Traffic big data dimensionality reduction method based on manifold learning

Abstract

The invention provides a traffic big data dimensionality reduction method based on manifold learning. The traffic big data dimensionality reduction method comprises the following steps: 1, acquiring spatial-temporal trajectory data of various urban traffic to obtain traffic big data; 2, classifying the traffic big data, uniformly configuring attributes of the traffic big data and loading data into a database; and 3, performing data dimensionality reduction processing on the traffic big data by an LLE (Locally linear embedding) manifold learning method. Through adoption of the traffic big data dimensionality reduction method, the data dimension reduction is performed on high-dimensionality spatial data by a manifold learning algorithm, so that an excessively-large computation amount is avoided; the essential characteristics of the data can be reflected better; and the mining performance of traffic data is enhanced.

Description

technical field [0001] The invention belongs to the field of big data processing technology and intelligent traffic application, and specifically relates to a dimensionality reduction processing method for traffic big data based on manifold learning. Background technique [0002] Traffic flow is a complex physical phenomenon, and the resulting urban traffic big data has the characteristics of dynamic change, high randomness, nonlinearity, heterogeneity and short life cycle. For example, in the process of rapid development in many cities, serious traffic congestion inevitably occurs. Traffic data forms a high-dimensional spatial data structure, and the traffic data of these high-dimensional data spatial structures are also highly time-sensitive. Traditional transportation theory is difficult to deal with this kind of high-dimensional space data, because when the data is located in a space with high dimensionality, if the data is directly processed, there will be the followin...

AI Technical Summary

Problems solved by technology

Traditional transportation theory is difficult to deal with this kind of high-dimensional space data, because when the data is located in a space with high dimensionality, if the data is directly processed, there will be the following problems: First, the so-called "curse of dimensionality" will appear problems, resulting in a huge amount of computation; secondly, these data usually cannot reflect the essential characteristics of the data, and if they are directly processed, ideal results cannot be obtained

[0003] The traditional traffic theory is not perfect in the processing of high-dimensional spatial data. It is difficult to accurately predict the traffic pattern, and its reliability cannot be effectively analyzed, resulting in the inability to conduct in-depth mining of comprehensive data information. Therefore, a large amount of traffic data cannot accurately reflect the real situation. traffic condition

Images