Open AccessResearch on Intelligent Prediction of Urban Short-term Traffic Flow Based on Big Data
Author(s) -
Haixiang Lang
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 - 10.1088/1742-6596/1648/2/022074
Subject(s) - computer science , intelligent transportation system , big data , key (lock) , process (computing) , traffic flow (computer networking) , artificial neural network , traffic congestion , term (time) , measure (data warehouse) , data mining , scale (ratio) , real time computing , distributed computing , artificial intelligence , transport engineering , computer network , computer security , engineering , physics , quantum mechanics , operating system
Traffic congestion has been the scale of major cities. Urban highway is an important carrier, which is to ensure the normal operation of the whole city. Therefore, we must establish intelligent transportation system, which is the most effective measure for intelligent prediction (hereinafter referred to as IP) of urban short-term traffic flow (hereinafter referred to as STTF). Among them, STTF prediction and big data are the key technologies, which require us to improve the accuracy and real-time performance of the prediction. This prediction model and intelligent system can be realized according to the idea of IP. The existing STTF prediction research is often based on the shallow model method, which can’t fully reflect the characteristics of STTF. Based on the IP method, this paper proposes a prediction model based on the distributed processing framework of MapReduce and BP neural network in Hadoop environment. Finally, this paper analyzes the basic process of the two runtime.