Hybrid PSO-GA Metaheuristic Optimization for Comprehensive Student Performance Enhancement

<ns3:p>Students aim for well-rounded performance, and higher education institutions strive to support them. While written tests assess academic achievement, they do not fully capture skills like critical thinking, creativity, public speaking, and physical fitness. The proposed paper suggests a holistic optimization model involving a Hybrid PSO-GA (Particle Swarm Optimization - Genetic Algorithm) metaheuristic algorithm that would generate a more holistic student assessment platform that constitutes a fitness function that would evaluate students not only on exams but also on academic, co-curricular and extracurricular facets. The model formulates a constrained optimization problem where cognitive effort allocation is optimized under individual workload limits derived from factors such as cognitive capacity, time availability, fatigue, and task complexity. Proposed model evaluated in C++ and analyzed statistically in Python across three setups with population sizes of 25, 50, and 100, and up to 200 iterations. A previous survey-based study was considered in formulating datasets, and normalized cognitive workload scores were applied to five categories of tasks. The hybrid algorithm outperformed standalone Genetic Algorithm and Particle Swarm Optimization methods, achieving the highest mean fitness of 1.273 and the lowest standard deviation of 0.004. Statistical significance was confirmed using the Friedman and Nemenyi tests with p-values less than 0.0001, demonstrating the robustness and superior convergence of the hybrid model. The proposed approach provides a computationally intelligent and statistically robust framework for holistic student performance assessment, with implications for adaptive academic workload management and policy-driven educational enhancement.</ns3:p>