Simulated annealing-based particle swarm optimisation with adaptive jump strategy for modelling of dynamic cerebral pressure autoregulation mechanism

摘要

This paper proposes a new particle swarm optimisation (PSO) algorithm based on simulated annealing (SA) with adaptive jump strategy to alleviate some of the limitations of the standard PSO algorithm. In this algorithm, swarm particles jump into the space to find new solutions. The jump radius is selected adaptively based on the particle velocity and its distance from the global best position. The designed algorithm has been tested on benchmark optimisation functions and on known autoregressive exogenous (ARX) model design problem. The results are superior as compared to the existing PSO methods. Finally, the designed algorithm has been applied for the analysis of the dynamic cerebral autoregulation mechanism.