
Ester BernadóTecnoCampus · Escola Superior Politècnica Tecnocampus
Ester Bernadó
PhD in Computer Engineering
About
84
Publications
9,351
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,324
Citations
Publications
Publications (84)
Higher education institutions across Europe are called to offer entrepreneurship education. Despite the rising interest and the increased offerings in the last decades, entrepreneurship education is yet not as mature as other disciplines, and it is still underdeveloped in some faculties and institutions. One way of embedding entrepreneurship educat...
This study provides an overview of the important initiatives higher education institutions (HEIs) are implementing to develop their entrepreneurial and innovative potential. The authors performed a systematic analysis of the 62 case studies reported on the HEInnovate website. The initiatives described within these case studies are classified under...
This contribution presents a course on imagination held at Politecnico di Milano. The aim of the course was to make students reflect on the role of imagination in various contexts (especially scientific and moral) and to teach them how to strengthen it to better perform as whole engineers. The pilot initiative was highly valued by the students as a...
Public repositories have contributed to the maturation of experimental methodology in machine learning. Publicly available data sets have allowed researchers to empirically assess their learners and, jointly with open source machine learning software, they have favoured the emergence of comparative analyses of learners’ performance over a common fr...
The excellence of a given learner is usually claimed through a performance comparison with other learners over a collection of data sets. Too often, researchers are not aware of the impact of their data selection on the results. Their test beds are small, and the selection of the data sets is not supported by any previous data analysis. Conclusions...
The classification problem can be addressed by numerous techniques and algorithms which belong to different paradigms of machine learning. In this paper, we are interested in evolutionary algorithms, the so-called genetics-based machine learning algorithms. In particular, we will focus on evolutionary approaches that evolve a set of rules, i.e., ev...
GECCO-2011 A joint meeting of the twentieth international conference on genetic algorithms (ICGA-2011) and the sixteenth annual genetic programming conference (GP-2011)
Currently available real-world problems do not cover the whole complexity space and, therefore, do not allow us to thoroughly test learner behavior on the border of its domain of competence. Thus, the necessity of developing a more suitable testing scenario arises. With this in mind, data complexity analysis has shown promise in characterizing diff...
KEEL is a Data Mining software tool to assess the behaviour of evolutionary learning algorithms in particular and soft computing algorithms in general for different kinds of Data Mining problems including as regression, classification, clustering, pattern mining and so on. It allows us to perform a complete analysis of some learning model in compar...
The landscape contest provides a new and configurable framework to evaluate the robustness of supervised classification techniques and detect their
limitations. By means of an evolutionary multiobjective optimization approach, artificial data sets are generated to cover
reachable regions in different dimensions of data complexity space. Systematic...
This tutorial gives an introduction to Learning Classifier Systems focusing on the Michigan-Style type and XCS in particular. The objective is to introduce (1) where LCSs come from, (2) how LCSs generally work, (3) which different systems exist, (4) how the XCS system works, (5) how an LCS should be applied to a problem at hand, and (6) which curre...
KEEL is a Data Mining software tool to assess the behaviour of evolutionary learning algorithms in particular and soft computing algorithms in general for different kinds of Data Mining problems including as regression, classification, clustering, pattern mining and so on. It allows us to perform a complete analysis of some learning model in compar...
KEEL is a Data Mining software tool to assess the behaviour of evolutionary learning algorithms in particular and soft computing algorithms in general for different kinds of Data Mining problems including as regression, classification, clustering, pattern mining and so on. It allows us to perform a complete analysis of some learning model in compar...
Evolutionary prototype selection has shown its effectiveness in the past in the prototype selection domain. It improves in most of the cases the results offered by classical prototype selection algorithms but its computational cost is expensive. In this paper, we analyze the behavior of the evolutionary prototype selection strategy, considering a c...
Michigan-style learning classifier systems (LCSs) are online machine learning techniques that incrementally evolve distributed subsolutions which individually solve a portion of the problem space. As in many machine learning systems, extracting accurate models from problems with class imbalances-that is, problems in which one of the classes is poor...
Typical domains used in machine learning analyses only cover the complexity space partially, remaining a large proportion of problem difficulties that are not tested. Since the acquisition of new real-world problems is costly, the machine learning community has started giving importance to the automatic generation of learning domains with bounded d...
One of the most important challenges in supervised learning is how to evaluate the quality of the models evolved by different
machine learning techniques. Up to now, we have relied on measures obtained by running the methods on a wide test bed composed
of real-world problems. Nevertheless, the unknown inherent characteristics of these problems and...
XCS is a learning classifier system that uses genetic algorithms to evolve a population of classifiers online. When applied to classification problems described by continuous attributes, XCS has demonstrated to be able to evolve classifica- tion models—represented as a set of independent interval-based rules—that are, at least, as accurate as those...
This paper presents Fuzzy-UCS, a Michigan-style learning fuzzy-classifier system specifically designed for supervised learning tasks. Fuzzy-UCS is inspired by UCS, an on-line accuracy-based learning classifier system. Fuzzy-UCS introduces a linguistic representation of the rules with the aim of evolving more readable rule sets, while maintaining si...
© Springer-Verlag 2008 Abstract This paper investigates the capabilities of evolutionary on-line rule-based systems, also called learning classifier systems (LCSs), for extracting knowledge from imbalanced data. While some learners may suffer from class imbalancesandinstancessparselydistributedaroundthefea- ture space, we show that LCSs are flexibl...
Usually, performance of classifiers is evaluated on real-world problems that mainly belong to public repositories. However, we ignore the inherent properties of these data and how they affect classifier behavior. Also, the high cost or the difficulty of experiments hinder the data collection, leading to complex data sets characterized by few instan...
Abstract During the last decade, research on Genetic- Based Machine Learning has resulted in several proposals of supervised learning methodologies,that use evolutionary algorithms,to evolve,rule-based classification models. Usually, these new GBML approaches are accompanied by little experimentation,and there is a lack of comparisons among differe...
This paper introduces an approximate fuzzy representation to Fuzzy- UCS, a Michigan-style Learning Fuzzy-Classifier System that evolves linguistic fuzzy rules, and studies whether the flexibility provided by the approximate representation results in a significant improvement of the accuracy of the mod- els evolved by the system. We test Fuzzy-UCS w...
XCS is a learning classifier system that combines a re- inforcement learning scheme with evolutionary algorithms to evolve rule sets on-line by means of the interaction with an environment. Usually, research conducted on XCS has mainlyfocused on theanalysis and improvementofthe rein- forcement learning component, overlooking the evolution- ary disc...
In this paper, we highlight the use of synthetic data sets to analyze learners behavior under bounded complexity. We propose a method to generate synthetic data sets with a specific complexity, based on the length of the class boundary. We design a genetic algorithm as a search technique and find it useful to obtain class labels according to the de...
This paper presents CSar, a Michigan-style Learning Clas- sier System which has been designed for extracting quanti- tative association rules from streams of unlabeled examples. The main novelty of CSar with respect to the existing asso- ciation rule miners is that it evolves the knowledge on-line and so it is prepared to adapt its knowledge to cha...
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learning approach. A genetic algorithm is iteratively called to find a partition of the search space where a linear regressor can accurately fit the objective function. The res...
This chapter gives insight in the use of Genetic-Based Machine Learning (GBML) for supervised tasks. Five GBML systems which
represent different learning methodologies and knowledge representations in the GBML paradigm are selected for the analysis:
UCS, GAssist, SLAVE, Fuzzy AdaBoost, and Fuzzy LogitBoost. UCS and GAssist are based on a non-fuzzy...
This chapter investigates the capabilities of XCS for mining imbalanced datasets. Initial experiments show that, for moderate
and high class imbalances, XCS tends to evolve a large proportion of overgeneral classifiers. Theoretical analyses are developed,
deriving an imbalance bound up to which XCS should be able to differentiate between accurate a...
This paper proposes Pitts-DNF-C, a multi- objective Pittsburgh-style Learning Classifier System that evolves a set of DNF-type fuzzy rules for classification tasks. The system is explicitly designed to only explore solutions that lead to consistent, complete, and compact rule sets without redundancies and inconsistencies. The behavior of the system...
This chapter provides an introduction to Learning Classifier Systems before reviewing a number of historical uses in data
mining. An overview of the rest of the volume is then presented.
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learning approach. A genetic algorithm is iteratively called to find a partition of the search space where a linear regressor can accurately fit the objective function. The res...
This paper deals with the characterization of data complexity and the re- lationship with the classification accuracy. We study three dimensions of data com- plexity: the length of the class boundary, the number of features, and the number of instances of the data set. We find that the length of the clas s boundary is the most relevant dimension of...
XCS is a complex,machine,learning technique that combines,credit ap- portionment techniques for rule evaluation with genetic algorithms for rule discov- ery to evolve a distributed set of sub-solutions online. Recent research on XCS has mainly focused on achieving a better understanding of the reinforcement compo- nent, yielding several improvement...
Just over thirty years after Holland first presented the outline for Learning Classifier System paradigm, the ability of LCS to solve complex real-world problems is becoming clear. In particular, their capability for rule induction in data mining has sparked renewed interest in LCS. This book brings together work by a number of individuals who are...
This book constitutes the thoroughly refereed joint post-conference proceedings of two consecutive International Workshops on Learning Classifier Systems that took place in Seattle, WA, USA in July 2006, and in London, UK, in July 2007 - all hosted by the Genetic and Evolutionary Computation Conference, GECCO.
The 14 revised full papers presented w...
Case retrieval from a clustered case memory consists in find- ing out the clusters most similar to the new input case, and then retriev- ing the cases from them. Although the computational time is improved, the accuracy rate may be degraded if the clusters are not representative enough due to data geometry. This paper proposes a methodology for al-...
ABSTRACT In this paper, we derive models of the selection pressure in XCS for proportionate (roulette wheel) selection and tournament,selection. We show that these models can explain the empirical results that have been previously presented in the literature. We validate the models on simple problems showing that, (i) when the model assumptions hol...
This paper analyzes the scalability of the population size required in XCS to maintain niches that are infrequently activated. Facetwise models have been developed to predict the efiect of the imbalance ratio|ratio between the number of instances of the majority class and the minority class that are sampled to XCS|on population initialization, and...
This paper presents a learning methodology based on a substructural classification model to solve decomposable classification problems. The proposed method consists of three important components: (1) a structural model that represents salient interactions between attributes for a given data, (2) a surrogate model which provides a functional approxi...
This paper presents Fuzzy-UCS, a Michigan-style Learning Fuzzy-Classifier System designed for supervised learning tasks. Fuzzy-UCS combines the generalization capabilities of UCS with the good interpretability of fuzzy rules to evolve highly accurate and understandable rule sets. Fuzzy-UCS is tested on a set of real-world problems, and compared to...
Case-Based Reasoning (CBR) systems solve new problems using others which have been previously resolved. The knowledge is composed
of a set of cases stored in a case memory, where each one describes a situation in terms of a set of features. Therefore,
the size and organization of the case memory influences in the computational time needed to solve...
This paper presents a methodology to transform a problem to make it suitable for classification methods, while reducing its complexity so that the classification models extracted are more accurate. The problem is represented by a dataset, where each instance consists of a variable number of descriptors and a class label. We study dataset transforma...
This paper provides a deep insight into the learning mechanisms of UCS, a learning classifier system (LCS) derived from XCS
that works under a supervised learning scheme. A complete description of the system is given with the aim of being useful
as an implementation guide. Besides, we review the fitness computation, based on the individual accuracy...
Over the recent years, research on Learning Classifier Systems (LCSs) got more and more pronounced and diverse. There have
been significant advances of the LCS field on various fronts including system understanding, representations, computational
models, and successful applications. In comparison to other machine learning techniques, the advantages...
This paper presents a learning methodology based on a substructural classification model to solve decomposable classification
problems. The proposed method consists of three important components: (1) a structural model, which represents salient interactions
between attributes for a given data, (2) a surrogate model, which provides a functional appr...
This paper presents Fuzzy-UCS, a Michigan-style Learning Fuzzy-Classifier System designed for supervised learning tasks. Fuzzy-UCS combines the generalization capabilities of UCS with the good interpretability of fuzzy rules to evolve highly accurate and understandable rule sets. Fuzzy-UCS is tested on a large collection of real-world problems, and...
Resumen Este artículo estudia el comportamiento del sis-tema HIDER, que se caracteriza por ser un sis-tema clasicador incremental que evoluciona un conjunto jerárquico de reglas. Mediante un conjun-to de problemas articiales, se analiza la capacidad del algoritmo incremental para evolucionar repre-sentaciones en entornos formados por ejemplos dis-t...
ABSTRACT This paper,analyzes,the behavior,of the XCS classifier sys- tem,on imbalanced,datasets. We show,that XCS with stan- dard parameter,settings is quite robust,to considerable,class imbalances. For high class imbalances, XCS suffers from bi- ases toward,the majority,class. We analyze,XCS’s behavior under,such extreme,imbalances,and,prove that...
The incidence of breast cancer varies greatly among countries, but statistics show that every year 720,000 new cases will be diagnosed world-wide. However, a low percentage of women who suffer it can be detected using mammography methods. Therefore, it is necessary to develop new strategies to detect its formation in early stages. Many machine lear...
We study the behavior of XCS, a classifier based on genetic algorithms. XCS summarizes the state of the art of the evolutionary
learning field and benefits from the long experience and research in the area. We describe the XCS learning mechanisms by
which a set of rules describing the class boundaries is evolved. We study XCS’s behavior and its rel...
We study the domain of competence of a set of popular classifiers, by means of a methodology that relates the classifier’s
behavior to problem complexity. We find that the simplest classifiers—the nearest neighbor and the linear classifier—have
extreme behavior in the sense that they mostly behave either as the best approach for certain types of pr...
The class imbalance problem has been said recently to hinder the performance of learning systems. In fact, many of them are designed with the assumption of well-balance datasets. However, it is very common to find higher presence of one of the classes in real classification problems. The aim of this paper is to make a preliminary analysis on the ef...
The XCS classifier system has recently shown a high degree of competence on a variety of data mining problems, but to what kind of problems XCS is well and poorly suited is seldom understood, especially for real-world classification problems. The major inconvenience has been attributed to the difficulty of determining the intrinsic characteristics...
The class imbalance problem has been said recently to hinder the performance of learning systems. In fact, many of them are
designed with the assumption of well-balanced datasets. But this commitment is not always true, since it is very common to
find higher presence of one of the classes in real classification problems. The aim of this paper is to...
The class imbalance problem has been said to challenge the performance of concept learning systems. Learning systems tend to be biased towards the majority class, and thus have poor generalization for the minority class instances. We analyze the class imbalance problem in learning classifier systems based on genetic algorithms. In particular we stu...
Pseudonoise (PN) sequence sets must fulfill crosscorrelation properties in order to minimize multiuser interference. These properties are satisfied by the mathematical methods used to design these sets. In multiuser spread spectrum signals working with multiresolutive receivers, the pseudonoise sequences need to have more features for the proper pe...
We study the domain of dominant competence of six popular classifiers in a space of data complexity measurements. We observe that the simplest classifiers, nearest neighbor and linear classifier, have extreme behavior of being the best for the easiest and the most difficult problems respectively, while the sophisticated ensemble classifiers tend to...
XCS is a classifier system that combines reinforcement learning and genetic algorithms to learn a set of rules describing the knowledge inherent in a dataset. Re-cent studies have shown that XCS is highly competitive with respect to other classifier schemes. However, these studies have been mainly based on the analysis and improve-ment of the class...
Evolutionary learning systems (also known as Pittsburgh learningclassifier systems) need to balance accuracy and parsimony for evolving high quality general hypotheses. The learning
process used in evolutionary learning systems is based on a set of training instances that sample the target concept to be
learned. Thus, the learning process may overf...
Recently, Learning Classifier Systems (LCS) and particularly XCS have arisen as promising methods for classification tasks and data mining. This paper investigates two models of accuracy-based learning classifier systems on different types of classification problems. Departing from XCS, we analyze the evolution of a complete action map as a knowled...
Learning systems (also known as Pittsburgh learning classifier systems) need to balance accuracy and parsimony for evolving high quality general hypotheses. The evolutionary learning process used in learning systems is based on using a set of training instances that sample the target concept to be learned. Thus, the the learning process may overfit...
This paper compares the learning performance, in terms of prediction accuracy, of two genetic-based machine learning systems (GBML), XCS and GALE, with six wellknown learning algorithms, coming from instance based learning, decision tree induction, rule-learning, statistical modeling and support vector machines. The experiments, performed on severa...
This paper compares the learning perfor-mance, in terms of prediction accuracy, of two genetic-based machine learning systems (GBML), XCS and GALE, with six well-known learning algorithms, coming from in-stance based learning, decision tree induc-tion, rule-learning, statistical modeling and support vector machines. The experiments, performed on se...
This paper compares the learning performance, in terms of prediction accuracy, of two genetic-based learning systems, XCS and GALE, with six well-known learning algorithms, coming from instance based learning, decision tree induction, rule-learning, statistical modeling and support vector machines. The experiments, performed on several datasets, sh...
This paper compares the learning performance, in terms of prediction accuracy, of two genetic-based learning systems, XCS and GALE, with six well-known learning algorithms, coming from instance based learning, decision tree induction, rule-learning, statistical modeling and support vector machines. The experiments, performedon several datasets, sho...
MOLeCS is a classifier system (CS) which addresses its learning as a multiobjective task. Its aim is to develop an optimal
set of rules, optimizing the accuracy and the generality of each rule simultaneously. This is achieved by considering these two goals in the rule fitness. The paper studies four
multiobjective strategies that establish a compro...
Resumen La asignatura de Programación constituye una base fundamental para las diversas carreras de ingeniería. Los posibles enfoques que se pueden utilizar, tanto de contenidos como de método docente, son muy diversos. En este artículo presentamos la solución adoptada en Enginyeria i Arquitectura la Salle (Universitat Ramon Llull) para ayudar a lo...
This paper describes the application of Machine Learning (ML) techniques to a real world problem: the Automatic Diagnosis (classification) of Mammary Biopsy Images. The starting point consists of a set of data (solved cases) provided by the Signal Theory Research Group of our University [9]. The techniques applied are Genetic Algorithms (GA) and Ca...
This paper describes the application of Machine Learning (ML) techniques to a real world problem: the Automatic Diagnosis (classification) of Mammary Biopsy Images. The techniques applied are Genetic Algorithms (GA) and Case-Based Reasoning (CBR). The paper compares our results with previous results obtained using Neural Networks. The main goals ar...
In this paper we present a classifier system based on Genetic Algorithms for a medical domain. The system evolves a set of
rules, using the Pittsburgh approach. Therefore, each individual of the Genetic Algorithm codifies a complete set of rules.
Our efforts have focused on the improvement of classification and prediction accuracy and the minimizat...
Learning concept descriptions from data is a complex multiobjective task. The model induced by the learner should be accurate so that it can represent precisely the data instances, complete, which means it can be generalizable to new instances, and minimum, or easily readable. Learning Classifier Systems (LCSs) are a family of learners whose primar...
This paper studies UCS, a learning classifier system (LCS) derived from XCS that works under a supervised learning scheme. A complete description of the system is given. Be-sides, we introduce a fitness sharing scheme to UCS and analyze UCS both with fitness sharing and without fitness sharing. Results show the benefits of fitness sharing in all th...
We study the behavior of XCS, a classifier based on genetic algorithms. XCS summarizes the state-of-the-art of the genetic based machine learning field and benefits from long experience and research in the area. We describe the learn-ing mechanisms of XCS by which a set of rules describing the class boundaries is evolved. We study XCS's behavior re...
Learning concept descriptions from data is a complex multiobjective task. The model in- duced by the learner should be accurate so that it can represent precisely the data instances, complete, which means it can be generalizable to new instances, and minimum, or easily readable. Learning Classifier Systems (LCSs) are a family or learners whose prim...
Resumen: En este artículo se presentan los Seminarios del Grupo de Investigación en Sistemas Inteligentes de Enginyeria i Arquitectura La Salle de la Universitat Ramon Llull, estructurados como un curso de introducción a las técnicas de aprendizaje automático. Este curso ofrece un marco común a los alumnos que cursan asignaturas de libre elección,...