Acerca de fergunet

PhD at Computer Science. I like Doctor Who.

GeNeura en la Noche de los Investigadores 2015

GeNeura estuvo presente dentro de la Noche Europea de los Investigadores en el stand de la actividad El Ojo que todo lo ve. En este evento estuvimos realizando difusión de los proyectos SIPESCA, MOSOS, PETRA y el recientemente solicitado SiMoPE. Dentro del stand estuvimos mostrando el estado de los proyectos, sus avances, los dispositivos de captación, y los datos de dispositivos móviles que habíamos ido tomando. Tuvo una gran afluencia de público, que participó de forma activa a través de preguntas y opiniones. Además, estuvimos midiendo el paso de las personas que estuvieron asistiendo al evento con uno de nuestros dispositivos.

Algunas fotos del evento:

La Noche Europea de los Investigadores 2015Noche Europea de l@s Investigador@s 2015

La Noche Europea de los Investigadores 2015

Muchas gracias a todos los asistentes!

Anuncios

Evostar 2015 mandatory post

We can never skip the chance to assist the Evostar conference, and aside learn the latest trends in Evolutionary Computation and present our results, we also have a good time with our other colleagues.

This time the conference was held in Copenhagen (Denmark), and because Antonio and me were part of the organization we didn’t have much time to go sightseeing, but we went to Tivoli Gardens and ride the flying chairs (and screamed like babies).

On the scientific part, we presented two papers to EvoGames track, related with our research lines on content generation for videogames and AI optimization. The first paper, How the World Was MADE: Parametrization of Evolved Agent-Based Models for Backstory Generation, presents a study on parametrization of the values that define a virtual world to facilitate the emergence of archetypes, and be able to generate interesting backstories (for videogames, for example). See the poster here:

The poster

Also, as we are commited to open science and open software, you can download the MADE environment from its web. The abstract:

Generating fiction environments for a multi-agent system optimized by genetic algorithms (with some specific requirements related to the desirable plots), presents two main problems: first it is impossible to know in advance the optimal value for the particular designed fitness function, and at the same time, it creates a vast search space for the parameters that it needs. The purpose of this paper is to define a methodology to find the best parameter values for both, the evolutionary algorithm, and the own fictional world configuration. This design includes running, to completion, a world simulation represented as a chromosome, and assigning a fitness to it, thus composing a very complex fitness landscape.
In order to optimize the resources allocated to evolution and to have some guarantees that the final result will be close to the optimum, we systematically analyze a set of possible values of the most relevant parameters, obtaining a set of generic rules. These rules, when applied to the plot requisites, and thus, to the fitness function, will lead to a reduced range of parameter values that will help the storyteller to create optimal worlds with a reduced computation budget.

Evostar 2015 - Copenhagen(That’s me with the IKEA rat plushies I used to describe our system)

Our other paper, It’s Time to Stop: A Comparison of Termination Conditions in the Evolution of Game Bots, describes a methodology to compare different termination conditions in noisy environments such as the RTS games. The abstract:

Evolutionary Algorithms (EAs) are frequently used as a mechanism for the optimization of autonomous agents in games (bots), but knowing when to stop the evolution, when the bots are good enough, is not as easy as it would a priori seem. The first issue is that optimal bots are either unknown (and thus unusable as termination condition) or unreachable. In most EAs trying to find optimal bots fitness is evaluated through game playing. Many times it is found to be noisy, making its use as a termination condition also complicated. A fixed amount of evaluations or, in the case of games, a certain level of victories does not guarantee an optimal result. Thus the main objective of this paper is to test several termination conditions in order to find the one that yields optimal solutions within a restricted amount of time, and that allows researchers to compare different EAs as fairly as possible. To achieve this we will examine several ways of finishing an EA who is finding an optimal bot design process for a particular game, Planet Wars in this case, with the characteristics described above, determining the capabilities of every one of them and, eventually, selecting one for future designs.

Evostar 2015 - Copenhagen(Here’s Antonio presenting the paper)

You can see the rest of the Evostar photos in their flickr account.

How the world was MADE: parametrisation of evolved agent-based models for backstory generation

Our paper “How the world was MADE: parametrisation of evolved agent-based models for backstory generation” has been accepted in Evostar 2015 conference. This paper continues our previous work published at ALIFE. You can also download the MADE framework source and binaries to test it for your own. Also, read the draft in our repository on GitHub.

The abstract:

Generating fiction environments for a multi-agent system optimized by genetic algorithms (with some specific requirements related to the desirable plots), presents two main problems: first it is impossible to know in advance the optimal value for the particular designed fitness function, and at the same time, it creates a vast search space for the parameters that it needs. The purpose of this paper is to define a methodology to find the best parameter values for both, the evolutionary algorithm, and the own fictional world configuration. This design includes running, to completion, a world simulation represented as a chromosome, and assigning a fitness to it, thus composing a very complex fitness landscape.

In order to optimize the resources allocated to evolution and to have some guarantees that the final result will be close to the optimum, we systematically analyse a set of possible values of the most relevant parameters, obtaining a set of generic rules. These rules, when applied to the plot requisites, and thus, to the fitness function, will lead to a reduced range of parameter values that will help the storyteller to create optimal worlds with a reduced computation budget.

PETRA: Predicción del Estado del Tráfico usando un sistema de monitorización de bajo coste

Código: SPIP2014-1437
Programa financiador: Ayudas a la I+D+i en materia de tráfico, movilidad y seguridad vial.
Entidad financiadora: Dirección General de Tráfico. Ministerio del Interior.
Responsable: Pablo García Sánchez (pablogarciaATugr.es)
Fecha inicio: 18/11/2014
Fecha fin: 14/10/2015
Web: Proyecto Petra

Resumen

El objetivo de este proyecto es crear un sistema que permita ofrecer información completa y en tiempo real del tráfico en un área metropolitana, predecir en diferentes marcos temporales el mismo y ofrecer esa información como datos abiertos para su consumo por parte de aplicaciones creadas por la administración o los usuarios. El objetivo de este sistema es mejorar la información de tráfico disponible al usuario de las carreteras, fusionando distintas fuentes de datos, para predecir y prevenir atascos y otros tipos de incidencias utilizando técnicas de Big Data, mejorando la fluidez de los desplazamientos.

Actualmente existen diferentes medios que permiten conocer, en tiempo real, el estado de ciertos tramos de las carreteras, como por ejemplo las cámaras de seguridad, o los aforadores. En un proyecto anterior de esta convocatoria (SINECA, Nº Exp 0100DGT21285) introdujimos un dispositivo de bajo coste que permitía conocer este estado en tiempo real y además identificar cuándo un vehículo pasa por dos sitios diferentes.

En este proyecto se desplegaron una serie de dispositivos en distintas zonas urbanas e interurbanas, que recogían información de los dispositivos móviles (mediante Bluetooth) para realizar seguimiento de los vehículos que pasaban cerca de esos nodos, almacenando su identificador y una marca de tiempo. Los resultados de ese prototipo fueron una serie de mediciones (tales como paso de vehículos por días, horas, y velocidades medias) en un área limitada que demostraron la viabilidad de la propuesta.

Una vez comprobada la viabilidad del tipo de enfoque propuesto por ese proyecto, se puede usar como base para obtener datos nuevos que puedan compararse y ser analizados con otros medios de obtención de datos, y realizar análisis de predicción sobre ellos. En esta nueva propuesta se plantea partir de los resultados del anterior proyecto, añadiendo información complementaria, añadiendo más nodos y otras fuentes de información, como Google Traffic o los aforadores oficiales de la DGT. Con los datos obtenidos se realizarán predicciones del estado futuro del tráfico de forma más precisa, utilizando métodos dentro de la rama del Soft Computing y de Data Mining. Se plantea un estudio sobre distintos métodos de predicción disponibles en la literatura, como por ejemplo ARIMA, Croston, Theta, Spline, L-Co-R, LR y SVM-MLP entre otros.

El análisis de los datos proporcionará información relativa a predicción de atascos, uso de las carreteras, velocidades medias o información geolocalizada sobre el estado de las carreteras. Así mismo, se propone la extensión de los sistemas de difusión de los datos obtenidos usando servicios web, creando una serie de datos de acceso público para que futuros investigadores puedan realizar sus análisis, facilitando así el Open Data.

The Parking

[Paper] My life as a sim: evolving unique and engaging life stories using virtual worlds

Our latest publication My life as a sim: evolving unique and engaging life stories using virtual worlds, using our framework MADE (created by @rubenhek), has been published in the ALIFE 2014 conference. The abstract:

Stories are not only painfully weaved by crafty writers in the solitude of their studios; they also have to be produced massively for non-player characters in the video game industry or tailored to particular tastes in personalized stories. However, the creation of fictional stories is a very complex task that usually implies a creative process where the author has to combine characters, conflicts and backstories to create an engaging narrative. This work describes a general methodology to generate cohesive and coherent backstories where desired archetypes (universally accepted literary symbols) can emerge in complex stochastic systems. This methodology supports the modeling and parametrization of the agents, the environment where they will live and the desired literary setting. The use of a Genetic Algorithm (GA) is proposed to establish the parameter configuration that will lead to backstories that best fit the setting. Information extracted from a simulation can then be used to create the literary work. To demonstrate the adequacy of the methodology, we perform an implementation using a specific multi-agent system and evaluate the results, testing with three different literary settings.

Check out the presentation by @jjmerelo at http://jj.github.io/alife14-made/#/home. You can download the proceedings of the conference (CC license), or download the paper draft.

More information is available on the project page.

[Paper] A Methodology to Develop Service Oriented Evolutionary Algorithms

Paper about our methodology for service oriented EAs

OSGiLiath Evolutionary Framework

Our paper A Methodology to Develop Service Oriented Evolutionary Algorithms has been published in the proceedings of the 8th International Symposium on Intelligent Distributed Computing – IDC’2014. This paper is a resume of the SOA-EA methodology, one of the chapters of my thesis (available here). The presentation, made by JJ Merelo, is quite cool:

http://jj.github.io/pres-idc-2014/index.html#/home

The abstract:

This paper proposes a methodology to design and implement Evolutionary Algorithms using the Service Oriented Architecture paradigm. This paradigm allows to deal with some of the shortcomings in the Evolutionary Algorithms area, facilitating the development, integration, standardization of services that conform a evolutionary algorithm, and, besides, the dynamic alteration of those elements in runtime.
A four-step methodology to design services for Evolutionary Algorithms is presented: identification, specification, implementation and deployment. Also, as an example of application of this methodology, an adaptive algorithm is developed.

You can download the paper draft from…

Ver la entrada original 15 palabras más

Paper “Testing the Differences of Using RGB and HSV Histograms During Evolution in Evolutionary Art” in ECTA

This week we are presenting the paper “Testing the Differences of Using RGB and HSV Histograms During Evolution in Evolutionary Art” in the Evolutionary Computation Theory and Applications.

This is the work we developed in the Hackathon of the Spanish Free Software Contest of the University of Granada with the help of several students of our university (who are also authors!).

In this work we have added Processing to our OSGiLiath (service oriented architecture for evolutionary algorithms) framework to generate images from individual representations to work with generative art. The fitness is the equality to a predefined image. HSV, RGB and a combination of both have been used.

The abstract:

This paper compares the use of RGB and HSV histograms during the execution of an Evolutionary Algorithm. This algorithm generates abstract images that try to match the histograms of a target image. Three different fitness functions have been used to compare: the differences between the individual with the RGB histogram of the test image, the HSV histogram, and an average of the two histograms at the same time. Results show that the HSV fitness also increases the similarities of the RGB (and therefore, the average) more than the other two measures.

And here is the poster:

ecta