Skip to main content

Table 4 Results for datasets 2, 3, and 4 by running experiments on hicloud

From: Designing a parallel evolutionary algorithm for inferring gene networks on the cloud computing environment

  Algorithm Sequential Sequential Parallel
   GA-PSO iGA-PSO iGA-PSO
50 genes (dataset 2) Master / Slaves 1 / 0 1 / 0 1 / 20 1 / 30
  Time cost (mins) 3019 2898 591 465
  Speed-up - 1 4.9036 6.2323
  Fitness value per gene 0.2345 0.2115 0.2140 0.2076
100 genes (dataset 3) Master / Slaves 1 / 0 1 / 0 1 / 20 1 / 30
  Time cost (mins) 11342 10284 1526 1316
  Speed-up - 1 6.7392 7.8146
  Fitness value per gene 0.3843 0.3520 0.3642 0.3582
125 genes (dataset 4) Master / Slaves 1 / 0 1 / 0 1 / 20 1 / 30
  Time cost (mins) 18019 16323 2152 1792
  Speed-up - 1 7.5850 9.1088
  Fitness value per gene 0.2358 0.2056 0.2195 0.2195