AN ADAPTIVE DECISION AID FOR REAL ENVIRONMENTS

Decision making in the real world is concerned with both deterministic models and undeterministic human expertise, However, both current dec ision-making methods use either mathematical programming or heuristic rules; each approach by itself loses the other piece of information, T his paper proposes a new approach to integrate these two different typ es of information simultaneously and adaptively. It uses fuzzy mathema tical programming to quantitatively model objectives and resource cons traints, and a linguistic knowledge base to qualitatively model imprec ise human expertise. The coordination between these two modules and th e new idea of subjective knowledge adaptation for human-in-the-loop sy stems are discussed in detail.