Raúl Pérez

Raúl Pérez
University of Granada | UGR · Department of Computer Science and Artificial Intelligence

Doctor

About

72
Publications
4,613
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
1,353
Citations
Citations since 2017
18 Research Items
390 Citations
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060
Introduction
Raúl Pérez currently works at the Department of Computer Science and Artificial Intelligence, University of Granada. Raúl does research in Artificial Intelligence, Data Mining and Human-computer Interaction. Their current project is 'Plan Miner: integrating automated planning and process mining for learning hierarchical planning domains from experience stored in event logs '.
Additional affiliations
October 1992 - present
University of Granada
Position
  • Professor (Associate)

Publications

Publications (72)
Preprint
World wide transport authorities are imposing complex Hours of Service regulations to drivers, which constraint the amount of working, driving and resting time when delivering a service. As a consequence, transport companies are responsible not only of scheduling driving plans aligned with laws that define the legal behaviour of a driver, but also...
Article
Full-text available
Age estimation is a fundamental task in forensic anthropology for both the living and the dead. The procedure consists of analyzing properties such as appearance, ossification patterns, and morphology in different skeletonized remains. The pubic symphysis is extensively used to assess adults’ age-at-death due to its reliability. Nevertheless, most...
Article
In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions. We have trained this architecture on a video game environment used as a standard test-bed for intelligent syste...
Article
In data science there are problems that are not visible until you work with a sufficiently large number of data. This is the case, for example, with the design of the inference engine in fuzzy rule-based classification systems. The most common way to implement the winning rule inference method is to use sequential processing that reviews each of th...
Preprint
Full-text available
This paper presents the PlanMiner-N algorithm, a domain learning technique based on the PlanMiner domain learning algorithm. The algorithm presented here improves the learning capabilities of PlanMiner when using noisy data as input. The PlanMiner algorithm is able to infer arithmetic and logical expressions to learn numerical planning domains from...
Article
Full-text available
In this paper, we propose a domain learning process build on a machine learning-based process that, starting from plan traces with (partially known) intermediate states, returns a planning domain with numeric predicates, and expressive logical/arithmetic relations between domain predicates written in the planning domain definition language (PDDL)....
Chapter
In this work we propose an architecture which learns to select subgoals with Deep Q-Learning in order to decrease the load of a planner when faced with scenarios with tight time restrictions, such as online execution systems. We have trained this architecture on a video game environment used as a standard testbed for intelligent systems application...
Conference Paper
The Fuzzy Rule-Based Classification Systems (FRBCS) are classification model that use fuzzy rules to represent knowledge. FBRCS are popular today, with numerous applications and studies of their behavior and efficiency. This work is dedicated to studying a method that allows the minimization of FBRCS generated by the Chi Algorithm, using the Quine-...
Article
When delivering a transport service, scheduled driver workplans have to be aligned with world wide complex hours of service (HoS) regulations which constraint the amount of working and driving time without resting. The activities of such workplans are recorded by onboard sensors in large temporal event logs. Transport companies are interested on re...
Article
Full-text available
The recent emergence of massive amounts of data requires new algorithms that are capable of processing them in an acceptable time frame. Several proposals have been made, and all of them share the idea of using a procedure to break down the entire set of examples into smaller subsets, process each subset with a learning algorithm, and then combine...
Article
Regression problems try estimating a continuous variable from a number of characteristics or predictors. Several proposals have been made for regression models based on the use of fuzzy rules; however, all these proposals make use of rule models in which the irrelevance of the input variables in relation to the variable to be approximated is not ta...
Conference Paper
The MapReduce paradigm is a programming model mainly thought to process big data sets. This model has recently been used in a new proposal of a linguistic fuzzy rule-based learning algorithm. One of the most important aspects of this proposal is the use of a parallel and distributed algorithm. An alternative to this parallel and distributed organiz...
Article
Ordinal classification is a supervised learning problem. The distinctive feature of ordinal classification is that there is an order relationship among the categories to learn. In this paper, we present a fuzzy rule learning algorithm based on the sequential covering strategy applied to ordinal classification. This proposal modifies a nominal class...
Conference Paper
La clasificación ordinal es un problema de clasificación supervisada cuyo objetivo es predecir la categoría a la que pertenece un patrón teniendo presente que hay una relación de orden entre dichas categorías. En este trabajo presentamos un algoritmo de aprendizaje de reglas difusas basado en la estrategia de recubrimiento secuencial para clasifica...
Conference Paper
The sequential covering strategy has been and still is a very common way to develop rule learning algorithms. This strategy follows a greedy procedure to learn rules, where, after each step one rule is obtained. Recently, we proposed a new sequential covering strategy that allowed the review of previously learned knowledge during the learning proce...
Conference Paper
Full-text available
The inherent interpretability properties of fuzzy rule-based classification systems (FRBCSs) are undoubtedly one of their major advantages when com- pared to conventional black-box classifiers. In this paper we present a preliminary study of how the so- called technique of feature construction can prove useful in the context of land cover classific...
Article
The local set is the largest hypersphere centered on an instance such that it does not contain instances from any other class. Due to its geometrical nature, this structure can be very helpful for distance-based classification, such as classification based on the nearest neighbor rule. This paper is focused on instance selection for nearest neighbo...
Article
In recent years, some authors have approached the instance selection problem from a meta-learning perspective. In their work, they try to find relationships between the performance of some methods from this field and the values of some data-complexity measures, with the aim of determining the best performing method given a data set, using only the...
Article
Full-text available
Inductive learning has been—and still is—one of the most important methods that can be applied in classification problems. Knowledge is usually represented using rules that establish relationships between the problem variables. SLAVE (Structural Learning Algorithm in a Vague Environment) was one of the first fuzzy-rule learning algorithms, and sinc...
Conference Paper
Different fuzzy rule-based learning algorithms use the sequential covering strategy. This model applies a problem decomposition strategy, in which the task of finding a complete rule base is reduced to a sequence of subproblems in each of which the solution is to add a single rule. Now, we are interested in introducing additional capabilities in th...
Article
Traditionally, each instance selection proposal applies the same selection criterion to any problem. However, the performance of such criteria depends on the input data and a single one is not sufficient to guarantee success over a wide range of environments. An option to adapt the selection criteria to the input data is the use of meta-learning to...
Conference Paper
The main difficulty faced by a learning algorithm is to find the appropriate knowledge inside of the huge search space of possible solutions. Typically, the researchers try to solve this problem developing more efficient search algorithms, defining ”ad-hoc” heuristic for the specific problem or reducing the expressiveness of the knowledge represent...
Article
This paper presents a proposal that introduces the use of feature construction in a fuzzy rule learning algorithm. This is done by means of the combination of two different approaches together with a new learning strategy. The first of these two approaches consists of using relations in the antecedent of fuzzy rules while the second one employs fun...
Article
In system identification process often a predetermined set of features is used. However, in many cases it is difficult to know a priori whether the selected features were really the more appropriate ones. This is the reason why the feature construction techniques have been very interesting in many applications. Thus, the current proposal introduces...
Article
Fuzzy modelling research has traditionally focused on certain types of fuzzy rules. However, the use of alternative rule models could improve the ability of fuzzy systems to represent a specific problem. In this proposal, an extended fuzzy rule model, that can include relations between variables in the antecedent of rules is presented. Furthermore,...
Conference Paper
Desarrollar algoritmos de aprendizaje de reglas difusas que obtengan un buen balance entre pre- cisión e interpretabilidad es uno de los campos de investigación dentro del aprendizaje de sistemas difusos. En este trabajo se presenta una propuesta que permite a un algoritmo de clasificación elegir entre cuatro posibles configuraciones para cons- tru...
Conference Paper
This paper presents a proposal for using feature construction in a fuzzy rule-based learning algorithm as a method to avoid working with a fixed set of features to describe a particular problem. The main purpose is to increase the amount of information extracted from initial variables to construct a model that has better prediction capability. This...
Article
This paper presents a proposal for using feature construction in a fuzzy rule-based learning algorithm as a method to avoid working with a fixed set of features to describe a particular problem. The main purpose is to increase the amount of information extracted from initial variables to construct a model that has better prediction capability. This...
Article
Although there are several proposals in the instance selection field, none of them consistently outperforms the others over a wide range of domains. In recent years many authors have come to the conclusion that data must be characterized in order to apply the most suitable selection criterion in each case. In light of this hypothesis, herein we pro...
Conference Paper
Traditionally, fuzzy rule based models work with a fixed set of features to describe a particular problem. Our proposal is to use feature construction by means of functions in order to obtain new variables that allow us to get more information about the problem. In particular, we propose the use of previously defined functions over the input variab...
Conference Paper
Two basic requirements of fuzzy modeling are the accuracy and simplicity of the knowledge obtained. In this study, we propose a genetic learning algorithm of fuzzy relational rules, that is, fuzzy rules that include fuzzy relations. Fuzzy relational rules allow us to obtain fuzzy models with a good interpretability-accuracy trade-off. Since, the in...
Conference Paper
Learning fuzzy rules using genetic algorithms has proven to be a feasible way to learn from data with a high level of uncertainly. Some researches in this area are based on the Genetic Iterative Approach, where a genetic algorithm is the main element of an iterative covering scheme, learning one rule in each iteration. The goal of this work is to e...
Conference Paper
Instance selection is a feasible strategy to solve the problem of dealing with large databases in inductive learning. There are several proposals in this area, but none of them consistently outperforms the others over a wide range of domains. In this paper we present a set of measures to characterize the databases, as well as a new algorithm that u...
Article
Full-text available
The genetic iterative approach has shown to be useful for developing fuzzy rule learning algorithms. The goal of this paper is to extend the iterative scheme of SLAVE for obtaining a complete rule in each iteration, reducing the needed time for the learning process. Thus, we analysis this extension and we present a wide experimental study for showi...
Article
Full-text available
Learning algorithms have real com-plexity and interpretability prob-lems when they are working with high dimensionality problems. In this case, one important problem is to reduce the number of rules main-taining a trade-off between inter-pretability and accuracy. In this task, the fuzzy set theory and the feature selection models play an im-portant...
Article
In the area of the intelligent mobile robots the hybrid reactive-deliberative architectures for navigation are aimed at an efficient integration of reactive and deliberative skills. Reactive skills allow the robot a fast reaction to unexpected events whereas deliberative skills permit the generation of plans to carry out tasks. In these systems a h...
Article
Full-text available
This paper presents the use of genetic algorithms to develop smartly tuned fuzzy logic controllers dedicated to the control of heating, ventilating and air conditioning systems concerning energy performance and indoor comfort requirements. This problem has some specific restrictions that make it very particular and complex because of the large time...
Conference Paper
An inductive approach for learning fuzzy relational rules is described. Fuzzy rela- tional rules are rules in which fuzzy rela- tions in the antecedent parts of the rules are allowed. These rules allow us to use an extended model of rule with a greather ca- pability to represent knowledge in a simi- lar human way, but with an additional com- plexit...
Conference Paper
Full-text available
Contributors to the special track on Evolutionary Fuzzy Systems at the EUSFLAT 2003 conference were asked to record their thoughts and ideas on the current state of evolutionary fuzzy systems research, "burning issues" and future directions. This paper brings together these contributions.
Chapter
This work presents the use of genetic algorithms for the optimization and control of Heating, Ventilating and Air Conditioning (HVAC) systems developing smartly tuned fuzzy logic controllers for energy efficiency and overall performance of these systems. An optimum operation of the HVAC systems is a necessary condition for minimizing energy consump...
Chapter
The learning algorithms can be an useful tool for helping to the humans to understand the behavior of phenomena from a set of samples. In particular, those algorithms that represent the knowledge obtained by linguistic fuzzy rules are appropriate for this task. However, it is not sufficient that the knowledge representation is close to the humans c...
Article
One of the basic elements in the development of the AI system is the search mechanism. The choice of the search method can determine the goodness of the developed system. In concrete, in the learning algorithms, the search mechanisms play a very important role. SLAVE is an inductive learning algorithm that describes the behavior of a system by a fu...
Article
Learning algorithms can obtain very useful descriptions of several problems. Many different alternative descriptions can be generated. In many cases, a simple description is preferable since it has a higher possibility of being valid in unseen cases and also it is usually easier to understand by a human expert. Thus, the main idea of this paper is...
Article
Full-text available
Genetic algorithms offer a powerful search method for a variety of learning tasks, and there are different approaches in which they have been applied to learning processes. Structural learning algorithm on vague environment (SLAVE) is a genetic learning algorithm that uses the iterative approach to learn fuzzy rules. SLAVE can select the relevant f...
Article
Full-text available
A very important problem associated with the use of learning algorithms consists of fixing the correct assignment of the initial domains for the predictive variables. In the fuzzy case, this problem is equivalent of define the fuzzy labels for each variable. In this work, we propose the inclusion in a learning algorithm, called SLAVE, of a particul...
Article
Full-text available
SLAVE is an inductive learning algorithm that uses concepts based on fuzzy logic theory. This theory has been shown to be a useful representational tool for improving the understanding of the knowledge obtained from a human point of view. Furthermore, SLAVE uses an iterative approach for learning based on the use of a genetic algorithm (GA) as a se...
Article
Genetic Algorithms have proven to be a powerful tool for automating the Fuzzy Rule Base definition and, therefore, they have been widely used to design descriptive Fuzzy Rule-Based Systems for Qualitative Modeling. These kinds of genetic processes, called Genetic Fuzzy Rule-Based Systems, may be based on different genetic learning approaches, with...
Article
A fuzzy theory refinement algorithm composed of a heuristic process of generaliza- tion, specification, addition and elimination of rules is proposed. This refinement algo- rithm can be applied to knowledge bases obtained from several sources (learning algorithms, experts), but its development is strongly associated with the SLAVE learn- ing system...
Article
The completeness and consistency conditions were introduced in order to achieve acceptable concept recognition rules. In real problems, we can handle noise-affected examples and it is not always possible to maintain both conditions. Moreover, when we use fuzzy information there is a partial matching between examples and rules, therefore the consist...
Article
Full-text available
Fuzzy logic controller performance depends on the fuzzy control rule set. This set can be obtained either by an expert or from a learning algorithm through a set of examples. Recently, we have developed SLAVE an inductive learning algorithm capable of identifying fuzzy systems. The refinement of the rules proposed by SLAVE (or by an expert) can be...
Conference Paper
SLAVE is a genetic learning algorithm that learns the partial relevance of the attributes but when working with large databases the search space is too widespread and the running time is sometimes excessive. We propose a new genetic algorithm with two levels where we include information about the partial relevance of each variable and the consequen...
Conference Paper
Full-text available
Inductive learning algorithms obtain the knowledge of a system from a set of examples. One of the most difficult problems in machine learning is to obtain the structure of this knowledge. We propose an algorithm which is able to manage fuzzy information and to learn the structure of the rules that represent the system. The algorithm gives a reasona...
Article
Full-text available
Resumen Un problema fundamental en la investigación de los procesos de Interacción Robot-Persona es el desarrollo de técnicas que permitan al robot comprender las necesidades de las per-sonas que se encuentran en su entorno. Estas técnicas requieren de procesos en los que se pueda diferenciar a las personas de otros ob-jetos y se pueda comprender,...

Network

Cited By

Projects

Project (1)
Project
This project has two objectives (1) extract the experience stored in the event logs of an organization, representing it in a structured way with HTN planning domains and (2) operationalize this knowledge providing it as input to an HTN planner in order to support decision-making in problem solving to the experts in an organization. In order to achieve these objectives the project take advantge from the interdisciplinary experience of the group (in the development of previous projects in the areas of Machine Learning and Automated Planning) by integrating process mining with HTN domain learning. Process Mining uses mainly Data Mining and Machine Learning to analyze event logs in order to generate a process model that describes how processes are performed in an organization. HTN planning techniques are appropriate for the development of decision support applications, since it alows for the representation of problem-solving expert knowledge. However, the main obstacle for the adoption of solutions based on HTN planning is the knowledge modeling step, since it is still based on an interview process with the expert. In order to eliminate this obstacle, techniques for learning HTN planning domains are being recently investigated.