A Genetic Algorithm (GA) is a population-based metaheuristic optimization technique inspired by biological evolution, which iteratively applies selection, crossover, and mutation operators to a set of candidate solutions in order to converge toward optimal or near-optimal parameter configurations. In the context of WiFi/CSI sensing and crowd modeling research, GAs are particularly valuable for calibrating complex agent-based and data-driven models where the parameter search space is high-dimensional and gradient-based methods are intractable. Key variants include standard GAs operating on binary or real-valued encodings, multi-objective GAs such as NSGA-II for simultaneously optimizing competing objectives, and hybrid approaches that combine GAs with local search or other machine learning methods to improve convergence speed and solution quality.

Source Papers

  • A crowd team evacuation model considering spring effect — A crowd team evacuation model considering spring effect
  • Data Assimilation for Agent-Based Models — Data Assimilation for Agent-Based Models
  • Data-driven Crowd Modeling Techniques: A Survey — Data-driven Crowd Modeling Techniques: A Survey
  • Efficient Adaptive Beacon Deployment Optimization for Indoor Crowd Monitoring Applications — Efficient Adaptive Beacon Deployment Optimization for Indoor
  • Parameter estimation and comparative evaluation of crowd simulations — Parameter estimation and comparative evaluation of crowd sim
  • Social force models for pedestrian traffic – state of the art — Social force models for pedestrian traffic – state of the ar