Skip to main content

Table 3 Comparison of the number of online CST calls \(|\text{CC}_{\text{GPR-H}}^{\text{online}}|\) and effective calls \(|\text{EC}_{\text{GPR-H}}^{\text{online}}|\) for the GPR-Hybrid approach with different updating strategies

From: A blackbox yield estimation workflow with Gaussian process regression applied to the design of electromagnetic devices

  No sorting EGL criterion Hybrid criterion
  \(|\text{CC}_{\text{GPR-H}}^{\text{online}}|\) \(|\text{EC}_{\text{GPR-H}}^{\text{online}}|\) \(|\text{CC}_{\text{GPR-H}}^{\text{online}}|\) \(|\text{EC}_{\text{GPR-H}}^{\text{online}}|\) \(|\text{CC}_{\text{GPR-H}}^{\text{online}}|\) \(|\text{EC}_{\text{GPR-H}}^{\text{online}}|\)
\(N_{\text{B}}=1\) 320 320 269 269 254 254
\(N_{\text{B}}=20\) 352 18 299 15 288 15
\(N_{\text{B}}=50\) 378 8 339 7 326 7