An Interactive Knowledge-based Multi-objective Evolutionary Algorithm Framework for Practical Optimization Problems

Experienced users often have useful knowledge and intuition in solving real-world optimization problems. User can be formulated as inter-variable relationships to assist an algorithm finding good solutions faster. Such interactions also automatically learned from high-performing discovered at intermediate iterations run – a process called innovization. These relations, if vetted by the users, enforced among newly generated steer towards practically promising regions search space. Challenges arise for large-scale problems where number of such variable may high. This paper proposes interactive knowledge-based evolutionary multi-objective () framework that extracts hidden variable-wise evolving solutions, shares them with receive feedback, applies back improve its effectiveness. The extraction uses systematic elegant graph analysis method which scales well variables. working proposed is demonstrated on three engineering design simplicity elegance achievement quickly indicate power framework. results presented should motivate further interaction-based studies their routine use practice.