Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362452066> ?p ?o ?g. }
- W4362452066 endingPage "1217" @default.
- W4362452066 startingPage "1201" @default.
- W4362452066 abstract "Predictive analytics is an increasingly popular tool for enhancing decision-making processes but is in many business settings based on rule-based models. These rule-based models reach their limits in complex settings. This study compares the performance of a rule-based system with a customised LSTM encoder-decoder deep learning model for predicting train delays. For this, we use a purposefully built real-world dataset on railway transportation, where trains’ interdependence over the network makes delay prediction more difficult. Results show that the deep learning model, which incorporates rich spatiotemporal interdependency information in real-time, outperforms the rule-based system by 18%, with the difference increasing to above 23% with higher complexity. The study also dissects the performance difference across different settings: dense versus rural areas, peak versus off-peak hours, low versus high delay, and before versus during the COVID-19 pandemic. The deep learning model is implemented as a proof of concept for decision support within Belgium’s railway infrastructure company Infrabel." @default.
- W4362452066 created "2023-04-05" @default.
- W4362452066 creator A5005919993 @default.
- W4362452066 creator A5008566215 @default.
- W4362452066 creator A5019391686 @default.
- W4362452066 creator A5074711308 @default.
- W4362452066 date "2023-11-01" @default.
- W4362452066 modified "2023-10-09" @default.
- W4362452066 title "Capturing complexity over space and time via deep learning: An application to real-time delay prediction in railways" @default.
- W4362452066 cites W1689711448 @default.
- W4362452066 cites W1984710451 @default.
- W4362452066 cites W1988604380 @default.
- W4362452066 cites W2022740958 @default.
- W4362452066 cites W2053811733 @default.
- W4362452066 cites W2064675550 @default.
- W4362452066 cites W2070564502 @default.
- W4362452066 cites W2079246731 @default.
- W4362452066 cites W2107878631 @default.
- W4362452066 cites W2110920860 @default.
- W4362452066 cites W2121394390 @default.
- W4362452066 cites W2121991049 @default.
- W4362452066 cites W2143953455 @default.
- W4362452066 cites W2148714761 @default.
- W4362452066 cites W2157331557 @default.
- W4362452066 cites W2248783999 @default.
- W4362452066 cites W2360467051 @default.
- W4362452066 cites W2595390076 @default.
- W4362452066 cites W2610956397 @default.
- W4362452066 cites W2618782758 @default.
- W4362452066 cites W2746326988 @default.
- W4362452066 cites W2791079235 @default.
- W4362452066 cites W2801389612 @default.
- W4362452066 cites W2887126012 @default.
- W4362452066 cites W2919115771 @default.
- W4362452066 cites W2937568364 @default.
- W4362452066 cites W2937808860 @default.
- W4362452066 cites W2943548682 @default.
- W4362452066 cites W2945277272 @default.
- W4362452066 cites W2951591639 @default.
- W4362452066 cites W2963059095 @default.
- W4362452066 cites W2969420897 @default.
- W4362452066 cites W2971452554 @default.
- W4362452066 cites W2975867066 @default.
- W4362452066 cites W2980544481 @default.
- W4362452066 cites W2987656958 @default.
- W4362452066 cites W2994808218 @default.
- W4362452066 cites W2997073788 @default.
- W4362452066 cites W3004721071 @default.
- W4362452066 cites W3010786073 @default.
- W4362452066 cites W3044811479 @default.
- W4362452066 cites W3088297353 @default.
- W4362452066 cites W3109254449 @default.
- W4362452066 cites W3118077410 @default.
- W4362452066 cites W3121399352 @default.
- W4362452066 cites W3125387313 @default.
- W4362452066 cites W3133396942 @default.
- W4362452066 cites W3140537764 @default.
- W4362452066 cites W3145694833 @default.
- W4362452066 cites W3165519921 @default.
- W4362452066 cites W3179620152 @default.
- W4362452066 cites W3180962798 @default.
- W4362452066 cites W3199841521 @default.
- W4362452066 cites W4214669199 @default.
- W4362452066 cites W4220694402 @default.
- W4362452066 cites W4320170226 @default.
- W4362452066 doi "https://doi.org/10.1016/j.ejor.2023.03.040" @default.
- W4362452066 hasPublicationYear "2023" @default.
- W4362452066 type Work @default.
- W4362452066 citedByCount "1" @default.
- W4362452066 countsByYear W43624520662023 @default.
- W4362452066 crossrefType "journal-article" @default.
- W4362452066 hasAuthorship W4362452066A5005919993 @default.
- W4362452066 hasAuthorship W4362452066A5008566215 @default.
- W4362452066 hasAuthorship W4362452066A5019391686 @default.
- W4362452066 hasAuthorship W4362452066A5074711308 @default.
- W4362452066 hasConcept C101738243 @default.
- W4362452066 hasConcept C108583219 @default.
- W4362452066 hasConcept C119857082 @default.
- W4362452066 hasConcept C124101348 @default.
- W4362452066 hasConcept C154945302 @default.
- W4362452066 hasConcept C17744445 @default.
- W4362452066 hasConcept C185874996 @default.
- W4362452066 hasConcept C190839683 @default.
- W4362452066 hasConcept C199539241 @default.
- W4362452066 hasConcept C205649164 @default.
- W4362452066 hasConcept C41008148 @default.
- W4362452066 hasConcept C58640448 @default.
- W4362452066 hasConcept C79158427 @default.
- W4362452066 hasConcept C83209312 @default.
- W4362452066 hasConceptScore W4362452066C101738243 @default.
- W4362452066 hasConceptScore W4362452066C108583219 @default.
- W4362452066 hasConceptScore W4362452066C119857082 @default.
- W4362452066 hasConceptScore W4362452066C124101348 @default.
- W4362452066 hasConceptScore W4362452066C154945302 @default.
- W4362452066 hasConceptScore W4362452066C17744445 @default.
- W4362452066 hasConceptScore W4362452066C185874996 @default.
- W4362452066 hasConceptScore W4362452066C190839683 @default.
- W4362452066 hasConceptScore W4362452066C199539241 @default.