Category: Evolutionary Intelligence

Special issue on genetic fuzzy systems: new advances

Special issue on genetic fuzzy systems: new advances
Content Type Journal ArticleDOI 10.1007/s12065-009-0027-yAuthors
Rafael Alcalá, University of Granada Department of Computer Science and A.I. 18071 Granada SpainYusuke Nojima, Osaka Prefecture Un…

Special issue on genetic fuzzy systems: new advances

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0027-y
  • Authors
    • Rafael Alcalá, University of Granada Department of Computer Science and A.I. 18071 Granada Spain
    • Yusuke Nojima, Osaka Prefecture University Department of Computer Science and Intelligent Systems 1-1 Gakuen-cho, Naka-ku Sakai, Osaka 599-8531 Japan

Multiagent coevolutionary genetic fuzzy system to develop bidding strategies in electricity markets: computational economics to assess mechanism design

Abstract  This paper suggests a genetic fuzzy system approach to develop bidding strategies for agents in online auction environments.
Assessing efficient bidding strategies is a key to evaluate auction models and verify if the underlying me…

Abstract  This paper suggests a genetic fuzzy system approach to develop bidding strategies for agents in online auction environments.
Assessing efficient bidding strategies is a key to evaluate auction models and verify if the underlying mechanism design achieves
its intended goals. Due to its relevance in current energy markets worldwide, we use day-ahead electricity auctions as an
experimental and application instance of the approach developed in this paper. Successful fuzzy bidding strategies have been
developed by genetic fuzzy systems using coevolutionary algorithms. In this paper we address a coevolutionary fuzzy system
algorithm and present recent results concerning bidding strategies behavior. Coevolutionary approaches developed by coevolutionary
agents interact through their fuzzy bidding strategies in a multiagent environment and allow realistic and transparent representations
of agents behavior in auction-based markets. They also improve market representation and evaluation mechanisms. In particular,
we study how the coevolutionary fuzzy bidding strategies perform against each other during hourly electric energy auctions.
Experimental results show that coevolutionary agents may enhance their profits at the cost of increasing system hourly price
paid by demand.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0023-2
  • Authors
    • Igor Walter, Brazilian Electricity Regulatory Agency, ANEEL Brasília DF Brazil
    • Fernando Gomide, University of Campinas, Unicamp Faculty of Electrical and Computer Engineering, FEEC Campinas SP Brazil

Evolutionary parallel and gradually distributed lateral tuning of fuzzy rule-based systems

Abstract  The tuning of Fuzzy Rule-Based Systems is often applied to improve their performance as a post-processing stage once an initial
set of fuzzy rules has been extracted. This optimization problem can become a hard one when the size of…

Abstract  The tuning of Fuzzy Rule-Based Systems is often applied to improve their performance as a post-processing stage once an initial
set of fuzzy rules has been extracted. This optimization problem can become a hard one when the size of the considered system
in terms of the number of variables, rules and, particularly, data samples is big. Distributed Genetic Algorithms are excellent
optimization algorithms which exploit the nowadays available parallel hardware (multicore microprocessors and clusters) and
could help to alleviate this growth in complexity. In this work, we present a study on the use of the Distributed Genetic
Algorithms for the tuning of Fuzzy Rule-Based Systems. To this end, we analyze the application of a specific Gradual Distributed
Real-Coded Genetic Algorithm which employs eight subpopulations in a hypercube topology and local parallelization at each
subpopulation. We tested our approach on nine real-world datasets of different sizes and with different numbers of variables.
The empirical performance in solution quality and computing time is assessed by comparing its results with those from a highly
effective sequential tuning algorithm. The results show that the distributed approach achieves better results in terms of
quality and execution time as the complexity of the problem grows.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0025-0
  • Authors
    • I. Robles, University of Granada Dept. of Computer Sciences and Artificial Intelligence 18071 Granada Spain
    • R. Alcalá, University of Granada Dept. of Computer Sciences and Artificial Intelligence 18071 Granada Spain
    • J. M. Benítez, University of Granada Dept. of Computer Sciences and Artificial Intelligence 18071 Granada Spain
    • F. Herrera, University of Granada Dept. of Computer Sciences and Artificial Intelligence 18071 Granada Spain

Multi-objective evolutionary learning of granularity, membership function parameters and rules of Mamdani fuzzy systems

Abstract  In this paper, we propose a multi-objective evolutionary algorithm (MOEA) to generate Mamdani fuzzy rule-based systems with
different trade-offs between accuracy and complexity by learning concurrently granularities of the input an…

Abstract  In this paper, we propose a multi-objective evolutionary algorithm (MOEA) to generate Mamdani fuzzy rule-based systems with
different trade-offs between accuracy and complexity by learning concurrently granularities of the input and output partitions,
membership function (MF) parameters and rules. To this aim, we introduce the concept of virtual and concrete partitions: the
former is defined by uniformly partitioning each linguistic variable with a fixed maximum number of fuzzy sets; the latter
takes into account, for each variable, the number of fuzzy sets determined by the evolutionary process. Rule bases and MF
parameters are defined on the virtual partitions and, whenever a fitness evaluation is required, mapped to the concrete partitions
by employing appropriate mapping strategies. The implementation of the MOEA relies on a chromosome composed of three parts,
which codify the partition granularities, the virtual rule base and the membership function parameters, respectively, and
on purposely-defined genetic operators. The MOEA has been tested on three real-world regression problems achieving very promising
results. In particular, we highlight how starting from randomly generated solutions, the MOEA is able to determine different
granularities for different variables achieving good trade-offs between complexity and accuracy.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0022-3
  • Authors
    • Michela Antonelli, University of Pisa Dipartimento di Ingegneria dell’Informazione: Elettronica, Informatica, Telecomunicazioni Via Diotisalvi 2 56122 Pisa Italy
    • Pietro Ducange, University of Pisa Dipartimento di Ingegneria dell’Informazione: Elettronica, Informatica, Telecomunicazioni Via Diotisalvi 2 56122 Pisa Italy
    • Beatrice Lazzerini, University of Pisa Dipartimento di Ingegneria dell’Informazione: Elettronica, Informatica, Telecomunicazioni Via Diotisalvi 2 56122 Pisa Italy
    • Francesco Marcelloni, University of Pisa Dipartimento di Ingegneria dell’Informazione: Elettronica, Informatica, Telecomunicazioni Via Diotisalvi 2 56122 Pisa Italy

A study on diversity for cluster geometry optimization

Abstract  Diversity is a key issue to consider when designing evolutionary approaches for difficult optimization problems. In this paper,
we address the development of an effective hybrid algorithm for cluster geometry optimization. The prop…

Abstract  Diversity is a key issue to consider when designing evolutionary approaches for difficult optimization problems. In this paper,
we address the development of an effective hybrid algorithm for cluster geometry optimization. The proposed approach combines
a steady-state evolutionary algorithm and a straightforward local method that uses derivative information to guide search
into the nearest local optimum. The optimization method incorporates a mechanism to ensure that the diversity of the population
does not drop below a pre-specified threshold. Three alternative distance measures to estimate the dissimilarity between solutions
are evaluated. Results show that diversity is crucial to increase the effectiveness of the hybrid evolutionary algorithm,
as it enables it to discover all putative global optima for Morse clusters up to 80 atoms. A comprehensive analysis is presented
to gain insight about the most important strengths and weaknesses of the proposed approach. The study shows why distance measures
that consider structural information for estimating the dissimilarity between solutions are more suited to this problem than
those that take into account fitness values. A detailed explanation for this differentiation is provided.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0020-5
  • Authors
    • Francisco B. Pereira, Instituto Superior de Engenharia de Coimbra 3030-199 Coimbra Portugal
    • Jorge M. C. Marques, Universidade de Coimbra Departamento de Química 3004-535 Coimbra Portugal

Sequential problems that test generalization in learning classifier systems

Abstract  We present an approach to build sequential decision making problems which can test the generalization capabilities of classifier
systems. The approach can be applied to any sequential problem defined over a binary domain and it gen…

Abstract  We present an approach to build sequential decision making problems which can test the generalization capabilities of classifier
systems. The approach can be applied to any sequential problem defined over a binary domain and it generates a new problem
with bounded sequential difficulty and bounded generalization difficulty. As an example, we applied the approach to generate
two problems with simple sequential structure, huge number of states (more than a million), and many generalizations. These
problems are used to compare a classifier system with effective generalization (XCS) and a learner without generalization
(Q-learning). The experimental results confirm what was previously found mainly using single-step problems: also in sequential
problems with huge state spaces, XCS can generalize effectively by detecting those substructures that are necessary for optimal
sequential behavior.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0019-y
  • Authors
    • Martin V. Butz, University of Würzburg Röntgenring 11 97070 Würzburg Germany
    • Pier Luca Lanzi, Politecnico di Milano Dipartimento di Elettronica e Informazione Milan Italy

Automated feature selection in neuroevolution

Abstract  Feature selection is a task of great importance. Many feature selection methods have been proposed, and can be divided generally
into two groups based on their dependence on the learning algorithm/classifier. Recently, a feature se…

Abstract  Feature selection is a task of great importance. Many feature selection methods have been proposed, and can be divided generally
into two groups based on their dependence on the learning algorithm/classifier. Recently, a feature selection method that
selects features at the same time as it evolves neural networks that use those features as inputs called Feature Selective
NeuroEvolution of Augmenting Topologies (FS-NEAT) was proposed by Whiteson et al. In this paper, a novel feature selection
method called Feature Deselective NeuroEvolution of Augmenting Topologies (FD-NEAT) is presented. FD-NEAT begins with fully
connected inputs in its networks, and drops irrelevant or redundant inputs as evolution progresses. Herein, the performances
of FD-NEAT, FS-NEAT and traditional NEAT are compared in some mathematical problems, and in a challenging race car simulator
domain (RARS). On the whole, the results show that FD-NEAT significantly outperforms FS-NEAT in terms of network performance
and feature selection, and evolves networks that offer the best compromise between network size and performance.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0018-z
  • Authors
    • Maxine Tan, Vrije Universiteit Brussel, IBBT Department of Electronics and Informatics (ETRO) Brussel Belgium
    • Michael Hartley, DownUnder Geosolutions 80 Churchill Avenue Subiaco WA 6008 Australia
    • Michel Bister, Vrije Universiteit Brussel, IBBT Department of Electronics and Informatics (ETRO) Brussel Belgium
    • Rudi Deklerck, Vrije Universiteit Brussel, IBBT Department of Electronics and Informatics (ETRO) Brussel Belgium

Evolution of internal dynamics for neural network nodes

Abstract  Most artificial neural networks have nodes that apply a simple static transfer function, such as a sigmoid or gaussian, to
their accumulated inputs. This contrasts with biological neurons, whose transfer functions are dynamic and d…

Abstract  Most artificial neural networks have nodes that apply a simple static transfer function, such as a sigmoid or gaussian, to
their accumulated inputs. This contrasts with biological neurons, whose transfer functions are dynamic and driven by a rich
internal structure. Our artificial neural network approach, which we call state-enhanced neural networks, uses nodes with dynamic transfer functions based on n-dimensional real-valued internal state. This internal state provides the nodes with memory of past inputs and computations.
The state update rules, which determine the internal dynamics of a node, are optimized by an evolutionary algorithm to fit
a particular task and environment. We demonstrate the effectiveness of the approach in comparison to certain types of recurrent
neural networks using a suite of partially observable Markov decision processes as test problems. These problems involve both
sequence detection and simulated mice in mazes, and include four advanced benchmarks proposed by other researchers.

  • Content Type Journal Article
  • DOI 10.1007/s12065-009-0017-0
  • Authors
    • David Montana, BBN Technologies 10 Moulton Street Cambridge MA 02138 USA
    • Eric VanWyk, BBN Technologies 10 Moulton Street Cambridge MA 02138 USA
    • Marshall Brinn, BBN Technologies 10 Moulton Street Cambridge MA 02138 USA
    • Joshua Montana, BBN Technologies 10 Moulton Street Cambridge MA 02138 USA
    • Stephen Milligan, BBN Technologies 10 Moulton Street Cambridge MA 02138 USA

Genetic-based approach for cue phrase selection in dialogue act recognition

Abstract  Automatic cue phrase selection is a crucial step for designing a dialogue act recognition model using machine learning techniques.
The approaches, currently used, are based on specific type of feature selection approaches, called r…

Abstract  Automatic cue phrase selection is a crucial step for designing a dialogue act recognition model using machine learning techniques.
The approaches, currently used, are based on specific type of feature selection approaches, called ranking approaches. Despite
their computational efficiency for high dimensional domains, they are not optimal with respect to relevance and redundancy.
In this paper we propose a genetic-based approach for cue phrase selection which is, essentially, a variable length genetic
algorithm developed to cope with the high dimensionality of the domain. We evaluate the performance of the proposed approach
against several ranking approaches. Additionally, we assess its performance for the selection of cue phrases enriched by phrase’s
type and phrase’s position. The results provide experimental evidences on the ability of the genetic-based approach to handle
the drawbacks of the ranking approaches and to exploit cue’s type and cue’s position information to improve the selection.
Furthermore, we validate the use of the genetic-based approach for machine learning applications. We use selected sets of
cue phrases for building a dynamic Bayesian networks model for dialogue act recognition. The results show its usefulness for
machine learning applications.

  • Content Type Journal Article
  • DOI 10.1007/s12065-008-0016-6
  • Authors
    • Anwar Ali Yahya, University Putra Malaysia Intelligent System and Robotics Laboratory, Institute of Advanced Technology 43400 UPM Serdang Selangor Malaysia
    • Abd Rahman Ramli, University Putra Malaysia Intelligent System and Robotics Laboratory, Institute of Advanced Technology 43400 UPM Serdang Selangor Malaysia

MENNAG: a modular, regular and hierarchical encoding for neural-networks based on attribute grammars

Abstract  Recent work in the evolutionary computation field suggests that the implementation of the principles of modularity (functional
localization of functions), repetition (multiple use of the same sub-structure) and hierarchy (recursive…

Abstract  Recent work in the evolutionary computation field suggests that the implementation of the principles of modularity (functional
localization of functions), repetition (multiple use of the same sub-structure) and hierarchy (recursive composition of sub-structures)
could improve the evolvability of complex systems. The generation of neural networks through evolutionary algorithms should
in particular benefit from an adapted use of these notions. We have consequently developed modular encoding for neural networks
based on attribute grammars (MENNAG), a new encoding designed to generate the structure of neural networks and parameters
with evolutionary algorithms, while explicitly enabling these three above-mentioned principles. We expressed this encoding
in the formalism of attribute grammars in order to facilitate understanding and future modifications. It has been tested on
two preliminary benchmark problems: cart-pole control and robotic arm control, the latter being specifically designed to evaluate
the repetition capabilities of an encoding. We compared MENNAG to a direct encoding, ModNet, NEAT, a multi-layer perceptron
with a fixed structure and to reference controllers. Results show that MENNAG performs better than comparable encodings on
both problems, suggesting a promising potential for future applications.

  • Content Type Journal Article
  • DOI 10.1007/s12065-008-0015-7
  • Authors
    • Jean-Baptiste Mouret, Université Pierre et Marie Curie, Paris 6 FRE 2507, ISIR, 4 place Jussieu 75005 Paris France
    • Stéphane Doncieux, Université Pierre et Marie Curie, Paris 6 FRE 2507, ISIR, 4 place Jussieu 75005 Paris France