A new hybrid simulated Kalman filter and particle swarm optimization for continuous numerical optimization problems

Badaruddin Muhammad, Zuwairie Ibrahim, Kamarul Hawari Ghazali, Kamil Zakwan Mohd Azmi, Nor Azlina Ab Aziz, Nor Hidayati Abd Aziz, Mohd Saberi Mohamad

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)


Inspired by the estimation capability of Kalman filter, we have recently introduced a novel population-based optimization algorithm called simulated Kalman filter (SKF). Every agent in SKF is regarded as a Kalman filter. Based on the mechanism of Kalman filtering, which includes prediction, measurement, and estimation, the global minimum/maximum can be estimated. Measurement process, which is required in Kalman filtering, is mathematically modelled and simulated. Agents communicate among them to update and improve the solution during the search process. Inspired by the bird flocking, particle swarm optimization (PSO) has been introduced in 1994. In PSO, a swarm of agent search the global minimum/maximum by velocity and position updates, which are influenced by current position of agent, current position of agent, personal best, and global best of the swarm. In this research, SKF and PSO are hybridized in such a way that PSO is employed as prediction operator in SKF. The performance of the proposed hybrid SKF-PSO algorithm (SKF-PSO) is compared against SKF and PSO using CEC2014 benchmark dataset for continuous numerical optimization problems. Based on the analysis of experimental results, we found that the proposed hybrid SKF-PSO is superior to both SKF and PSO algorithm.

Original languageEnglish
Pages (from-to)17171-17176
Number of pages6
JournalARPN Journal of Engineering and Applied Sciences
Issue number22
Publication statusPublished - 2015
Externally publishedYes


  • cec2014 benchmark problem
  • Optimization
  • Particle swarm
  • Simulated kalman filter

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'A new hybrid simulated Kalman filter and particle swarm optimization for continuous numerical optimization problems'. Together they form a unique fingerprint.

Cite this