Catálogo de publicaciones - libros

Most real life applications have huge search spaces. Evolutionary Computation provides an advantage in the form of parallel explorations of many parts of the search space. In this report, Genetic Programming is the technique we used to search for good melodic fragments. It is generally accepted that knowledge is a crucial factor to guide search. Here, we show that SOM can be used to facilitate the encoding of domain knowledge into the system. The SOM was trained with music of desired quality and was used as fitness functions. In this work, we are not interested in music with complex rules but with simple music employed in computer games. We argue that this technique provides a flexible and adaptive means to capture the domain knowledge in the system.

This paper describes an automated computer improviser which attempts to follow and improvise against the frequencies and timbres found in an incoming audio stream. The improviser is controlled by an ever changing set of sequences which are generated by analysing the incoming audio stream (which may be a feed from a live musician) for its physical and musical properties such as pitch and amplitude. Control data from these sequences is passed to the synthesis engine where it is used to configure sonic events. These sonic events are generated using sound synthesis algorithms designed by an unsupervised genetic algorithm where the fitness function compares snapshots of the incoming audio to snapshots of the audio output of the evolving synthesizers in the spectral domain in order to drive the population to match the incoming sounds. The sound generating performance system and sound designing evolutionary system operate in real time in parallel to produce an interactive stream of synthesised sound. An overview of related systems is provided, this system is described then some preliminary results are presented.

Research on the application of Interactive Evolutionary Computation(IEC) to the field of musical computation has been improved in recent years, marking an interesting parallel to the current trend of applying human characteristics or sensitivities to computer systems. However, past techniques developed for IEC-based composition have not necessarily proven very effective for professional use. This is due to the large difference between data representation used by IEC and authored classical music composition. To solve this difficulties, we purpose a new IEC approach to music composition based on classical music theory. In this paper, we describe an established system according to the above idea, and detail of making success of composition a piece.

The work concerns using evolutionary methods to evolve melodic sequences, obtained through a music generative approach from Chua’s circuit, a non-linear dynamic system, universal paradigm for studying chaos. The main idea was to investigate how to turn potential aesthetical musical forms, generated by chaotic attractors, in melodic patterns, according to the western musical tradition. A single attractor was chosen from the extended gallery of the Chua’s dynamical systems. A specific codification scheme was used to map the attractor’s space of phases into the musical pitch domain. A genetic algorithm was used to search throughout all possible solutions in the space of the attractor’s parameters. Musical patterns were selected by a suitable fitness function. Experimental data show a progressive increase of the fitness values.

Music pieces have been composed using a behavior-inspired evolutionary algorithm, harmony search (HS). The HS algorithm mimics behaviors of music players in an improvisation process, where each player produces a pitch based on one of three operations (random selection, memory consideration, and pitch adjustment) in order to find a better state of harmony which can be translated into a solution vector in the optimization process. When HS was applied to the organum (an early form of polyphonic music) composition, it could successfully compose harmony lines based on original Gregorian chant lines.

This paper introduces a new evolutionary model of the art and design process. The whole process of interactive image creating was decomposed into three steps: evolving the Bezier curve, evolving the geometric transformations of the curve, and evolving the style of painting it. A model was implemented, and a series of promising experiments was performed.

This paper presents an approach to new method for music composition with multi-agent system, which is a field of new research and offers vast possibilities for both scientific research and artistic expression. Proposed model is an ecological approach in which the agents coexist in a virtual world displaying predator/prey behavior. It realizes self-organization of sound structure and real-time performance with laptop PC. The demo movies, including all reference movies in section 3 are available on the Web (http://www.dubdb.com/gismo/ evo/). Please refer to them for agents’ behaviors and sounds.

When dealing with dynamic environments two major aspects must be considered in order to improve the algorithms’ adaptability to changes: diversity and memory. In this paper we propose and study a new evolutionary algorithm that combines two populations, one playing the role of memory, with a biological inspired recombination operator to promote and maintain diversity. The size of the memory mechanism may vary along time. The size of the (usual) search population may also change in such a way that the sum of the individuals in the two populations does not exceed an established limit. The two populations have minimum and maximum sizes allowed that change according to the stage of the evolutionary process: if an alteration is detected in the environment, the search population increases its size in order to readapt quickly to the new conditions. When it is time to update memory, its size is increased if necessary. A genetic operator, inspired by the biological process of conjugation, is proposed and combined with this memory scheme. Our ideas were tested under different dynamics and compared with other approaches on two benchmark problems. The obtained results show the efficacy, efficiency and robustness of the investigated algorithm.

Addressing dynamic optimization problems has been a challenging task for the genetic algorithm community. Over the years, several approaches have been developed into genetic algorithms to enhance their performance in dynamic environments. One major approach is to maintain the diversity of the population, e.g., via random immigrants. This paper proposes an elitism-based immigrants scheme for genetic algorithms in dynamic environments. In the scheme, the elite from previous generation is used as the base to create immigrants via mutation to replace the worst individuals in the current population. This way, the introduced immigrants are more adapted to the changing environment. This paper also proposes a hybrid scheme that combines the elitism-based immigrants scheme with traditional random immigrants scheme to deal with significant changes. The experimental results show that the proposed elitism-based and hybrid immigrants schemes efficiently improve the performance of genetic algorithms in dynamic environments.

In recent years, there has been an increasing concern from the evolutionary computation community on dynamic optimization problems since many real-world optimization problems are time-varying. In this paper, a triggered memory scheme is introduced into the particle swarm optimization to deal with dynamic environments. The triggered memory scheme enhances traditional memory scheme with a triggered memory generator. Experimental study over a benchmark dynamic problem shows that the triggered memory-based particle swarm optimization algorithm has stronger robustness and adaptability than traditional particle swarm optimization algorithms, both with and without traditional memory scheme, for dynamic optimization problems.