Spatiotemporal Traffic Analysis using Big Data

Anandakumar H,Abishek Sailesh,Visalakshi S,Muthumani K,Muthumeenal C

doi:10.46532/ijaict-2020010

Abstract

In collaborated online technique traffic prediction methods is proposed with distributed context aware random forest learning algorithm .The random forest is ensemble classifier which learns different traffic and context model form distributed traffic patterns. One major challenge in predicting traffic is how much to rely on the prediction model constructed using historical data in the real-time traffic situation, which may differ from that of the historical data due to the fact that traffic situations are numerous and changing over time. The proposed algorithm is online predictor of real-time traffic, the global prediction is achieved with less convergence time .The distributed scenarios (traffic data and context data) are collected together to improve the learning accuracy of classifier. The conducted experimental results on prediction of traffic dataset prove that the proposed algorithm significantly outperforms the existing algorithm.

Highlights

Big data is data that exceeds the processing capacity of conventional database systems
K-Means Clustering is a method of vector quantization, originally from signal processing, that is popular for cluster analysis in data mining. k-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster
The existing approaches for traffic prediction aim at predicting traffic in specific traffic situations, e.g. either typical conditions or when accidents occur the existing approaches used for traffic prediction deploy models learned offline or they are retrained after long periods and they cannot adapt to dynamically changing traffic situations

Summary

Muthumeenal UG Scholar

Abstract - In collaborated online technique traffic prediction methods is proposed with distributed context aware random forest learning algorithm .The random forest is ensemble classifier which learns different traffic and context model form distributed traffic patterns. One major challenge in predicting traffic is how much to rely on the prediction model constructed using historical data in the real-time traffic situation, which may differ from that of the historical data due to the fact that traffic situations are numerous and changing over time. The proposed algorithm is online predictor of real-time traffic, the global prediction is achieved with less convergence time .The distributed scenarios (traffic data and context data) are collected together to improve the learning accuracy of classifier. The emergence of big data [3] into the enterprise brings with it a necessary counterpart: agility.

INTRODUCTION

PROPOSED WORK

CONCLUSION