A comparative study of heuristic algorithms: GA and UMDA in spatially multiplexed communication systems

  • Authors:
  • Sajid Bashir;Muhammad Naeem;Syed Ismail Shah

  • Affiliations:
  • Center for Advanced Studies in Engineering, Islamabad, Pakistan;Simon Fraser University, Burnaby, Canada;Iqra University Islamabad Campus, H-9, Islamabad, Pakistan

  • Venue:
  • Engineering Applications of Artificial Intelligence
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

A performance comparison of genetic algorithm (GA) and the univariate marginal distribution algorithm (UMDA) as decoders in multiple input multiple output (MIMO) communication system is presented in this paper. While the optimal maximum likelihood (ML) decoder using an exhaustive search method is prohibitively complex, simulation results show that the GA and UMDA optimized MIMO detection algorithms result in near optimal bit error rate (BER) performance with significantly reduced computational complexity. The results also suggest that the heuristic based MIMO detection outperforms the vertical bell labs layered space time (VBLAST) detector without severely increasing the detection complexity. The performance of UMDA is found to be superior to that of GA in terms of computational complexity and the BER performance.