Towards developing an intelligent system to suggest optimal path based on historic and real-time traffic data
- 1 December 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Traffic congestion is a common scenario in the metropolitan areas specially in developing countries like Bangladesh where people lose valuable time of their busy schedule by getting trapped in heavy traffic. Moreover, reliable traffic congestion avoidance or prediction mechanism for providing real-time traffic jam information and route selection is not up to the mark in Bangladesh. In this paper, we have proposed an intelligent system with a cost function using Ant Colony Optimization (ACO) and a meta-heuristic approach, which will calculate optimal paths of lowest travel cost considering both historic and real time traffic data and different time windows of a day. It will also dynamically re-route the path in case of heavy congestion during travel time for avoiding unusual situations. Experimental results show that the designed algorithm of the proposed system performs accordingly with reliable realtime traffic prediction and it's suggested routes provide better navigation and may save valuable time.Keywords
This publication has 15 references indexed in Scilit:
- Solving the Selective Pickup and Delivery Problem Using Max-Min Ant System2017
- An improved formulation for the multi-depot open vehicle routing problemOR Spectrum, 2015
- Dynamic Travel Path Optimization System Using Ant Colony Optimization2014
- Pickup and delivery problem using metaheuristics techniquesExpert Systems with Applications, 2012
- Ant Colony Optimization for traffic dispersion routing2010
- Travel time prediction for dynamic routing using Ant Based Control2009
- Sensor network for real-time vehicle tracking on road networks2009
- Avoiding Traffic Jam Using Ant Colony Optimization - A Novel Approach2007
- Ant colony optimizationIEEE Computational Intelligence Magazine, 2006
- Prediction of Road Traffic using a Neural Network ApproachNeural Computing and Applications, 1999