Users' Fuzzy Cognition Knowledge Learning in Interactive Evolutionary Computation and its Application

Abstract

user in interactive evolutionary computation (IEC) has the characteristic of fuzzy cognition. Based on this, a method to learn users’ fuzzy cognition knowledge is given. The method includes the fuzzy expression of the basic elements of IEC such as search space, population, gene sense unit and so on. Then a method to increase the performance of IEC based on the knowledge of users’ fuzzy cognition is given. The above results enrich the researches of IEC users' cognition.

Scheme of Big-Data Supported Interactive Evolutionary Computation

“…In the past years, many users and volunteers took part in IEC experiments or applications, and multi-dimensional preference evaluation data, including fuzzy type evaluation [5], accurately numeric type evaluation [6], rank type evaluation [7], eye-tracked evaluation [8], interval type evaluation [9], best-selection type evaluation [2] and so on, are stored. Label the set composed by these data as , where is the preference information about the user .…”

“…Those actively select solutions are located in search space and are embedded in the new population for the user's evaluation. With AL aided BD_IEC, there is: (5) where is the information that stored in big data as the set of users' preference. This means that the population is generated based on both evolutionary operators and TL aided BD.…”