Improving n-Similarity Problem by Genetic Algorithm and Its Application in Text Document Resemblance

In this paper, some methods of similarity measures between objects are presented with their properties reviewed. The study is conducted to propose a new method based on genetic algorithm in order to reduce the time complexity of finding n most similar objects among the huge number of objects. This method is tested on two applications. The former aims at finding the most similar residents in a condominium, and the latter deals with finding the most similar n-groups of text documents out of a great dataset. The simulation results show that the proposed method can efficiently improve the order of time complexity especially for the second application.