LCS & GBML Central

Deadline approaching: IWLCS @ GECCO (March 28)

docurbs — Thu, 14 Mar 2013 22:04:35 +0000

Just a quick reminder that the deadline for the IWLCS will be here in two weeks (March 28). IWLCS is a great place to present your quality projects and ongoing work related to LCS research. This year it is particularly important for you to make a contribution to this workshop which serves as a valuable and central exchange of knowledge and ideas for those interested in the study of these unique algorithms, as well as for those interested in learning more about them.

Last year the IWLCS only got two paper submissions, a record low for the meeting. It is our hope that we will see many more submissions this year in order to demonstrate interest in this workshop.

Submission instructions are on the IWLCS 2013 website under the CFP tab.

http://homepages.ecs.vuw.ac.nz/~iqbal/iwlcs2013/index.html
*********************************************************************
** CALL FOR PAPERS **
** Sixteenth International Workshop on Learning Classifier Systems **
** July 06-10, 2013, Amsterdam, The Netherlands **
** Organized by ACM SIGEVO **
*********************************************************************

The Sixteenth International Workshop on Learning Classifier Systems (IWLCS
2013) will be held in Amsterdam, The Netherlands during the Genetic and
Evolutionary Computation Conference (GECCO-2013), July 06-10, 2013.

Originally, Learning Classifier Systems (LCSs) were introduced by John H.
Holland as a way of applying evolutionary computation to machine learning
and adaptive behaviour problems. Since then, the LCS paradigm has
broadened greatly into a framework that encompasses many representations,
rule discovery mechanisms, and credit assignment schemes.

Current LCS applications range from data mining, to automated innovation
and the on-line control of cognitive systems. LCS research includes
various actual system approaches: While Wilson’s accuracy-based XCS system
(1995) has received the highest attention and gained the highest
reputation; studies and developments of other LCSs are usually discussed
and contrasted. Advances in machine learning, and reinforcement learning
in particular, as well as in evolutionary computation have brought LCS
systems the necessary competence and guaranteed learning properties. Novel
insights in machine learning and evolutionary computation are being
integrated into the LCS framework.

Thus, we invite submissions that discuss recent developments in all areas
of research on, and applications of, Learning Classifier Systems. IWLCS is
the event that brings together most of the core researchers in classifier
systems. The workshop also provides an opportunity for researchers
interested in LCSs to get an impression of the current research directions
in the field as well as a guideline for the application of LCSs to their
problem domain.

Topics of interests include but are not limited to:

Paradigms of LCS (Michigan, Pittsburgh …)
Theoretical developments (behaviour, scalability and learning bounds …)
Representations (binary, real-valued, oblique, non-linear, fuzzy …)
Types of target problems (single-step, multiple-step, regression/function
approximation …)
System enhancements (competent operators, problem structure identification
and linkage learning …)
LCS for Cognitive Control (architectures, emergent behaviours …)
Applications (data mining, medical domains, bioinformatics …)
Optimizations and parallel implementations (GPU, matching algorithms …)

All accepted papers will be presented at IWLCS 2013 and will appear in the
GECCO workshop volume, which will be published by ACM (Association for
Computing Machinery). Authors will be invited after the workshop to submit
revised (full) papers that, after a thorough review process, are to be
published in a special issue of the Evolutionary Intelligence journal.

Important dates

March 28, 2013 – Paper submission deadline
April 15, 2013 – Notification to authors
April 25, 2013 – Submission of camera-ready material
July 06-10, 2013 – GECCO 2013 Conference in Amsterdam, The Netherlands

Organizing Committee

Muhammad Iqbal, muhammad.iqbal@ecs.vuw.ac.nz
Kamran Shafi, k.shafi@adfa.edu.au
Ryan Urbanowicz, ryan.j.urbanowicz@dartmouth.edu

Regards

Ryan Urbanowicz

2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO-2013)

will — Fri, 07 Dec 2012 05:03:06 +0000

*** CALL FOR PAPERS ***
2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO-2013) *** Genetics-Based Machine Learning track ***
*** July 06-10, 2013, Amsterdam, The Netherlands ***
*** Organized by ACM SIGEVO ***
***http://www.sigevo.org/gecco-2013 ***

The Genetics-Based Machine Learning (GBML) track at GECCO 2013 covers all advances in theory and application of evolutionary computation methods to Machine Learning (ML) problems.

ML presents an array of paradigms — unsupervised, semi-supervised, supervised, and reinforcement learning — which frame a wide range of clustering, classification, regression, prediction and control tasks.

The literature shows that evolutionary methods can tackle many different tasks within the ML context:

- addressing subproblems of ML e.g. feature selection and construction
- optimising parameters of other ML methods
- as learning methods for classification, regression or control tasks
- as meta-learners which adapt base learners
* evolving the structure and weights of neural networks
* evolving the data base and rule base in genetic fuzzy systems
* evolving ensembles of base learners

The global search performed by evolutionary methods can complement the local search of non-evolutionary methods and combinations of the two are particularly welcome.

Some of the main GBML subfields are:

* Learning Classifier Systems (LCS) are rule-based systems introduced
by John Holland in the 1970s. LCSs are one of the most active and
best-developed forms of GBML and we welcome all work on them.
* Genetic Programming (GP) when applied to machine learning tasks (as
opposed to function optimisation).
* Evolutionary ensembles, in which evolution generates a set of
learners which jointly solve problems.
* Artificial Immune Systems (AIS).
* Evolving neural networks or Neuroevolution.
* Genetic Fuzzy Systems (GFS) which combine evolution and fuzzy logic.

In addition we encourage submissions including but not limited to the
following:

1. Theoretical advances

* Theoretical analysis of mechanisms and systems
* Identification and modeling of learning and scalability bounds
* Connections and combinations with machine learning theory
* Analysis and robustness in stochastic, noisy, or non-stationary
environments
* Complexity analysis in MDP and POMDP problems
* Efficient algorithms

2. Modification of algorithms and new algorithms

* Evolutionary rule learning, including but not limited to:
o Michigan style (SCS, NewBoole, EpiCS, ZCS, XCS, UCS…)
o Pittsburgh style (GABIL, GIL, COGIN, REGAL, GA-Miner, GALE,
MOLCS, GAssist…)
o Anticipatory LCS (ACS, ACS2, XACS, YACS, MACS…)
o Iterative Rule Learning Approach (SIA, HIDER, NAX, BioHEL,…)
* Artificial Immune Systems
* Genetic fuzzy systems
* Learning using evolutionary Estimation of Distribution
Algorithms (EDAs)
* Evolution of Neural Networks
* Evolution of ensemble systems
* Other hybrids combining evolutionary techniques with other
machine learning techniques

3. Issues in GBML

* Competent operator design and implementation
* Encapsulation and niching techniques
* Hierarchical architectures
* Default hierarchies
* Knowledge representations, extraction and inference
* Data sampling
* (Sub-)Structure (building block) identification and linkage learning
* Integration of other machine learning techniques
* Mechanisms to improve scalability

4. Applications

* Data mining
* Bioinformatics and life sciences
* Rapid application development frameworks for GBML
* Robotics, engineering, hardware/software design, and control
* Cognitive systems and cognitive modeling
* Dynamic environments, time series and sequence learning
* Artificial Life
* Adaptive behavior
* Economic modelling
* Network security
* Other kinds of real-world applications

5. Related Activities

* Visualisation of all aspects of GBML (performance, final solutions, evolution of the population)
* Platforms for GBML, e.g. GPGPUs
* Competitive performance, e.g. GBML performance in Competitions and Awards
* Education and dissemination of GBML, e.g. software for teaching and exploring aspects of GBML.

All accepted papers will appear in the proceedings of GECCO 2013, which will be published by ACM (Association for Computing Machinery).

Important Dates:

January 23, 2013 – Paper submission deadline
April 17, 2013 – Camera-ready version of accepted articles
July 06-10, 2013 – GECCO 2013 Conference in Amsterdam, The Netherlands

Track Chairs:
- Jaume Bacardit,jaume.bacardit@nottingham.ac.uk
- Tim Kovacs,kovacs@cs.bris.ac.uk

GECCO 2012 Genetics-based Machine Learning track deadline extended to 27 Jan. 2012

will — Wed, 11 Jan 2012 02:24:09 +0000

The submission deadline for all tracks at GECCO 2012 has been extended to January 27, 2012

====================================================================
GECCO 2012: Call for Papers on GENETICS-BASED MACHINE LEARNING (GBML)

2012 Genetic and Evolutionary Computation Conference (GECCO-2012)
The largest conference in the field of evolutionary computation
July 7-11, Philadelphia, USA
http://www.sigevo.org/gecco-2012/

**Extended submission deadline: January 27, 2012**

Co-located with the International Workshop on Learning Classifier Systems (IWLCS)
====================================================================

The Genetics-Based Machine Learning (GBML) track at GECCO covers all advances in theory and application of evolutionary computation methods to Machine Learning (ML) problems.

Evolutionary methods have a range of uses in ML:
- addressing subproblems of ML e.g.
– feature selection and construction
– optimising parameters of other ML methods
- as learning methods e.g.
– generating classification hypotheses with Genetic Programming
– learning control systems or cognitive modelling with Learning Classifier Systems
- as meta-learners which adapt base learners e.g.
– evolving the structure and weights of neural networks
– evolving the data base and rule base in genetic fuzzy systems
– evolving ensembles of base learners
– evolving representations, update rules or algorithms for base learners

The global search performed by evolutionary methods can complement the local search of non-evolutionary methods and combinations of the two are particularly welcome.

Free tutorials include:
- Learning Classifier Systems
- Large Scale Data Mining using Genetics-Based Machine Learning

Track Chairs

Dr. Will Browne, Victoria University of Wellington, NZ (will.browne -at-
ecs -dot- vuw -dot- ac -dot- nz)

Dr. Tim Kovacs, University of Bristol, U.K. (kovacs -at- cs -dot- bris
-dot- ac -dot- uk)

OFP_CLASS: a hybrid method to generate optimized fuzzy partitions for classification

Community — Fri, 28 Oct 2011 16:44:55 +0000

Abstract

The discretization of values plays a critical role in data mining and knowledge discovery. The representation of information
through intervals is more concise and easier to understand at certain levels of knowledge than the representation by mean
continuous values. In this paper, we propose a method for discretizing continuous attributes by means of fuzzy sets, which
constitute a fuzzy partition of the domains of these attributes. This method carries out a fuzzy discretization of continuous
attributes in two stages. A fuzzy decision tree is used in the first stage to propose an initial set of crisp intervals, while
a genetic algorithm is used in the second stage to define the membership functions and the cardinality of the partitions.
After defining the fuzzy partitions, we evaluate and compare them with previously existing ones in the literature.

Content Type Journal Article
Category Original Paper
Pages 1-16
DOI 10.1007/s00500-011-0778-0
Authors
- Jose M. Cadenas, Dept. de Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- M. Carmen Garrido, Dept. de Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- Raquel Martínez, Dept. de Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- Piero P. Bonissone, GE Global Research, One Research Circle, Niskayuna, NY 12309, USA

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

How landscape ruggedness influences the performance of real-coded algorithms: a comparative study

Community — Sat, 15 Oct 2011 15:44:54 +0000

Abstract

Ruggedness has a strong influence on the performance of algorithms, but it has been barely studied in real-coded optimization,
mainly because of the difficulty of isolating it from a number of involved topological properties. In this paper, we propose
a framework consisting of increasing ruggedness function sets built by a mechanism which generates multiple funnels. This
mechanism introduces different levels of sinusoidal distortion which can be controlled to isolate the singular influence of
some related features. Some commonly used measures of ruggedness have been applied to analyze these sets of functions, and
a numerical study to compare the performance of some representative algorithms has been carried out. The results confirm that
ruggedness has an influence on the performance of the algorithm, proving that it depends on the multi-funnel structure and
peak features, such as height and relative size of the global peak, and not on the number of peaks.

Content Type Journal Article
Category Original Paper
Pages 1-16
DOI 10.1007/s00500-011-0781-5
Authors
- Jesús Marín, Department of Automatic Control (ESAII), Universitat Politècnica de Catalunya, EUETIB, Urgell 187, 08036 Barcelona, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Towards interval-based non-additive deconvolution in signal processing

Community — Sat, 15 Oct 2011 15:44:53 +0000

Abstract

Reconstructing a signal from its observations via a sensor device is usually called “deconvolution”. Such reconstruction requires
perfect knowledge of the impulse response of the sensor involved in the signal measurement. The lower this knowledge, the
more biased the reconstruction. In this paper, we present a novel method for reconstructing a signal measured by a sensor
whose impulse response is imprecisely known. This technique is based on modeling the relationship between the measurement
and the signal via a concave capacity and extending the convolution concept to a concave set of impulse responses. The reconstructed
signal is interval-valued, thus reflecting the poor knowledge of the sensor impulse response.

Content Type Journal Article
Category Focus
Pages 1-12
DOI 10.1007/s00500-011-0771-7
Authors
- Olivier Strauss, LIRMM Université Montpellier II, 161 rue Ada, 34392 Montpellier cedex 5, France
- Agnès Rico, LIRMM Université Montpellier II, 161 rue Ada, 34392 Montpellier cedex 5, France

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis

Community — Sat, 15 Oct 2011 15:44:51 +0000

Abstract

Using a statistical model in a diagnosis task generally requires a large amount of labeled data. When ground truth information
is not available, too expensive or difficult to collect, one has to rely on expert knowledge. In this paper, it is proposed
to use partial information from domain experts expressed as belief functions. Expert opinions are combined in this framework
and used with measurement data to estimate the parameters of a statistical model using a variant of the EM algorithm. The
particular application investigated here concerns the diagnosis of railway track circuits. A noiseless Independent Factor
Analysis model is postulated, assuming the observed variables extracted from railway track inspection signals to be generated
by a linear mixture of independent latent variables linked to the system component states. Usually, learning with this statistical
model is performed in an unsupervised way using unlabeled examples only. In this paper, it is proposed to handle this learning
process in a soft-supervised way using imperfect information on the system component states. Fusing partially reliable information
about cluster membership is shown to significantly improve classification results.

Content Type Journal Article
Category Focus
Pages 1-14
DOI 10.1007/s00500-011-0766-4
Authors
- Zohra L. Cherfi, GRETTIA, French Institute of Science and Technology for Transport, Development and Networks, Université Paris-Est, Marne-la-Vallée, France
- Latifa Oukhellou, LISSI, Université Paris-Est Créteil, Créteil, France
- Etienne Côme, GRETTIA, French Institute of Science and Technology for Transport, Development and Networks, Université Paris-Est, Marne-la-Vallée, France
- Thierry Denœux, HEUDIASYC, Université de Technologie de Compiègne, UMR CNRS 6599, Compiègne, France
- Patrice Aknin, GRETTIA, French Institute of Science and Technology for Transport, Development and Networks, Université Paris-Est, Marne-la-Vallée, France

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Missing data imputation for fuzzy rule-based classification systems

Community — Thu, 13 Oct 2011 15:47:01 +0000

Abstract

Fuzzy rule-based classification systems (FRBCSs) are known due to their ability to treat with low quality data and obtain
good results in these scenarios. However, their application in problems with missing data are uncommon while in real-life
data, information is frequently incomplete in data mining, caused by the presence of missing values in attributes. Several
schemes have been studied to overcome the drawbacks produced by missing values in data mining tasks; one of the most well
known is based on preprocessing, formerly known as imputation. In this work, we focus on FRBCSs considering 14 different approaches
to missing attribute values treatment that are presented and analyzed. The analysis involves three different methods, in which
we distinguish between Mamdani and TSK models. From the obtained results, the convenience of using imputation methods for
FRBCSs with missing values is stated. The analysis suggests that each type behaves differently while the use of determined
missing values imputation methods could improve the accuracy obtained for these methods. Thus, the use of particular imputation
methods conditioned to the type of FRBCSs is required.

Content Type Journal Article
Category Focus
Pages 1-19
DOI 10.1007/s00500-011-0774-4
Authors
- Julián Luengo, Deptartment of Computer Science and Artificial Intelligence, University of Granada, 18071 Granada, Spain
- José A. Sáez, Deptartment of Computer Science and Artificial Intelligence, University of Granada, 18071 Granada, Spain
- Francisco Herrera, Deptartment of Computer Science and Artificial Intelligence, University of Granada, 18071 Granada, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Extending information processing in a Fuzzy Random Forest ensemble

Community — Thu, 13 Oct 2011 15:47:01 +0000

Abstract

Imperfect information inevitably appears in real situations for a variety of reasons. Although efforts have been made to incorporate
imperfect data into classification techniques, there are still many limitations as to the type of data, uncertainty, and imprecision
that can be handled. In this paper, we will present a Fuzzy Random Forest ensemble for classification and show its ability
to handle imperfect data into the learning and the classification phases. Then, we will describe the types of imperfect data
it supports. We will devise an augmented ensemble that can operate with others type of imperfect data: crisp, missing, probabilistic
uncertainty, and imprecise (fuzzy and crisp) values. Additionally, we will perform experiments with imperfect datasets created
for this purpose and datasets used in other papers to show the advantage of being able to express the true nature of imperfect
information.

Content Type Journal Article
Category Focus
Pages 1-17
DOI 10.1007/s00500-011-0777-1
Authors
- Jose M. Cadenas, Dept. Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- M. Carmen Garrido, Dept. Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- Raquel Martínez, Dept. Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, Murcia, Spain
- Piero P. Bonissone, GE Global Research, One Research Circle, Niskayuna, NY 12309, USA

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Mining fuzzy association rules from low-quality data

Community — Thu, 13 Oct 2011 05:50:04 +0000

Abstract

Data mining is most commonly used in attempts to induce association rules from databases which can help decision-makers easily
analyze the data and make good decisions regarding the domains concerned. Different studies have proposed methods for mining
association rules from databases with crisp values. However, the data in many real-world applications have a certain degree
of imprecision. In this paper we address this problem, and propose a new data-mining algorithm for extracting interesting
knowledge from databases with imprecise data. The proposed algorithm integrates imprecise data concepts and the fuzzy apriori
mining algorithm to find interesting fuzzy association rules in given databases. Experiments for diagnosing dyslexia in early
childhood were made to verify the performance of the proposed algorithm.

Content Type Journal Article
Category Focus
Pages 1-19
DOI 10.1007/s00500-011-0775-3
Authors
- A. M. Palacios, Department of Computer Science, University of Oviedo, 33204 Gijón, Spain
- M. J. Gacto, Department of Computer Science, University of Jaén, 23071 Jaén, Spain
- J. Alcalá-Fdez, Department of Computer Science and Artificial Intelligence, CITIC-UGR, University of Granada, 18071 Granada, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

A fuzzy regression model based on distances and random variables with crisp input and fuzzy output data: a case study in biomass production

Community — Wed, 12 Oct 2011 16:05:48 +0000

Abstract

Least-squares technique is well-known and widely used to determine the coefficients of a explanatory model from observations
based on a concept of distance. Traditionally, the observations consist of pairs of numeric values. However, in many real-life
problems, the independent or explanatory variable can be observed precisely (for instance, the time) and the dependent or
response variable is usually described by approximate values, such as “about

£300

” or “approximately $500”, instead of exact values, due to sources of uncertainty that may affect the response. In this paper,
we present a new technique to obtain fuzzy regression models that consider triangular fuzzy numbers in the response variable.
The procedure solves linear and non-linear problems and is easy to compute in practice and may be applied in different contexts.
The usefulness of the proposed method is illustrated using simulated and real-life examples.

Content Type Journal Article
Category Focus
Pages 1-11
DOI 10.1007/s00500-011-0769-1
Authors
- C. Roldán, Department of Statistics and Operations, University of Jaén, Las Lagunillas s/n, Jaén, Spain
- A. Roldán, Department of Statistics and Operations, University of Jaén, Las Lagunillas s/n, Jaén, Spain
- J. Martínez-Moreno, Department of Mathematics, University of Jaén, Las Lagunillas s/n, Jaén, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Artificial immune optimization system solving constrained omni-optimization

Community — Wed, 12 Oct 2011 16:05:40 +0000

Abstract

This work investigates an artificial immune optimization system suitable for single and multi-objective constrained optimization.
In this optimizer, an evaluation index, which can decide the importance of individual in the current population, is developed
to accelerate population division; the niching-like proliferation scheme is introduced to strengthen the diversity of population.
Thereafter, those diverse antibodies, with the help of immune evolution operations, evolve their structures along different
directions. Theoretical results show that such optimization system is convergent with low computational complexity. Experimentally,
one such optimizer is sufficiently examined by a suite of single and multi-objective test problems. Comparative experiments
illustrate that the optimizer with some striking characteristics is a potentially alternative optimization tool for constrained
omni-optimization.

Content Type Journal Article
Category Research Paper
Pages 1-16
DOI 10.1007/s12065-011-0064-1
Authors
- Zhuhong Zhang, Institute of System Science and Information Technology, College of Science, Guizhou University, Guiyang, 550025 Guizhou, People’s Republic of China

Journal Evolutionary Intelligence
Online ISSN 1864-5917
Print ISSN 1864-5909

A cooperative coevolutionary approach dealing with the skull–face overlay uncertainty in forensic identification by craniofacial superimposition

Community — Wed, 12 Oct 2011 05:45:04 +0000

Abstract

Craniofacial superimposition is a forensic process where photographs or video shots of a missing person are compared with
the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned three-dimensional
skull model against the face photo/video shot), the forensic anthropologist can try to establish whether that is the same
person. The whole process is influenced by inherent uncertainty mainly because two objects of different nature (a skull and
a face) are involved. In previous work, we categorized the different sources of uncertainty and introduced the use of imprecise
landmarks to tackle most of them. In this paper, we propose a novel approach, a cooperative coevolutionary algorithm, to deal
with the use of imprecise cephalometric landmarks in the skull–face overlay process, the main task in craniofacial superimposition.
Following this approach we are able to look for both the best projection parameters and the best landmark locations at the
same time. Coevolutionary skull–face overlay results are compared with our previous fuzzy-evolutionary automatic method. Six
skull–face overlay problem instances corresponding to three real-world cases solved by the Physical Anthropology Lab at the
University of Granada (Spain) are considered. Promising results have been achieved, dramatically reducing the run time while
improving the accuracy and robustness.

Content Type Journal Article
Category Focus
Pages 1-12
DOI 10.1007/s00500-011-0770-8
Authors
- O. Ibáñez, European Centre for Soft Computing, 33600 Mieres, Asturias, Spain
- O. Cordón, European Centre for Soft Computing, 33600 Mieres, Asturias, Spain
- S. Damas, European Centre for Soft Computing, 33600 Mieres, Asturias, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

New algorithms for finding approximate frequent item sets

Community — Mon, 10 Oct 2011 15:01:03 +0000

Abstract

In standard frequent item set mining a transaction supports an item set only if all items in the set are present. However,
in many cases this is too strict a requirement that can render it impossible to find certain relevant groups of items. By
relaxing the support definition, allowing for some items of a given set to be missing from a transaction, this drawback can
be amended. The resulting item sets have been called approximate, fault-tolerant or fuzzy item sets. In this paper we present
two new algorithms to find such item sets: the first is an extension of item set mining based on cover similarities and computes
and evaluates the subset size occurrence distribution with a scheme that is related to the Eclat algorithm. The second employs
a clustering-like approach, in which the distances are derived from the item covers with distance measures for sets or binary
vectors and which is initialized with a one-dimensional Sammon projection of the distance matrix. We demonstrate the benefits
of our algorithms by applying them to a concept detection task on the 2008/2009 Wikipedia Selection for schools and to the
neurobiological task of detecting neuron ensembles in (simulated) parallel spike trains.

Content Type Journal Article
Category Focus
Pages 1-15
DOI 10.1007/s00500-011-0776-2
Authors
- Christian Borgelt, European Centre for Soft Computing, c/ Gonzalo Gutiérrez Quirós s/n, 33600 Mieres (Asturias), Spain
- Christian Braune, European Centre for Soft Computing, c/ Gonzalo Gutiérrez Quirós s/n, 33600 Mieres (Asturias), Spain
- Tobias Kötter, Department of Computer Science, University of Konstanz, Box 712, 78457 Constance, Germany
- Sonja Grün, RIKEN Brain Science Institute, Wako-Shi, Saitama 351-0198, Japan

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Evolutionary computation as an artificial attacker: generating evasion attacks for detector vulnerability testing

Community — Sat, 08 Oct 2011 15:43:59 +0000

Abstract

Intrusion detection systems protect our infrastructures by monitoring for signs of intrusions. However, intrusion detection
systems are themselves susceptible to vulnerabilities, which the attackers take advantage of to evade detection. In particular,
we focus on evasion attacks in which the attacker aims to generate a stealthy attack that eliminates or minimizes the likelihood
of detection. Attackers achieve stealth by mimicking normal behaviour while achieving the attack goals, hence bypassing the
detector. Previous work focused on generating evasion attacks using the internal knowledge of the detectors, hence adopting
a ‘white-box’ access to the detector. On the other hand, we adopt a ‘black-box’ approach and propose an evolutionary attacker
based on Genetic Programming. The access of our ‘black-box’ approach is limited to the feedback of the detector such as anomaly
rates and delays. We compare our ‘black-box’ approach with various ‘white-box’ approaches to investigate its effectiveness.
In doing so, the impact of anomalies from the break-in stage of the attacks and the delays based on locality frame counts
are also discussed. This is particularly important if the performance comparison is to reflect the real capabilities of detectors.

Content Type Journal Article
Category Research Paper
Pages 1-24
DOI 10.1007/s12065-011-0065-0
Authors
- Hilmi Güneş Kayacık, School of Computer Science, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
- A. Nur Zincir-Heywood, Faculty of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS B3H 1W5, Canada
- Malcolm I. Heywood, Faculty of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS B3H 1W5, Canada

Journal Evolutionary Intelligence
Online ISSN 1864-5917
Print ISSN 1864-5909

Singular spectral analysis of ill-known signals and its application to predictive maintenance of windmills with SCADA records

Community — Fri, 07 Oct 2011 15:57:11 +0000

Abstract

A generalization of the singular spectral analysis (SSA) technique to ill-defined data is introduced in this paper. The proposed
algorithm achieves tight estimates of the energy of irregular or aperiodic oscillations from records of interval or fuzzy-valued
signals. Fuzzy signals are given a possibilistic interpretation as families of nested confidence intervals. In this context,
some types of Supervisory Control And Data Analysis (SCADA) records, where the minimum, mean and maximum values of the signal
between two scans are logged, are regarded as fuzzy constrains of the values of the sampled signal. The generalized SSA of
these records produces a set of interval-valued or fuzzy coefficients, that bound the spectral transform of the SCADA data.
Furthermore, these bounds are compared to the expected energy of AR(1) red noise, and the irrelevant components are discarded.
This comparison is accomplished using statistical tests for low quality data, that are in turn consistent with the possibilistic
interpretation of a fuzzy signal mentioned before. Generalized SSA has been applied to solve a real world problem, with SCADA
data taken from 40 turbines in a Spanish wind farm. It was found that certain oscillations in the pressure at the hydraulic
circuit of the tip brakes are correlated to long term damages in the windmill gear, showing that this new technique is useful
as a failure indicator in the predictive maintenance of windmills.

Content Type Journal Article
Category Focus
Pages 1-14
DOI 10.1007/s00500-011-0767-3
Authors
- Luciano Sánchez, Computer Science Department, University of Oviedo, Campus de Viesques, 33071 Gijón, Asturias, Spain
- Inés Couso, Facultad de Ciencias, Statistics Department, University of Oviedo, 33071 Oviedo, Asturias, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Guest editorial: special issue on “knowledge extraction from low quality data: theoretical, methodological and practical issues”

Community — Thu, 06 Oct 2011 06:28:11 +0000

Guest editorial: special issue on “knowledge extraction from low quality data: theoretical, methodological and practical issues”

Content Type Journal Article
Category Editorial
Pages 1-2
DOI 10.1007/s00500-011-0765-5
Authors
- Luciano Sánchez, Computer Science Department, University of Oviedo, Campus de Viesques, 33071 Gijón, Asturias, Spain
- Inés Couso, Statistics Department, University of Oviedo, Facultad de Ciencias, 33071 Oviedo, Asturias, Spain

Journal Soft Computing – A Fusion of Foundations, Methodologies and Applications
Online ISSN 1433-7479
Print ISSN 1432-7643

Response to the review of "Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach"

Community — Mon, 03 Oct 2011 18:44:00 +0000

Trent McConaghy, coauthor of Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach, wrote a response to the review of the book in Genetic Programming and Evolvable Machines and I have agreed to publish his response here. Trent’s letter follows:

In the December issue of Genetic Programming and Evolvable Machines (volume 12:4), John Rieffel gave a review of the book “Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach”, of which I was a co-author.

We would like to express our thanks to John for a thoughtful review, covering the reliable and trustworthy approaches to perform industrially-oriented symbolic regression, robust optimization, and analog structural synthesis.

We would like to clarify one point: while the review reports that the book ignores “simulators that cheat”, the book in fact dedicates substantial space on this issue, and how open-ended synthesis approaches are highly prone to it. (See pp. 157-167, including the section “SPICE can lie”.)

The broader issue — trustworthy synthesis — is a broad challenge that the last half of the book addresses. Trustworthy synthesis outputs circuits that a designer trusts enough to commit to silicon. The book proposes to use hierarchical building blocks developed over the decades by expert designers, enabling synthesis to output circuits that are trustworthy by construction.

As the book discusses, the computational intelligence techniques presented generalize beyond analog CAD, to domains such as robotics, financial engineering, mechanical design, and more.

– Trent McConaghy, October 3, 2011

Response to the review of "Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach"

Community — Mon, 03 Oct 2011 18:44:00 +0000

In the December issue of Genetic Programming and Evolvable Machines (volume 12:4), John Rieffel gave a review of the book “Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach”, of which I was a co-author.

We would like to express our thanks to John for a thoughtful review, covering the reliable and trustworthy approaches to perform industrially-oriented symbolic regression, robust optimization, and analog structural synthesis.

We would like to clarify one point: while the review reports that the book ignores “simulators that cheat”, the book in fact dedicates substantial space on this issue, and how open-ended synthesis approaches are highly prone to it. (See pp. 157-167, including the section “SPICE can lie”.)

The broader issue — trustworthy synthesis — is a broad challenge that the last half of the book addresses. Trustworthy synthesis outputs circuits that a designer trusts enough to commit to silicon. The book proposes to use hierarchical building blocks developed over the decades by expert designers, enabling synthesis to output circuits that are trustworthy by construction.

As the book discusses, the computational intelligence techniques presented generalize beyond analog CAD, to domains such as robotics, financial engineering, mechanical design, and more.

– Trent McConaghy, October 3, 2011

Response to the review of "Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach"

Community — Mon, 03 Oct 2011 18:44:00 +0000

In the December issue of Genetic Programming and Evolvable Machines (volume 12:4), John Rieffel gave a review of the book “Variation-Aware Analog Structural Synthesis: A Computational Intelligence Approach”, of which I was a co-author.

We would like to express our thanks to John for a thoughtful review, covering the reliable and trustworthy approaches to perform industrially-oriented symbolic regression, robust optimization, and analog structural synthesis.

We would like to clarify one point: while the review reports that the book ignores “simulators that cheat”, the book in fact dedicates substantial space on this issue, and how open-ended synthesis approaches are highly prone to it. (See pp. 157-167, including the section “SPICE can lie”.)

The broader issue — trustworthy synthesis — is a broad challenge that the last half of the book addresses. Trustworthy synthesis outputs circuits that a designer trusts enough to commit to silicon. The book proposes to use hierarchical building blocks developed over the decades by expert designers, enabling synthesis to output circuits that are trustworthy by construction.

As the book discusses, the computational intelligence techniques presented generalize beyond analog CAD, to domains such as robotics, financial engineering, mechanical design, and more.

– Trent McConaghy, October 3, 2011