Catálogo de publicaciones - libros

We propose an interactive computer graphics authoring method based on interactive evolutionary computation (IEC). Previous systems mainly employed genetic algorithm (GA) to explore an optimum set of 3D graphics parameters. The proposed method adopts a different computation model called immune algorithm (IA) to ease the creation of varied 3D models even if a user doesn’t have any specific idea of final 3D products. Because artistic work like graphics design needs a process to diversify the user’s imagery, a tool that can show the user a broad range of solutions is particularly important. IA enables to effectively explore a global optimum solution as well as other multiple quasi-optimum solutions in a huge search space by using its essential mechanisms such as antibody formation and self-regulating function.

In this essay the construction of an interactive genetic algorithm and agents based application will be described. This construction is driven to plan the development of a human mosaic, starting from an initial design and an adjustment of several parameters. In addition, the same idea of generation will be show as suitable to be applied to character group movements inside a videogame. The software developed is enclosed, as far as the “creative” part of the solution is concerned, inside the evolutionary computation paradigm; while into agent orientation regarding characters coordination.

We present a time domain approach to explore a sound transformation paradigm for musical performance. Given a set of sounds containing desired qualities and a population of agents interacting locally, the method generates both musical form and matter resulting from sonic trajectories. This proposal involves the use of bio-inspired algorithms, which possess intrinsic features of adaptive, self-organizing systems, as definers of generating and structuring processes of sound elements. Self-organization makes viable the temporal emergence of stable structures without an external organizing element. Regarding musical performance as a creative process that can be described using trajectories through the compositional space, and having the simultaneous emergence of musical matter and form resulting from the process itself as the final objective, the conception of a generative paradigm in computer music that does not contemplate external organizing elements is the main focus of this proposal.

In this paper we introduce an hybrid evolutionary algorithm for computer-aided orchestration. Our current approach to orchestration consists in replicating a target sound with a set of instruments sound samples. We show how the orchestration problem can be viewed as a multi-objective 0/1 knapsack problem, with additional constraints and a case-specific criteria formulation. Our search method hybridizes genetic search and local search, for both of which we define ad-hoc genetic and neighborhood operators. A simple modelling of sound combinations is used to create two new mutation operators for genetic search, while a preliminary clustering procedure allows for the computation of sound mixtures neighborhoods for the local search phase. We also show in which way user interaction might be introduced in the orchestration procedure itself, and how to lead the search according to the users choices.

Photomosaics are images composed of smaller images (tiles). Viewed close up the details of the tiles are evident and the big picture is lost. Viewed from a distance the detail of the tiles is lost and the big picture is evident. We show how photomosaics can be generated by evolutionary search and how animations can be created by using the best individuals in a generation as frames of a movie. The animations can generate engaging visual effects such as gradually ‘materialising’ a face from a random arrangement of tiles on a screen. Our animations explore self representation through dynamic reinterpretations of mosaic and iconography traditions using target images and tiles that we created.

This paper outlines a current lack of consideration for the environmental context of Evolutionary Algorithms used for the generation of music. We attempt to readdress this balance by outlining the benefits of developing strong coupling strategies between agent and environment. It goes on to discuss the relationship between artistic process and the viewer and suggests a placement of the viewer and agent in a shared environmental context to facilitate understanding of the artistic process and a feeling of participation in the work. The paper then goes on to outline the installation ‘Excuse MeÕ and how it attempts to achieve a level of Sonic Ecology through the use of a shared environmental context.

A new way to control sound spatial dispersion using the ESSynth Method is introduced here. The Interaural Time Difference (ITD) is used as genotype of an evolutionary control of sound spatialization. Sound intensity and the ITD azimuth angle are used to define spatial dispersion and spatial similarity. Experimental results where crossover and mutation rates were used to create spatial sonic trajectories are discussed.

We present several practical improvements to the interactive evolution of 2D images, some of which are also applicable to more general genetic programming problems. We introduce tree alignments to improve the animation of evolved images when using genetic cross dissolves. The goal of these improvements is to strengthen the interactive evolution toolset and give the artist greater control and expressive power.

This paper presents an approximation towards an evolutionary generator of alliterative text. A simple text is given along with the preferred phoneme for alliterations as input. Then the evolutionary algorithm (with the aid of a phonemic transcriber, Microsoft Word and Google) will try to produce an alternative sentence while trying to preserve the initial meaning and coherence. A bigram language model and the evaluation of the phonetic analysis are used to assess the fitness of the sentences.

This paper describes an experiment carried out to determine which, among several possible evolutionary and non-evolutionary sound synthesizer graphical user interfaces, is the most suitable for the task of matching a target sound. Results show that standard and new varieties of evolutionary interface are competitive with a standard non-evolutionary interface, achieving better results in some situations and worse in others. Subjects’ comments suggest a preference for a new type of evolutionary interface, presented here, which allows faster audition of the population, avoiding the need for time-consuming fitness evaluation of poor-quality sounds.