Open AccessShort-Term Traffic Flow Prediction Methods: A Survey
Author(s) -
Yijing Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1486/5/052018
Subject(s) - traffic flow (computer networking) , term (time) , computer science , intelligent transportation system , autoregressive integrated moving average , advanced traffic management system , transport engineering , floating car data , traffic engineering , field (mathematics) , operations research , traffic congestion , engineering , computer security , computer network , time series , physics , mathematics , quantum mechanics , machine learning , pure mathematics
As a major part of a smart transport system, the vehicle management system has become an effective means for traffic management departments to control urban road traffic with the advent of smart transportation technology. The short-term traffic flow forecasting provides drivers with the best route as a core engineering of the car guidance system as well as the very relevant mathematical foundation in the field of intelligent transport, improving the traffic management schemes and managing traffic flow by measuring and projecting path flows. This paper mainly aims at incorporating the current mainstream approaches to avoid short-term traffic flow, including the ARIMA, RNN, Sparse Auto Encoder (SAE) and others. We hope that this article will help those who want to delve into it quickly.