Search space modulation in genetic algorithms: evolving the search space by sinusoidal transformations

An experimental form of Modulation (Reinterpretation) of the Search Space is presented. This modulation is developed as a mathematical method that can be implemented directly into existing evolutionary algorithms without writing special operators, changing the program loop etc. The main mathematical principle behind this method is the dynamic sinusoidal envelope of the search space. This method is presented in order to solve some theoretical and practical issues in evolutionary algorithms like numerical bounded variables, dynamic focalized search, dynamic control of diversity, feasible region analysis etc. Categories and Subject Descriptors: I.2.8 [Computing Methodologies][Artificial Intelligence]: Problem Solving, Control Methods, and Search General Terms: Algorithms, Theory

• Type: Conference
• Year: 2005
• Where: GECCO
• Authors: José Antonio Martin H.
• Keywords: Dynamic Sinusoidal Envelope, Evolutionary Algorithms, GECCO 2005, Search Space