Toward Modeling the Intrinsic Complexity of Test Problems

Abstract

The concept of intrinsic complexity explains why different problems of the same type, tackled by the same problem solver, can require different times to solve and yield solutions of different quality. This paper proposes a general four-step approach that can be used to establish a model for the intrinsic complexity of a problem class in terms of solving time. Such a model allows prediction of the time to solve new problems in the same class and helps instructors develop more reliable test problems. A complexity model, furthermore, enhances understanding of the problem and can point to new aspects interesting for education and research. Students can use complexity models to assess and improve their learning level. The approach is explained using the K-map minimization problem as a case study. The implications of this research for other problems in electrical and computer engineering education are highlighted. An important aim of this paper is to stimulate future research in this area. An ideal outcome of such research is to provide complexity models for many, or even all, relevant problem classes in various electrical and computer engineering courses.