Un análisis preliminar de nuevos modelos de mutación dirigida en algoritmos genéticos

En este artículo se presenta un análisis preliminar de un modelo de operador de mutación dirigida para problemas con codificación binaria y sin epistasis. Esta versión del operador permite asociar una probabilidad de mutación a cada gen de cada individuo, proporcional a la influencia que ha tenido dicho gen sobre la calidad del individuo durante el proceso evolutivo. Estos valores de probabilidad, permiten a cada individuo realizar mutaciones de manera dirigida, con el objetivo de reducir el tiempo de convergencia del algoritmo. El conjunto de experimentos realizado con el nuevo operador de mutación demuestra que el algoritmo genético converge a soluciones en etapas más tempranas del proceso evolutivo, en comparación con la mutación clásica. Se han llevado a cabo una serie de experimentos con un problema clásico de test, donde aplicando el nuevo operador de mutación dirigida, se consiguen buenos resultados. Aunque estos resultados son aún muy preliminares, esperamos poder continuar el estudio en problemas más complejos en el futuro, y mostrar así la utilidad de esta versión de la mutación dirigida en otros contextos.

Obtener el paper.

Energy-consumption prediction of Genetic Programming Algorithms using a Fuzzy Rule-Based System

Energy awareness has gained momentum over the last decade in the software industry, as well as in environmentally concious society. Thus, algorithm designers and programmers are paying increasing attention this issue, particularly when handheld devices are considered, given their battery-consuming characteristics. When we focus on Evolutionary Algorithms, few works have attempted to study the relationship between the main features of the algorithm, the problem to be solved and the underlying hardware where it runs. This work presents a preliminary analysis and modeling of energy consumption of EAs. We try to predict it by means of a fuzzy rule-based system, so that different devices are considered as well as a number of problems and Genetic Programming parameters. Experimental results performed show that the proposed model can predict energy consumption with very low error values.

https://doi.org/10.1145/3205651.3208216

On the impact of STEM sustained actions on the future of young students.

This paper presents a preliminary analysis on the impact of Municipal Schools of Young Scientists (MSYS) project on young students' decisions regarding their university studies. MSYS, and the pilot project that preceded it, has been operating in Extremadura for more than six years, and some of the students have already reached the age to access university studies. Although not all of them have attended MSYS all these years, we have performed a preliminary analysis that considers what they are studying, if they do, today.This paper presents data about those first years of MSYS that are then compared with the population of young people who have completed compulsory schooling in Spain, and particularly in Extremadura, Spanish region where the project is developed. The data collected shows evidence of a remarkable impact on students interests around STEM areas: an increase of 21 points on the average number of students studying a STEM university degree is reported, when compared with both the population in Spain and Extremadura.Although data obtained are still preliminary to establish a causal relationship, the correlation shows the interest of the approach, with an improvement on all of the measured values. In any case, we think the analysis of the project reported will be useful to design new sustained STEM actions in the future.We hope this results will encourage local administrations and families to continue supporting the project in the next decade.

DOI: 10.1109/FIE.2018.8659277

CGP4Matlab - A Cartesion Genetic Programming MATLAB Tollbox for Audio and Image Processing

This paper presents and describes CGP4Matlab, a powerful toolbox that allows to run Cartesian Genetic Programming within MATLAB. This toolbox is particularly suited for signal processing and image processing problems. The implementation of CGP4Matlab, which can be freely downloaded, is described. Some encouraging results on the problem of pitch estimation of musical piano notes achieved using this toolbox are also presented. Pitch estimation of audio signals is a very hard problem with still no generic and robust solution found. Due to the highly flexibility of CGP4Matlab, we managed to apply a new cartesian genetic programming based approach to the problem of pitch estimation. The obtained results are comparable with the state of the art algorithms.

https://doi.org/10.1007/978-3-319-77538-8_31