Genetic Algorithm for Adaptable Design using Crowdsourced Learning as Fitness Measure

This paper discusses the implementation and testing of a creative web element design system using an interactive genetic algorithm. Feedback in the form of voting will be used as a learning mechanism to give the system the ability to absorb quality measures in the domain of visual aesthetics. The crowdsourcing defines the learning basis for a K-NN algorithm. The K-NN machine learning is used to classify and evaluate generated designs based on feedback. This is incorporated into the fitness function of the genetic algorithm to breed the best possible design that suits the crowd. The method and the results of the implementation are described.