Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328103753> ?p ?o ?g. }
- W4328103753 endingPage "381" @default.
- W4328103753 startingPage "359" @default.
- W4328103753 abstract "Due to prediction on the traffic flow is influenced by the real environment and historical data, the produced traffic graph may include significant uncertainty. The graph convolution operation is widely used in traffic flow prediction with its effective modeling ability on graph structures. However, in this method, it ignores the roles of external factors and historical data from fixed period is used that inevitably will lead to exclusion of detailed dynamic spatial–temporal correlation. To this end, we propose a novel method based on prior knowledge enhanced time-varying graph convolution network (PKET-GCN). First, we characterize factors affecting the traffic flow into dynamic and static features. The dynamic features include data correlation and external interference, while the static features consist of physical distances. Then we design a prior knowledge based module to extract the correlation of nodes and combine it with graph convolution to obtain dynamic spatial features. Next, a time-varying feature extraction module is designed to derive dynamic and long-term temporal features from periodic and adjacent sequences. Finally, the projection module is established to fuse the multiple modules and give the prediction value. The experimental results on five real-world datasets indicate that PKET-GCN is more effective than several existing methods." @default.
- W4328103753 created "2023-03-22" @default.
- W4328103753 creator A5008965695 @default.
- W4328103753 creator A5059085853 @default.
- W4328103753 creator A5061702931 @default.
- W4328103753 creator A5069969191 @default.
- W4328103753 creator A5080152964 @default.
- W4328103753 creator A5090540721 @default.
- W4328103753 date "2023-07-01" @default.
- W4328103753 modified "2023-09-24" @default.
- W4328103753 title "PKET-GCN: Prior knowledge enhanced time-varying graph convolution network for traffic flow prediction" @default.
- W4328103753 cites W1574447377 @default.
- W4328103753 cites W2064675550 @default.
- W4328103753 cites W2508457857 @default.
- W4328103753 cites W2596628535 @default.
- W4328103753 cites W2613322775 @default.
- W4328103753 cites W2793820729 @default.
- W4328103753 cites W2901504064 @default.
- W4328103753 cites W2903871660 @default.
- W4328103753 cites W2904262414 @default.
- W4328103753 cites W2910892140 @default.
- W4328103753 cites W2945622688 @default.
- W4328103753 cites W2964319113 @default.
- W4328103753 cites W2968911474 @default.
- W4328103753 cites W3001437801 @default.
- W4328103753 cites W3020398622 @default.
- W4328103753 cites W3021810927 @default.
- W4328103753 cites W3025986213 @default.
- W4328103753 cites W3034408619 @default.
- W4328103753 cites W3035184251 @default.
- W4328103753 cites W3035338169 @default.
- W4328103753 cites W3037233197 @default.
- W4328103753 cites W3100997528 @default.
- W4328103753 cites W3103720336 @default.
- W4328103753 cites W3107462623 @default.
- W4328103753 cites W3115148317 @default.
- W4328103753 cites W3120707461 @default.
- W4328103753 cites W3127172108 @default.
- W4328103753 cites W3129626349 @default.
- W4328103753 cites W3185720226 @default.
- W4328103753 cites W3193349278 @default.
- W4328103753 cites W3212041461 @default.
- W4328103753 cites W4205542731 @default.
- W4328103753 cites W4210257598 @default.
- W4328103753 cites W4283574791 @default.
- W4328103753 cites W4285161977 @default.
- W4328103753 cites W4289444019 @default.
- W4328103753 cites W4312201182 @default.
- W4328103753 cites W4312852945 @default.
- W4328103753 cites W4315798480 @default.
- W4328103753 cites W4317721443 @default.
- W4328103753 doi "https://doi.org/10.1016/j.ins.2023.03.093" @default.
- W4328103753 hasPublicationYear "2023" @default.
- W4328103753 type Work @default.
- W4328103753 citedByCount "2" @default.
- W4328103753 countsByYear W43281037532023 @default.
- W4328103753 crossrefType "journal-article" @default.
- W4328103753 hasAuthorship W4328103753A5008965695 @default.
- W4328103753 hasAuthorship W4328103753A5059085853 @default.
- W4328103753 hasAuthorship W4328103753A5061702931 @default.
- W4328103753 hasAuthorship W4328103753A5069969191 @default.
- W4328103753 hasAuthorship W4328103753A5080152964 @default.
- W4328103753 hasAuthorship W4328103753A5090540721 @default.
- W4328103753 hasConcept C11413529 @default.
- W4328103753 hasConcept C117220453 @default.
- W4328103753 hasConcept C124101348 @default.
- W4328103753 hasConcept C132525143 @default.
- W4328103753 hasConcept C153180895 @default.
- W4328103753 hasConcept C154945302 @default.
- W4328103753 hasConcept C2524010 @default.
- W4328103753 hasConcept C27458966 @default.
- W4328103753 hasConcept C33923547 @default.
- W4328103753 hasConcept C41008148 @default.
- W4328103753 hasConcept C45347329 @default.
- W4328103753 hasConcept C50644808 @default.
- W4328103753 hasConcept C80444323 @default.
- W4328103753 hasConceptScore W4328103753C11413529 @default.
- W4328103753 hasConceptScore W4328103753C117220453 @default.
- W4328103753 hasConceptScore W4328103753C124101348 @default.
- W4328103753 hasConceptScore W4328103753C132525143 @default.
- W4328103753 hasConceptScore W4328103753C153180895 @default.
- W4328103753 hasConceptScore W4328103753C154945302 @default.
- W4328103753 hasConceptScore W4328103753C2524010 @default.
- W4328103753 hasConceptScore W4328103753C27458966 @default.
- W4328103753 hasConceptScore W4328103753C33923547 @default.
- W4328103753 hasConceptScore W4328103753C41008148 @default.
- W4328103753 hasConceptScore W4328103753C45347329 @default.
- W4328103753 hasConceptScore W4328103753C50644808 @default.
- W4328103753 hasConceptScore W4328103753C80444323 @default.
- W4328103753 hasLocation W43281037531 @default.
- W4328103753 hasOpenAccess W4328103753 @default.
- W4328103753 hasPrimaryLocation W43281037531 @default.
- W4328103753 hasRelatedWork W1567692042 @default.
- W4328103753 hasRelatedWork W1827256152 @default.
- W4328103753 hasRelatedWork W2041344627 @default.
- W4328103753 hasRelatedWork W2068395868 @default.
- W4328103753 hasRelatedWork W2080682474 @default.
- W4328103753 hasRelatedWork W2347219288 @default.