Calibrating Path Choices and Train Capacities for Urban Rail Transit Simulation Models Using Smart Card and Train Movement Data

Table 1

Algorithms’ summary.

Type	Algorithm	Constraints	Stochastic	Source
Heuristic method	Genetic algorithm (GA)	Yes	Yes	Fortin et al. [19]
	Simulated annealing (SA)	Yes	Yes	Tsallis and Stariolo [20]
Direct search	Nelder–Mead simplex algorithm (NMSA)	No	No	Gao and Han [21]
	Mesh adaptive direct search (MADS)	Yes	Yes	Abramson et al. [22]
Gradient-based	Simultaneous perturbation	Yes	Yes	Spall et al. [23]
	Stochastic approximation (SPSA)
Response surface	Bayesian optimization (BYO)	Yes	Yes	Snoek et al. [24]
	Constrained optimization using	Yes	Yes	Regis and Shoemaker [25]
	Response surfaces (CORS)