Skip to main content

Table 4 J values and computational time of the global optimization methods for Case Study 2, including the results for the noise-free and noisy data.

From: Biochemical systems identification by a random drift particle swarm optimization approach

Results for the Experiments with Noise-free Data

Algorithms

RDPSO

SS method

( μ, λ )-ES

PSO

DE

( μ + λ )-ES

Best Value of J

0.009124

7.1358e-07

0.022858

7.140163

10.168989

0.123209

Mean Value of J

0.178881

3.4.274e-06

0.736311

10.3859

17.701876

2.141820

Standard Deviation of J

0.252749

1.3649e-06

0.960729

3.1927

4.112377

1.692726

CPU time(h)

52.4

--

54.9

49.2

53.8

53.3

Results for the Experiments with Noisy Data

Algorithms

RDPSO

SS method

( μ , λ )-ES

PSO

DE

( μ + λ )-ES

Best Value of J

0.2313

0.2337

2.5957

7.7433

11.7900

5.1490

Mean Value of J

0.3459

0.3106

3.6029

11.2353

18.5928

10.8691

Standard Deviation of J

0.1268

0.1325

0.1730

3.2921

3.3616

3.7065

CPU time(h)

52.4

--

54.9

49.2

53.8

53.3