Open Access
Review
Table 2
Performance analysis of various hybrid AI techniques.
| Attributes | Hybrid-AI optimization techniques |
|||
|---|---|---|---|---|
| FNN | ANFIS | PSO-ANN | PSO-GWO | |
| Influence | Combines human reasoning with neural learning. | Combines neural networks for learning and fuzzy logic for decision making. | Based on the social behavior of bird flocking and fish schooling. | Integrates the social hierarchy of wolves with exploratory strategies. |
| Convergence | Fast convergence, enabled by learning and adaptability. | Fast convergence is achieved through adaptive mechanisms. | Performance is moderate and influenced by initial parameter choices. | Rapidly balances exploration and exploitation. |
| Computational time | Moderate | Moderate | Low | Low to Moderate |
| Scalability | Highly adaptable to problems of different sizes and complexities. | Highly suitable for a wide range of applications with excellent scalability. | Suitable for medium-sized problems with limited scalability. | Highly scalable for large and complex problem domains. |
| Robustness | Strong resistance to environmental noise and uncertainties | Very high adaptability to fluctuating environments. | Highly capable of managing data and variations in parameters. | Very effective in handling varied conditions and scenarios. |
| Real-time hardware functionality | Good | Very Good | Average | Very Good |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.