Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220986523> ?p ?o ?g. }
- W4220986523 endingPage "103607" @default.
- W4220986523 startingPage "103607" @default.
- W4220986523 abstract "Accurate short-term traffic forecasting is the cornerstone for Intelligent Transportation Systems. In the past several decades, many models have been proposed to continuously improve the predictive accuracy. A key but unsolved question is whether there is a theoretical bound to the accuracy with which traffic can be predicted and whether that limit can be directly estimated from data. To answer this question, we use core concepts in information theory to derive the limit of predictability in short-term traffic forecasting. Theoretical analysis proves that conditional differential entropy poses a rigorous lower bound of negative-log-likelihood (NLL) for probabilistic models. And the continuous form of Fano’s theorem further gives a loose lower bound of mean-square-error (MSE) for deterministic models. Based on the special properties of traffic dynamics, two assumptions are made in the estimate of entropy metrics: cyclostationarity (traffic phenomena show strong periodicity) and localized spatial correlation (due to kinematic wave propagation). They allow formulating the limit of predictability as a function of longitudinal space and time-of-day which finds the most uncertain locations and periods solely from data. Experiments on univariate traffic accumulation forecasting and network-level speed forecasting show that the selected models, including some state-of-the-art deep learning models, indeed cannot outperform the estimated lower bounds but just approach them. The limit of predictability depends on time-of-day, network locations, observation range, and prediction horizon. The results reveal that the stochastic nature of traffic dynamics and improper assumptions on the prior distribution of output are two major factors that restrict the predictive performance. In summary, the proposed method estimates a trustworthy performance boundary for most traffic forecasting models. These conclusions are helpful for further studies in this domain." @default.
- W4220986523 created "2022-04-03" @default.
- W4220986523 creator A5011057063 @default.
- W4220986523 creator A5015875245 @default.
- W4220986523 creator A5079555394 @default.
- W4220986523 date "2022-05-01" @default.
- W4220986523 modified "2023-10-04" @default.
- W4220986523 title "Estimate the limit of predictability in short-term traffic forecasting: An entropy-based approach" @default.
- W4220986523 cites W1968078488 @default.
- W4220986523 cites W1973463154 @default.
- W4220986523 cites W1984391316 @default.
- W4220986523 cites W1987228002 @default.
- W4220986523 cites W1995875735 @default.
- W4220986523 cites W2029486861 @default.
- W4220986523 cites W2037393538 @default.
- W4220986523 cites W2038622450 @default.
- W4220986523 cites W2060590556 @default.
- W4220986523 cites W2063059576 @default.
- W4220986523 cites W2076077609 @default.
- W4220986523 cites W2081120846 @default.
- W4220986523 cites W2090764388 @default.
- W4220986523 cites W2112024851 @default.
- W4220986523 cites W2124428761 @default.
- W4220986523 cites W2150879893 @default.
- W4220986523 cites W2152254020 @default.
- W4220986523 cites W2156705969 @default.
- W4220986523 cites W2172041433 @default.
- W4220986523 cites W2206302789 @default.
- W4220986523 cites W2267720383 @default.
- W4220986523 cites W2281039876 @default.
- W4220986523 cites W2402274463 @default.
- W4220986523 cites W2553942547 @default.
- W4220986523 cites W2579495707 @default.
- W4220986523 cites W2627057354 @default.
- W4220986523 cites W2750951965 @default.
- W4220986523 cites W2765086077 @default.
- W4220986523 cites W2773084720 @default.
- W4220986523 cites W2789788750 @default.
- W4220986523 cites W2799109291 @default.
- W4220986523 cites W2913352800 @default.
- W4220986523 cites W2917701982 @default.
- W4220986523 cites W3135178273 @default.
- W4220986523 cites W4247181706 @default.
- W4220986523 cites W939319017 @default.
- W4220986523 doi "https://doi.org/10.1016/j.trc.2022.103607" @default.
- W4220986523 hasPublicationYear "2022" @default.
- W4220986523 type Work @default.
- W4220986523 citedByCount "2" @default.
- W4220986523 countsByYear W42209865232023 @default.
- W4220986523 crossrefType "journal-article" @default.
- W4220986523 hasAuthorship W4220986523A5011057063 @default.
- W4220986523 hasAuthorship W4220986523A5015875245 @default.
- W4220986523 hasAuthorship W4220986523A5079555394 @default.
- W4220986523 hasBestOaLocation W42209865231 @default.
- W4220986523 hasConcept C105795698 @default.
- W4220986523 hasConcept C106301342 @default.
- W4220986523 hasConcept C121332964 @default.
- W4220986523 hasConcept C121864883 @default.
- W4220986523 hasConcept C122282355 @default.
- W4220986523 hasConcept C134306372 @default.
- W4220986523 hasConcept C149782125 @default.
- W4220986523 hasConcept C151201525 @default.
- W4220986523 hasConcept C185429906 @default.
- W4220986523 hasConcept C197640229 @default.
- W4220986523 hasConcept C33923547 @default.
- W4220986523 hasConcept C41008148 @default.
- W4220986523 hasConcept C49937458 @default.
- W4220986523 hasConcept C62520636 @default.
- W4220986523 hasConcept C77553402 @default.
- W4220986523 hasConceptScore W4220986523C105795698 @default.
- W4220986523 hasConceptScore W4220986523C106301342 @default.
- W4220986523 hasConceptScore W4220986523C121332964 @default.
- W4220986523 hasConceptScore W4220986523C121864883 @default.
- W4220986523 hasConceptScore W4220986523C122282355 @default.
- W4220986523 hasConceptScore W4220986523C134306372 @default.
- W4220986523 hasConceptScore W4220986523C149782125 @default.
- W4220986523 hasConceptScore W4220986523C151201525 @default.
- W4220986523 hasConceptScore W4220986523C185429906 @default.
- W4220986523 hasConceptScore W4220986523C197640229 @default.
- W4220986523 hasConceptScore W4220986523C33923547 @default.
- W4220986523 hasConceptScore W4220986523C41008148 @default.
- W4220986523 hasConceptScore W4220986523C49937458 @default.
- W4220986523 hasConceptScore W4220986523C62520636 @default.
- W4220986523 hasConceptScore W4220986523C77553402 @default.
- W4220986523 hasLocation W42209865231 @default.
- W4220986523 hasLocation W42209865232 @default.
- W4220986523 hasOpenAccess W4220986523 @default.
- W4220986523 hasPrimaryLocation W42209865231 @default.
- W4220986523 hasRelatedWork W1527837723 @default.
- W4220986523 hasRelatedWork W2031132253 @default.
- W4220986523 hasRelatedWork W2118112569 @default.
- W4220986523 hasRelatedWork W2133281999 @default.
- W4220986523 hasRelatedWork W2136222558 @default.
- W4220986523 hasRelatedWork W2182220522 @default.
- W4220986523 hasRelatedWork W2974068988 @default.
- W4220986523 hasRelatedWork W4290792893 @default.
- W4220986523 hasRelatedWork W4376104896 @default.
- W4220986523 hasRelatedWork W4385497698 @default.