Catálogo de publicaciones - libros

Temporal abstraction methods produce high level descriptions of a parameter evolution from collections of temporal data. As the level of abstraction of the data is increased, it becomes easier to use them in a reasoning process based on high-level explicit knowledge. Furthermore, the volume of data to be treated is reduced and, subsequently, the reasoning becomes more efficient. Besides, there exist domains, such as medicine, in which there is some imprecision when describing the temporal location of data, especially when they are based on subjective observations. In this work, we describe how the use of fuzzy temporal constraint networks enables temporal imprecision to be considered in temporal abstraction.

We describe a new software tool, called Spieldose (in English, musical box), suited to the automatic music composition task. Our system is based on the paradigm of Interactive Genetic Algorithms (abbreviated as Interactive GA) where the parent selection stage in a typical GA is made by the user according to his/her subjective criteria. The tool permits to integrate the interaction between the system and the potential users when they create their melodies. One important contribution of this work is the proposal of specific musical genetic operators (different types of crossover, mutation and improvement operators) which ensure that the generated melodies are in concordance with Music Theory and they are also nice to listening. Moreover, our software tool can be customized to a particular musical style by including the specific musical knowledge domain in the system. For validation purposes, we used Spieldose to compose different pieces corresponding to the classicism.