Traffic Flow Prediction using Machine Learning Techniques - A Systematic Literature Review

Abstract

Purpose: Traffic control in large cities is extremely tough. To alleviate costs associated with traffic congestion, some nations of the world have implemented Intelligent Transportation Systems (ITS). This paper reviews the application of artificial neural network (ANN) and machine learning (ML) techniques and also their implementation issues in TFP. Techniques other than ML and ANN have also been discussed.

Methodology: The survey of literature on TFP (TFP) and ITS was conducted using several secondary sources of information such as conference proceedings Journals, Books, and Research Reports published in various publications, and then the kinds of literature that are reported as promising have been included. The collected information is then reviewed to discover possible key areas of concern in the TFP and ITS.

Findings/Results: Traffic management in cities is important for smooth traffic flow. TFP and ITS are drawing much attention from researchers these days. Application of ML, ANN, and other techniques are being tried to alleviate the traffic flow problem in cities. TFP using ITS employing ML techniques to overcome the problem of traffic congestion looks promising.

Originality: This review of literature is conducted using secondary data gathered from various sources. The information acquired will be useful to expand on existing theories and frameworks or to develop a new technique or modify to improve the accuracy of TFP. Tables containing categories of prediction, ML Pipelining, open-source ML tools available, standard datasets available have been included.

Paper Type: Literature Review.