Researchers at the University of Professional Studies, Accra conduct a bibliometric-scoping study on hybrid metaheuristic–machine learning and metaheuristic–metaheuristic algorithms published in 2024. They analyze 119 peer-reviewed papers via structured searches and manual classification, charting publication trends by country and journal. The review highlights India's leadership in metaheuristic hybrids, China's growth in ML integrations, and key applications in energy forecasting, industrial scheduling, and IoT security.
Key points
- PRISMA-guided bibliometric-scoping of 119 studies reveals 14 MH-ML and 105 MH-MH algorithm hybrids across global publications.
- India leads PSO-based MH-MH research with 46 studies focusing on energy forecasting, industrial scheduling, and urban logistics optimizations.
- MH-ML integrations, including Deep Q-Network-driven memetic algorithms and GNN-enhanced genetic algorithms, improve decision-making and convergence in IoT security and traffic modeling.
Why it matters: By mapping global hybrid AI-optimization research trends, this review guides targeted algorithmic innovation for efficient, adaptive energy and logistics solutions.
Q&A
- What are metaheuristics and hybrid AI algorithms?
- How does bibliometric-scoping and PRISMA screening work?
- Why is Particle Swarm Optimization dominant in MH-MH research?
- What advantages do MH-ML hybrids offer over standalone methods?
