Management of traffic congestion in adaptive traffic signals using a novel classification-based approach

ABSTRACT

Traffic congestion is a critical problem which makes roads busy. Traffic congestion challenges traffic flow in urban areas. A growing urban area creates complex traffic problems in daily life. Congestion phenomena cannot be resolved only by applying physical constructs such as building bridges and motorways and increasing road capacity. It is necessary to build technological systems for transportation management to control the traffic phenomenon. In this article, a new idea is proposed to tackle traffic congestion with the aid of machine learning approaches. A new strategy based on a tree-like configuration (i.e. a decision-making model) is suggested to handle traffic congestion at intersections using adaptive traffic signals. Different traffic networks with different sizes, varying from nine to 400 intersections, are examined. Numerical results and discussion are presented to prove the efficiency and application of the proposed strategy to alleviate traffic congestion.

KEYWORDS:

• Traffic signal scheduling
• traffic congestion
• classification
• support vector machine
• extreme learning machine

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research is supported by the NTU-NXP Intelligent Transport System Test-Bed Living Lab Fund [S15-1105-RF-LLF] from the Economic Development Board, Singapore.