Spatio-temporal data prediction method based on stacking ensemble learning algorithm

Abstract

The invention discloses a spatio-temporal data prediction method based on a stacking ensemble learning algorithm, which can improve prediction efficiency and prediction accuracy. The spatio-temporal data prediction method based on stacking ensemble learning algorithm is based on massive data, using stacking ensemble learning algorithm to establish spatio-temporal data prediction model, avoiding the tedious statistical modeling process of spatio-temporal data in the past, which improves the efficiency of spatio-temporal data modeling, at the same time, the spatio-temporal data prediction modelbased on stacking ensemble learning algorithm needs less sample data, lower time complexity, the results of the model being not 'black box', the stacking spatio-temporal data modeling technology of the invention takes into account the characteristics of processing time, spatial characteristics, dynamic and static characteristics, and realizes the secondary processing generation of the characteristics through the stacking method, so that the training effect of the whole model is improved; the prediction efficiency of the spatio-temporal data is greatly improved. Thus, the prediction accuracy ofspatio-temporal data can be greatly improved, which is suitable for popularizing and applying in the field of data processing technology.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a spatio-temporal data prediction method based on a stacking integrated learning algorithm. Background technique [0002] Spatio-temporal data is data that has both time and space dimensions, and more than 80% of data in the real world is related to geographic location. As the world becomes instrumented and interconnected, spatiotemporal data are more pervasive and abundant than ever before, and capturing complex patterns in spatiotemporal data through spatiotemporal data prediction techniques has become more important and urgent for spatiotemporal data research applications . [0003] Trajectories of moving objects (such as taxis) recorded by GPS devices, social events (such as Weibo, crimes) and environmental monitoring with location markers and time stamps are typical spatio-temporal data. These emerging spatio-temporal data also bring new challenges and opportunitie...

AI Technical Summary

Problems solved by technology

However, the deep network is often a "black box", and the modeling time and space complexity is large, and requires a large number of training samples, and the ability to express uncertainty in spatiotemporal data is weak