 @default.
- W3204321804 cites W2950622064 @default.
- W3204321804 cites W2958796454 @default.
- W3204321804 cites W2962769218 @default.
- W3204321804 cites W2963255584 @default.
- W3204321804 cites W2963755523 @default.
- W3204321804 cites W2964010366 @default.
- W3204321804 cites W2964244673 @default.
- W3204321804 cites W2964264525 @default.
- W3204321804 cites W2971306341 @default.
- W3204321804 cites W2991520089 @default.
- W3204321804 cites W3006713198 @default.
- W3204321804 cites W3011716991 @default.
- W3204321804 cites W3013559684 @default.
- W3204321804 cites W3016236951 @default.
- W3204321804 cites W3024272117 @default.
- W3204321804 cites W3034427973 @default.
- W3204321804 cites W3043567704 @default.
- W3204321804 cites W3044249689 @default.
- W3204321804 cites W3048699616 @default.
- W3204321804 cites W3096986660 @default.
- W3204321804 cites W3119564402 @default.
- W3204321804 cites W76828661 @default.
- W3204321804 doi "https://doi.org/10.1109/icdm51629.2021.00109" @default.
- W3204321804 hasPublicationYear "2021" @default.
- W3204321804 type Work @default.
- W3204321804 sameAs 3204321804 @default.
- W3204321804 citedByCount "0" @default.
- W3204321804 crossrefType "proceedings-article" @default.
- W3204321804 hasAuthorship W3204321804A5000564739 @default.
- W3204321804 hasAuthorship W3204321804A5001295407 @default.
- W3204321804 hasAuthorship W3204321804A5039040673 @default.
- W3204321804 hasAuthorship W3204321804A5090893421 @default.
- W3204321804 hasBestOaLocation W32043218042 @default.
- W3204321804 hasConcept C105795698 @default.
- W3204321804 hasConcept C111919701 @default.
- W3204321804 hasConcept C118505674 @default.
- W3204321804 hasConcept C119857082 @default.
- W3204321804 hasConcept C124101348 @default.
- W3204321804 hasConcept C143724316 @default.
- W3204321804 hasConcept C151406439 @default.
- W3204321804 hasConcept C151730666 @default.
- W3204321804 hasConcept C153083717 @default.
- W3204321804 hasConcept C154945302 @default.
- W3204321804 hasConcept C2780598303 @default.
- W3204321804 hasConcept C33923547 @default.
- W3204321804 hasConcept C41008148 @default.
- W3204321804 hasConcept C50644808 @default.
- W3204321804 hasConcept C67186912 @default.
- W3204321804 hasConcept C77088390 @default.
- W3204321804 hasConcept C86803240 @default.
- W3204321804 hasConceptScore W3204321804C105795698 @default.
- W3204321804 hasConceptScore W3204321804C111919701 @default.
- W3204321804 hasConceptScore W3204321804C118505674 @default.
- W3204321804 hasConceptScore W3204321804C119857082 @default.
- W3204321804 hasConceptScore W3204321804C124101348 @default.
- W3204321804 hasConceptScore W3204321804C143724316 @default.
- W3204321804 hasConceptScore W3204321804C151406439 @default.
- W3204321804 hasConceptScore W3204321804C151730666 @default.
- W3204321804 hasConceptScore W3204321804C153083717 @default.
- W3204321804 hasConceptScore W3204321804C154945302 @default.
- W3204321804 hasConceptScore W3204321804C2780598303 @default.
- W3204321804 hasConceptScore W3204321804C33923547 @default.
- W3204321804 hasConceptScore W3204321804C41008148 @default.
- W3204321804 hasConceptScore W3204321804C50644808 @default.
- W3204321804 hasConceptScore W3204321804C67186912 @default.
- W3204321804 hasConceptScore W3204321804C77088390 @default.
- W3204321804 hasConceptScore W3204321804C86803240 @default.
- W3204321804 hasFunder F4320334704 @default.
- W3204321804 hasLocation W32043218041 @default.
- W3204321804 hasLocation W32043218042 @default.
- W3204321804 hasLocation W32043218043 @default.
- W3204321804 hasOpenAccess W3204321804 @default.
- W3204321804 hasPrimaryLocation W32043218041 @default.
- W3204321804 hasRelatedWork W1632690555 @default.
- W3204321804 hasRelatedWork W2156223678 @default.
- W3204321804 hasRelatedWork W2242271381 @default.
- W3204321804 hasRelatedWork W2357809648 @default.
- W3204321804 hasRelatedWork W2378555542 @default.
- W3204321804 hasRelatedWork W2381421930 @default.
- W3204321804 hasRelatedWork W2990514669 @default.