Asynchronous distributed interactive genetic algorithm for creating music melody reflecting multiple users' feelings

Abstract

In the area of product design, it is important that adding user's feelings on the products for emphasizing its value. Interactive Evolutionary Computation (IEC) is known as a method that searches optimal or better media contents suited for each user's feelings. In terms of expanding the ability of IEC, some recent studies applied IEC into problem of multiple users. This study aims to create music melody suited for multiple users' feelings by employing parallel Distributed Interactive Genetic Algorithm (DIGA). In this method, each of the users proceeds general Interactive Genetic Algorithm (IGA) process by evaluating solution candidates subjectively. In some generations, solution candidates are exchanged between the users. With the exchange, each of the users is affected by other users' feelings. As a result of these processes, obtaining good solution suited for all users. We conducted listening experiments for investigating efficiency of the DIGA for creation of music melody. Ten persons participated in the experiment as subjects, and pair of the subjects participated in the IGA task simultaneously. Experimental results show that higher fitness was obtained in the final generation, and similar melody was obtained through exchange of solutions. To clarify the efficiency of the exchange of the asynchronous method, further study with comparing experiment including conditions synchronous is needed.