FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999712306> ?p ?o ?g. }

• W2999712306 endingPage "372" @default.
• W2999712306 startingPage "352" @default.
• W2999712306 abstract "We propose a novel approach for network-wide traffic state prediction where the statistical time series model ARIMA is used to postprocess the residuals out of the fundamental machine learning algorithm MLP. This approach is named as NN-ARIMA. Neural Network MLP is employed to capture network-scale co-movement pattern of all traffic flows, and ARIMA is used to further extract location-specific traffic features in the residual time series out of Neural Network. The experiment results show that the postprocessing the residuals of Neural Network by the ARIMA analysis helps to significantly improve accuracy of traffic state prediction by 8.9–13.4% in term of mean squared error reduction. In order to verify the efficiency of the ARIMA analysis in the postprocessing, Multidimensional Support Vector Regression (MSVR) model is also employed to replace the role of Neural Network in the comparative experiment. Two streams of comparisons, (1) NN vs. NN-ARIMA and (2) MSVR vs. MSVR-ARIMA, are performed and show consistent results. The proposed approach not only can capture network-wide co-movement pattern of traffic flows, but also seize location-specific traffic characteristics as well as sharp nonlinearity of macroscopic traffic variables. The case study indicates that the accuracy of prediction can be significantly improved when both network-scale traffic features and location-specific characteristics are taken into account." @default.
• W2999712306 created "2020-01-23" @default.
• W2999712306 creator A5001459918 @default.
• W2999712306 creator A5044993745 @default.
• W2999712306 creator A5055024212 @default.
• W2999712306 date "2020-02-01" @default.
• W2999712306 modified "2023-10-14" @default.
• W2999712306 title "Hybrid machine learning algorithm and statistical time series model for network-wide traffic forecast" @default.
• W2999712306 cites W1875626450 @default.
• W2999712306 cites W1970037526 @default.
• W2999712306 cites W1973943669 @default.
• W2999712306 cites W1974539152 @default.
• W2999712306 cites W1975362087 @default.
• W2999712306 cites W1986320533 @default.
• W2999712306 cites W1988489815 @default.
• W2999712306 cites W1991770012 @default.
• W2999712306 cites W1996851706 @default.
• W2999712306 cites W2002033255 @default.
• W2999712306 cites W2005436527 @default.
• W2999712306 cites W2009485311 @default.
• W2999712306 cites W2009797633 @default.
• W2999712306 cites W2011504567 @default.
• W2999712306 cites W2015366158 @default.
• W2999712306 cites W2016025229 @default.
• W2999712306 cites W2019191255 @default.
• W2999712306 cites W2033582154 @default.
• W2999712306 cites W2034623865 @default.
• W2999712306 cites W2037141248 @default.
• W2999712306 cites W2041609516 @default.
• W2999712306 cites W2043530786 @default.
• W2999712306 cites W2047121359 @default.
• W2999712306 cites W2047493229 @default.
• W2999712306 cites W2049952439 @default.
• W2999712306 cites W2057918527 @default.
• W2999712306 cites W2059128538 @default.
• W2999712306 cites W2069929199 @default.
• W2999712306 cites W2075407851 @default.
• W2999712306 cites W2082533141 @default.
• W2999712306 cites W2083316861 @default.
• W2999712306 cites W2084149256 @default.
• W2999712306 cites W2090192376 @default.
• W2999712306 cites W2093921901 @default.
• W2999712306 cites W2093961844 @default.
• W2999712306 cites W2094350745 @default.
• W2999712306 cites W2095797625 @default.
• W2999712306 cites W2097334502 @default.
• W2999712306 cites W2103496339 @default.
• W2999712306 cites W2105934661 @default.
• W2999712306 cites W2112024851 @default.
• W2999712306 cites W2129615967 @default.
• W2999712306 cites W2131767615 @default.
• W2999712306 cites W2132711183 @default.
• W2999712306 cites W2137983211 @default.
• W2999712306 cites W2149866111 @default.
• W2999712306 cites W2150010190 @default.
• W2999712306 cites W2152878241 @default.
• W2999712306 cites W2160507653 @default.
• W2999712306 cites W2160884799 @default.
• W2999712306 cites W2162421262 @default.
• W2999712306 cites W2166662814 @default.
• W2999712306 cites W2169991130 @default.
• W2999712306 cites W2553942547 @default.
• W2999712306 cites W2579495707 @default.
• W2999712306 cites W2593182953 @default.
• W2999712306 cites W2613331518 @default.
• W2999712306 cites W2779684064 @default.
• W2999712306 cites W2793820729 @default.
• W2999712306 cites W2800123561 @default.
• W2999712306 cites W2892302657 @default.
• W2999712306 cites W2901013492 @default.
• W2999712306 cites W2914743966 @default.
• W2999712306 cites W2915550501 @default.
• W2999712306 cites W2938342315 @default.
• W2999712306 cites W2951927893 @default.
• W2999712306 cites W2974087501 @default.
• W2999712306 cites W4239510810 @default.
• W2999712306 cites W4241368925 @default.
• W2999712306 cites W4242121569 @default.
• W2999712306 cites W996830848 @default.
• W2999712306 doi "https://doi.org/10.1016/j.trc.2019.12.022" @default.
• W2999712306 hasPublicationYear "2020" @default.
• W2999712306 type Work @default.
• W2999712306 sameAs 2999712306 @default.
• W2999712306 citedByCount "70" @default.
• W2999712306 countsByYear W29997123062020 @default.
• W2999712306 countsByYear W29997123062021 @default.
• W2999712306 countsByYear W29997123062022 @default.
• W2999712306 countsByYear W29997123062023 @default.
• W2999712306 crossrefType "journal-article" @default.
• W2999712306 hasAuthorship W2999712306A5001459918 @default.
• W2999712306 hasAuthorship W2999712306A5044993745 @default.
• W2999712306 hasAuthorship W2999712306A5055024212 @default.
• W2999712306 hasConcept C11413529 @default.
• W2999712306 hasConcept C119857082 @default.
• W2999712306 hasConcept C12267149 @default.
• W2999712306 hasConcept C124101348 @default.
• W2999712306 hasConcept C143724316 @default.
• W2999712306 hasConcept C151406439 @default.

• next