An interactive genetic algorithm-based framework for handling qualitative criteria in design optimization

Consideration of qualitative factors is an integral and necessary part of design optimization. In this paper, we consider qualitative factors as design objectives to be optimized and attempt to optimize qualitative and quantitative criteria together. Interactive evolutionary computation (IEC) provides an ideal platform to include qualitative perspectives of the designer for the optimization of a design. This paper reviews the inclusion of qualitativeness in design, makes the case for its necessity, and classifies qualitative concepts in design optimization, before moving onto a comparison between sequential single objective and multi-objective optimization with regards to simultaneous handling of qualitative and quantitative criteria. The manufacturing plant layout design problem is used as an illustrative example. We further examine the enrichment of the optimization methods by allowing human interaction with the program within the framework of IEC. The multi-objective platform is found to be superior. Finally various challenges, such as the influence of human fatigue, are discussed.