Intelligent Systems Group

  • Increase font size
  • Default font size
  • Decrease font size
Intelligent Systems Group

The behaviour of frogs to design novel search metaheuristics


The web, specialized in the divulgation of science, references the work of our group member Borja Calvo and our colleague Christian Blum, where the authors find inspiration in the behaviour of a species of japanese frogs in order to design an optimization algorithm. The work is explained in the following publication:

Christian Blum, Borja Calvo, Maria J. Blesa. “FrogCOL and FrogMIS: new decentralized algorithms for finding large independent sets in graphs”. Swarm Intelligence 9 (2): 205-227, 2015.


Divulgative talk on data mining and big data -- "Deia" newspaper


29th September, 2015 -- Our group member Inaki Inza gave a talk titled "From data mining to big data" in a divulgative scientific meeting around the "big data" discipline organized by the newspaper "Deia". The meeting was the introduction for the awards of the "Best initiatives on social media", organized the the newspaper "Deia". Information about the event can be found here and in the following link of the newspaper.


New impact factor publications


Our members Carlos Pérez-Miguel, Alexander Mendiburu and José Miguel-Alonso have recently published the following two works:

"Competition-based failure-aware scheluding for high-throughput computing systems on peer-to-peer networks". Cluster Computing.

Abstract: in a High-Throughput Computing (HTC) system, system failures and churning pose an important performance limitation. The time used by tasks running in a node that suddenly fails (or abandons the system) constitutes a waste of resources. These aborted tasks are usually reinserted into the system for automatic re-execution, causing additional overheads. This problem has been partially addressed via fault tolerant techniques such as checkpointing and replication. However, these solutions cause additional overheads. In this work, we present several failure-aware scheduling policies that aim to reduce the waste of resources by means of mechanisms to match the submitted tasks with the best node to run it, taking into consideration the (predicted) duration of the task and the (expected) survival time of the nodes. Experimentation through simulation, in the context of an HTC system built on top of a peer-to-peer network, confirms that our policies, compared to several state-of-the-art alternatives, result in a more effective distribution of workload whose consequence is a higher task throughput.

"Modeling the availability of Cassandra". Journal of Parallel and Distributed Computing.

Abstract: Peer-to-Peer systems have been introduced as an alternative to the traditional client–server scheme. Distributed Hash Tables, a type of structured Peer-to-Peer system, have been designed for massive storage purposes. In this work we model the behavior of a DHT based system, Cassandra, with focus on its fault tolerance capabilities, and more specifically, on its availability when facing two different situations: (1) transient failures, those in which a node goes off-line for a while and returns on-line maintaining its data, and (2) memory-less failures, those in which a node goes off-line and returns with no data. First, we introduce two analytical models (one for each scenario) that provide approximations to the behavior of Cassandra under different configurations, and secondly, in order to validate our models, we complete a set of experiments over a real Cassandra cluster. Experimental results confirm the validity of the proposed models of the availability of Cassandra. We also provide some examples of how these models can be used to optimize the availability configuration of Cassandra-based applications.


An interview to Jonathan Ortigosa -- the role of machine learning in sentiment analysis


You can find an interesting interview to our group member Jonathan Ortigosa. The topic of the interview is the role of machine learning in the automatic classification of sentiment analysis of web posts, comments, etc.


Discovering Genes Involved in Disease and the Mystery of Missing Heritability


Tomorrow, 17th of June, Eleazar Eskin will give a talk at the Computer Science Faculty (San Sebastián).

Day: 17th of June

Hour: 11:00

Place: Seminar 3.1, Computer Science Faculty, Donostia - San Sebastián

Title: Discovering Genes Involved in Disease and the Mystery of Missing Heritability


It has been known for many decades that genetic differences among individuals account for a substantial por- tion of trait differences. Only recently has technology been developed to cost effectively measure genetic differences among individuals which creates the possibility of developing models that can predict disease related traits from an individual’s genetics. These models are a key component of personalized medicine and developing such models raise many computational challenges which provide important opportunities for Computer Scientists to make contributions toward human health.


Eleazar Eskin’s research focuses on developing computational methods for analysis of genetic variation.  He is currently a Professor in the Computer Science and Human Genetics departments at the University of California Los Angeles.  Previously, he was an Assistant Professor in Residence in Computer Science Engineering at the University of California, San Diego. Eleazar completed his Ph. D. in the Computer Science Department of Columbia University in New York City.  After graduation, he spent one year in the Computer Science Department at the Hebrew University in Jerusalem, Israel.


New impact factor publication -- Theoretical Computer Science


Our former group member Carlos Echegoyen, together with Roberto Santana, Alexander Mendiburu and Jose Antonio Lozano recently completed the following publication:

"Comprehensive characterization of the behaviors of estimation of distribution algorithms". Theoretical Computer Science.

Abstract: Estimation of distribution algorithms (EDAs) are a successful example of how to use machine learning techniques for designing robust and efficient heuristic search algorithms. Understanding the relationship between EDAs and the space of optimization problems is a fundamental issue for the successful application of this type of algorithms. A step forward in this matter is to create a taxonomy of optimization problems according to the different behaviors that an EDA can exhibit. This paper substantially extends previous work in the proposal of a taxonomy of problems for univariate EDAs, mainly by generalizing those results to EDAs that are able to deal with multivariate dependences among the variables of the problem. Through the definition of an equivalence relation between functions, it is possible to partition the space of problems into equivalence classes in which the algorithm has the same behavior. We provide a sufficient and necessary condition to determine the equivalence between functions. This condition is based on a set of matrices which provides a novel encoding of the relationship between the function and the probabilistic model used by the algorithm. The description of the equivalent functions belonging to a class is studied in depth for EDAs whose probabilistic model is given by a chordal Markov network. Assuming this class of factorization, we unveil the intrinsic connection between the behaviors of EDAs and neighborhood systems defined over the search space. In addition, we carry out numerical simulations that effectively reveal the different behaviors of EDAs for the injective functions defined over the search space {0,1}3. Finally, we provide a novel approach to extend the analysis of equivalence classes to non-injective functions.

  • «
  •  Start 
  •  Prev 
  •  1 
  •  2 
  •  3 
  •  4 
  •  5 
  •  6 
  •  7 
  •  Next 
  •  End 
  • »

Page 1 of 7