To predict the state of urban short-term traffic flow in real time and accurately, this paper puts forward a feasible scheme to realize traffic flow prediction by big data mining technology. Combined with the characteristics of urban traffic flow, we process and extract the collected data based on wavelet. Then, the relevant knowledge in the field of data mining is used to find the hypothesis rules most similar to current traffic flow characteristics. We also discuss the feasibility of machine learning to mine data with similar change trend from massive data for short-term traffic prediction, and provide the specific solution process. Finally, a more optimized frequent set computing method and implementation scheme are proposed through MapReduce on the cloud computing platform. The test results of the prediction model show that the excavated congestion conduction rules can accurately analyze the traffic congestion and it can be used to provide guidance paths for vehicles in real time within a local range.
Traffic Flow Prediction Method Based on Big Data Mining
01.03.2022
1095890 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Ship traffic flow prediction based on AIS data mining
IEEE | 2018
|Traffic flow prediction method based on mixed feature mining
Europäisches Patentamt | 2020
|Traffic flow prediction method based on multi-scale spatial feature mining
Europäisches Patentamt | 2023
|Method for traffic flow prediction based on spatio-temporal correlation mining
Europäisches Patentamt | 2017
|METHOD FOR TRAFFIC FLOW PREDICTION BASED ON SPATIO-TEMPORAL CORRELATION MINING
Europäisches Patentamt | 2016
|