How to improve the Systems Security using Data Mining

During this week, Geneura Team has welcomed Professor Ja’far Alqatawna from the University of Jordan. Ja’far Alqatawna is an Associate Professor at King Abdullah II School for Information Technology, University of Jordan. He received his B.Eng degree in Computer Engineering from Mu’tah University, Jordan, followed by MSc. in Information and Communication Systems Security from The Royal Institute of Technology (KTH), Sweden. In 2010 He has been awarded his Ph.D. Degree in Computer Information Systems with specialisation in Information Security and e-Business from Sheffield Hallam University, UK. He was part of researching projects for investigating XACML as a policy language for distributed networks at Security, Policy and Trust Lab (SPOT) of the Swedish Institute of Computer Science (SICS), Sweden. His current research interests are in the field of Cybersecurity in which he tries to look for multi-dimensional approaches that go beyond the technical dimension in order to develop trustworthy Cyberspace. Yesterday he presented a talk about the use of Data Mining for improving the security of the software systems which you can see in slide share, For this time, he presented and discussed several security areas in which data mining has the possibility of enhancing the existing security methods.



How good are different languages at runnig evolutionary algorithms?

As part of the EvoStar conference, which took place last week, we presented the poster Benchmarking Languages for Evolutionary Algorithms, where, with help from many friends in Open Science fashion, we tested several a bunch of compiled and scripting languages on several common evolutionary operations: crossover, mutation and OneMax.

It was presented in poster form, and you had to be there to actually understand it. Since you are not, it’s better if you use this comments (or those at the poster) to inquire about it. Or you can check out the interactive presentation we also did, which in fact includes data and everything in the source.
This work is ongoing, and you are very welcome to participate. Just take a peek at the repo, and do a pull request.

Towards automatic StarCraft strategy generation using genetic programming

I forgot to mention that we published our paper “Towards automatic StarCraft strategy generation using genetic programming” in CIG 2015 conference, held in Taiwan. This was a work made in collaboration with Alberto Tonda (INRA) and Giovanni Squillero (Politecnico di Torino), starting a new research line using this game (and also, starting other nice collaborations that are still a secret!)

The abstract:

Among Real-Time Strategy games few titles have enjoyed the continued success of StarCraft. Many research lines aimed at developing Artificial Intelligences, or “bots”, capable of challenging human players, use StarCraft as a platform. Several characteristics make this game particularly appealing for researchers, such as: asymmetric balanced factions, considerable complexity of the technology trees, large number of units with unique features, and potential for optimization both at the strategical and tactical level. In literature, various works exploit evolutionary computation to optimize particular aspects of the game, from squad formation to map exploration; but so far, no evolutionary approach has been applied to the development of a complete strategy from scratch. In this paper, we present the preliminary results of StarCraftGP, a framework able to evolve a complete strategy for StarCraft, from the building plan, to the composition of squads, up to the set of rules that define the bot’s behavior during the game. The proposed approach generates strategies as C++ classes, that are then compiled and executed inside the OpprimoBot open-source framework. In a first set of runs, we demonstrate that StarCraftGP ultimately generates a competitive strategy for a Zerg bot, able to defeat several human-designed bots.

Do you want to know more? Download the paper draft or electronic version in IEEE web.

There can be only one: Evolving RTS Bots via joust selection

During EvoStar, our group presented several papers on games, multiobjective optimization and implementation of evolutoinary algorithms. This paper was presented as a full talk at EvoGAMES 2016 in Porto (Portugal). BY: Antonio Fernández Ares, Pablo García-Sánchez, Antonio M. Mora García, Pedro A. Castillo, Juan J. Merelo

Source: There can be only one: Evolving RTS Bots via joust selection

Mathematics applied to the maintenance of radio communication devices

Yesterday, Alexander Lyubchenko, post-doctoral researcher from Omsk State Transport University, made a report on the topic “Mathematical support for preventive maintenance periodicity optimization of radio communication facilities”.

The presentation was:

He presented the results of his research field and shared with us ideas for future work.

A small discussion took place concerning the application of another research approaches for solving the presented task, which could provide better efficiency and accuracy of calculations… Somebody said Evolutionary Algorithms? Yes, of course! :D

Thus, it is possible to conclude that the organised event was productive.

Alexander is doing a short visit to our group until next June.

This was a triumph: Evolving intelligent bots for videogames. And for Science.

Today I gave the talk entitled “This was a triumph: Evolving intelligent bots for videogames. And for Science” to the students of the High School IES Montes Orientales. I talked about the concept of Evolutionary Algorithms, and then I presented some of our results of their application in games such as Planet Wars, Unreal, Starcraft or Content Generation.

Other members of the ETSIIT gave other amazing talks about Free Software, Artificial Vision, Robotics or Language Processing. Hopefully we will get some of these student working with us in several years!


Ayúdanos a hacer un poquito de ciencia / Help us to make a bit of Science

Se puede ayudar en un experimento simplemente visitando una página web. ¿Nos ayudas?

Víctor M. Rivas Santos

/cc @geneura –
(English version)

¿Me echas una mano con unos experimentos símplemente accediendo a la web

Como muchos sabéis, últimamente me dedico a la ejecución de algoritmos evolutivos y redes neuronales desde navegadores web. En relación a esta investigación, me gustaría enviar un trabajo a un congreso que habrá en Sevilla este año, llamado DCAI’2016.

Ya tengo el trabajo bastante avanzado, pero me gustaría poder tener más resultados; así que, si no te importa, accede a la web desde donde intentamos predecir valores de una serie temporal de temática económica.

Ten en cuenta que:

  • Puedes acceder a la página tantas veces como desees, y también abandonarla en el momento que decidas.
  • El programa que se ejecutará no instalará nada en tu ordenador, móvil o tablet, ni siquiera cookies.
  • Los algoritmos evolutivos suelen ser lentos, por eso, no te preocupes si tarda en…

View original post 193 more words