Table 1.
Summary of some BA-based and PSO-based hybrid techniques.
| Ref. | Technique | Hybridization methodology | Application |
|---|---|---|---|
| (Issa et al., 2018) | ASCA-PSO* | PSO exploits the regions around solutions found by SCA | LCCS between biological sequences |
| (Issa & Abd Elaziz, 2020) | IMO-PSO* | IMO starts exploring the search space then PSO refines the found solutions (exploitation phase) | LCCS between biological sequences |
| (Shehab et al., 2019) | BA-CSA | BA update procedure is applied to agents of CSA where new solutions survive if fitness improves | Global numerical optimization |
| (Yildizdan & Baykan, 2020) | BA-DE | The population is updated randomly using improved BA or DE mechanism to improve both exploration and exploitation | Global numerical optimization |
| (Manoj et al., 2016) | BA-PSO | PSO operators are applied to BA solutions in the exploitation phase | ANN training for Enhancement of image registration process of the diagnosis of medical images |
| (Ferdowsi et al., 2019) | BA-PSO | Swap and update mechanism is applied where best solutions of one algorithm replace worst solutions in the other one | Design of the labyrinth spillway geometry |
| (Yadav et al., 2015) | BA-PSO | Non satisfied solutions in the PSO population are updated using BA operators | Location of unified power flow controller in power systems |
| (Abd-Elazim & Ali, 2013) | PSO-BFA | PSO is applied as a mutation operator for BFA individuals | Design of power systems stabilizers in multimachine power systems |
| (Shen et al., 2008) | PSO-TS | TS works as a local improvement procedure for PSO solutions | Tumor classification using gene expression data |
| (Jiang et al., 2014) | PSO-GSA | Each updates its position with the contribution of both algorithms (co-evolutionary technique) | Economic emission load dispatch problems |
| (Dao et al., 2020) | BA-ALO | Updating operators of ALO were embedded into the updating equations of BA | Global numerical optimization |
| (Neto et al., 2019) | BA-LBBA | One of many micro-bats is assigned as a leader instead of only one best solution to influence the other agents of LBBA | The mobile robot localization problem |
| (Garg, 2016) | PSO-GA | Balancing exploration and exploitation is achieved via incorporating the crossover and mutation operators within PSO | Solving constrained optimization problems |
*Studies which implement the FLAT technique.