Multi-Objective Transport System Based on Regression Analysis and Genetic Algorithm Using Transport Data

Abstract

Intelligent transportation system (ITS) is a cutting-edge traffic solution employing state-of-the-art information and communication technologies. Optimized bus-scheduling, being an integral part of ITS, ensures safety, efficiency, traffic congestion-reduction, passengers' forecast, resource allocation, and drivers' experience enhancement. Nevertheless, of its significance, recent years have witnessed limited research carried out in this context. In this paper, we apply a uni-variate multi-linear regression over the past three years of data from a renowned bus company and forecasted potential passengers for different days in a week. Moreover, a minimum number of different types of buses have been calculated, and bus optimization has been performed in a genetic algorithm. The results of accurateness has been validated by using mean absolute deviation (MAD) and mean absolute percentage error (MAPE). The values of MAD (99.14) and MAPE (8.7%) advocate that the results are quite rational.