Neural Networks with Improved Extreme Learning Machine for Demand Prediction of Bike-sharing

Abstract Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost scheduling and improving user satisfaction. However, it a challenging issue due stochasticity non-linearity in systems. In this paper, model called pseudo-double hidden layer feedforward neural networks proposed approximately predict actual demands bike-sharing. Specifically, overcome limitations traditional back-propagation learning process, algorithm, extreme machine with improved particle swarm optimization, designed construct rules networks. The performance verified by comparing other algorithms on dataset Streeter Dr station Chicago.