Bus Passenger Volume Forecasting Based on Hybrid Quantum Swarm Intelligence

Accurate forecasting of bus passenger volume is essential for optimizing public transit operations and promoting low-carbon urban mobility. This study examines Hybrid Quantum Swarm Intelligence (HQSI), combining quantum neural networks (QNNs) with swarm-based optimization algorithms-Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)-to improve short-term bus passenger volume prediction. Using comprehensive 2024 smart card data from Keelung City focusing on Route 501, this study compares HQSI models with classical deep learning baselines (LSTM and GRU with ADAM) and QNNs optimized via Constrained Optimization BY Linear Approximation (COBYLA) and Simultaneous Perturbation Stochastic Approximation (SPSA). Experimental results demonstrate that the HQSI method QNN+PSO achieves the best performance, with a mean absolute error (MAE) of 309.07 and mean absolute percentage error (MAPE) of 6.37%, surpassing LSTM+ADAM (MAPE: 8.13%) and GRU+ADAM (MAPE: $\mathbf{8. 6 1 \%}$). These findings validate the efficacy of HQSI for enhancing the accuracy of transit demand forecasting, contributing to data-driven and sustainable public transport planning.