Particle Swarm Optimization (PSO) is a population-based metaheuristic optimization algorithm inspired by the collective movement of biological swarms, where candidate solutions (particles) iteratively update their positions in the search space by balancing individual best-known positions with the global best-known position found across the swarm. In the context of IoT and crowd sensing research, PSO is valued for its ability to efficiently solve complex, high-dimensional optimization problems — such as parameter tuning, resource allocation, and motion model fitting — without requiring gradient information, making it well-suited for non-linear and non-convex problem spaces. Key variants include adaptive PSO, which dynamically adjusts inertia weights and acceleration coefficients to improve convergence, and hybrid PSO formulations that combine the algorithm with other techniques such as genetic algorithms or fuzzy logic to enhance solution quality and avoid premature convergence to local optima.
Source Papers
- A crowd team evacuation model considering spring effect ↗ — A crowd team evacuation model considering spring effect
- A survey on Internet of Things architectures ↗ — A survey on Internet of Things architectures
- Motion estimation of high density crowd using fluid dynamics ↗ — Motion estimation of high density crowd using fluid dynamics