Data Dependent Passenger Flow Prediction System using Support Vector Regression Algorithm
Abstract
The paper establishes the idea of solving the traffic congestion problem faced the passengers using daily inter-city short distance buses. As the problem undertaken in this paper is a regression type, the Support Vector Regression algorithm eradicates the problem most efficiently. When the predictions are compared with the real time traffic-load data, the results are highly promising .The results suggest that real-time crowding information can be provided sufficiently early to influence passenger’s route, bus and timing choices, in order to reduce in-vehicle crowding and time wastage.