Table 1 Summary of comparative algorithms used in this study.
From: A hybrid Harris Hawks Optimization with Support Vector Regression for air quality forecasting
Algorithm | Principle | Strengths and Limitations |
|---|---|---|
HHO | Inspired by the predatory behavior of hawks using Levy flight and soft-hard besiege strategies | Strong exploration capabilities but requires careful parameter tuning to balance search efficiency |
GWO | Mimics the social hierarchy and hunting strategies of grey wolves | Simple to implement, with effective convergence, but prone to stagnation in complex search spaces |
WOA | Based on the bubble-net hunting behavior of humpback whales | Excels in exploration, but lacks diversity in the exploitation phase, reducing solution refinement |
SSA | Models the swarming behavior of salps in the ocean | Efficient for smaller-scale problems, but convergence becomes slower for high-dimensional or complex functions |
BMO | Simulates the mating behavior of barnacles | High diversity and global search ability but computationally expensive, particularly for large-scale problems |
HGSO | Derives from Henry’s law and gas solubility in liquids | Demonstrates strong convergence properties, but performance may depend on initial population quality |
MRFO | Inspired by the foraging strategies of manta rays | Effectively balances exploration and exploitation, making it robust across various optimization problems |
EO | Physics-based model utilizing dynamic mass balance and equilibrium states | Combines robust exploration and exploitation, highly competitive in benchmark functions, but sensitive to parameter tuning and slightly less effective in composite functions |
