Tag: Soft Computing – A Fusion of Foundations, Methodologies and Applications

State BL-algebras

Abstract  The concept of a state MV-algebra was firstly introduced by Flaminio and Montagna (An algebraic approach to states on MV-algebras.
In: Novák V (ed) Fuzzy logic 2, proceedings of the 5th EUSFLAT conference, September 11–14, Ostra…

Abstract  

The concept of a state MV-algebra was firstly introduced by Flaminio and Montagna (An algebraic approach to states on MV-algebras.
In: Novák V (ed) Fuzzy logic 2, proceedings of the 5th EUSFLAT conference, September 11–14, Ostrava, vol II, pp 201–206, 2007; Int J Approx Reason 50:138–152, 2009) as an MV-algebra with internal state as a unary operation. Di Nola and Dvurečenskij (Ann Pure Appl Logic 161:161–173, 2009a; Math Slovaca 59:517–534, 2009b) gave a stronger version of a state MV-algebra. In the present paper, we introduce the notion of a state BL-algebra, or more
precisely, a BL-algebra with internal state. We present different types of state BL-algebras, like strong state BL-algebras
and state-morphism BL-algebras, and we study some classes of state BL-algebras. In addition, we give a sample of important
examples of state BL-algebras and present some open problems.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0571-5
  • Authors
    • Lavinia Corina Ciungu, Polytechnical University of Bucharest Splaiul Independenţei 113 Bucharest Romania
    • Anatolij Dvurečenskij, Slovak Academy of Sciences Mathematical Institute Štefánikova 49 814 73 Bratislava Slovakia
    • Marek Hyčko, Slovak Academy of Sciences Mathematical Institute Štefánikova 49 814 73 Bratislava Slovakia

The variety generated by semi-Heyting chains

Abstract  The purpose of this paper was to investigate the structure of semi-Heyting chains and the variety

CSH
generated by them. We determine the number of non-isomorphic n-element semi-Heyting chains. As a contribution to the study of t…

Abstract  

The purpose of this paper was to investigate the structure of semi-Heyting chains and the variety

CSH

generated by them. We determine the number of non-isomorphic n-element semi-Heyting chains. As a contribution to the study of the lattice of subvarieties of

CSH,

we investigate the inclusion relation between semi-Heyting chains. Finally, we provide equational bases for

CSH

and for the subvarieties of

CSH

introduced in [5].

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0604-0
  • Authors
    • M. Abad, Universidad Nacional del Sur Departamento de Matemática 8000 Bahía Blanca Argentina
    • J. M. Cornejo, Universidad Nacional del Sur Departamento de Matemática 8000 Bahía Blanca Argentina
    • J. P. Díaz Varela, Universidad Nacional del Sur Departamento de Matemática 8000 Bahía Blanca Argentina

Heuristic search for optimizing diffusion of influence in a social network under the resource constraint

Abstract  The diffusion of influence in a social network has been recently investigated in various fields. In this paper, we study the
problem of minimizing the expected complete influence time of a social network under the resource constrai…

Abstract  

The diffusion of influence in a social network has been recently investigated in various fields. In this paper, we study the
problem of minimizing the expected complete influence time of a social network under the resource constraint. We focus on
the case where the budget for influencing the initial target set of individuals is limited. The incremental chance model is
adopted to characterize the diffusion of influence, and a lower bound for the expected complete influence time is presented.
In order to solve the problem effectively, we modify the well-known heuristic search approach, the A* algorithm, and provide a series of strategies for designing the heuristic functions. Finally, we perform experiments to
show that the proposed algorithm generally performs better than widely used trivial heuristic methods.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0601-3
  • Authors
    • Yaodong Ni, University of International Business and Economics School of Information Technology and Management Beijing China
    • Zhi-Qiang Liu, City University of Hong Kong School of Creative Media Hong Kong China

Pattern classification based on k locally constrained line

Abstract  A simple yet effective learning algorithm, k locally constrained line (k-LCL), is presented for pattern classification. In k-LCL, any two prototypes of the same class are extended to a constrained line (CL), through which the repres…

Abstract  

A simple yet effective learning algorithm, k locally constrained line (k-LCL), is presented for pattern classification. In k-LCL, any two prototypes of the same class are extended to a constrained line (CL), through which the representational capacity
of the training set is largely improved. Because each CL is adjustable in length, k-LCL can well avoid the “intersecting” of training subspaces in most traditional feature classifiers. Moreover, to speed up
the calculation, k-LCL classifies an unknown sample focusing only on its local CLs in each class. Experimental results, obtained on both synthetic
and real-world benchmark data sets, show that the proposed method has better accuracy and efficiency than most existing feature
line methods.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0602-2
  • Authors
    • Jianjun Qing, Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China
    • Hong Huo, Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China
    • Tao Fang, Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China

A new initialization procedure for the distributed estimation of distribution algorithms

Abstract  Estimation of distribution algorithms (EDAs) are one of the most promising paradigms in today’s evolutionary computation.
In this field, there has been an incipient activity in the so-called parallel estimation of distribution al…

Abstract  

Estimation of distribution algorithms (EDAs) are one of the most promising paradigms in today’s evolutionary computation.
In this field, there has been an incipient activity in the so-called parallel estimation of distribution algorithms (pEDAs).
One of these approaches is the distributed estimation of distribution algorithms (dEDAs). This paper introduces a new initialization
mechanism for each of the populations of the islands based on the Voronoi cells. To analyze the results, a series of different
experiments using the benchmark suite for the special session on Real-parameter Optimization of the IEEE CEC 2005 conference
has been carried out. The results obtained suggest that the Voronoi initialization method considerably improves the performance
obtained from a traditional uniform initialization.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0603-1
  • Authors
    • Santiago Muelas, Universidad Politécnica de Madrid Department of Computer Systems Architecture and Technology, Facultad de Informática Madrid Spain
    • José-María Peña, Universidad Politécnica de Madrid Department of Computer Systems Architecture and Technology, Facultad de Informática Madrid Spain
    • Antonio LaTorre, Universidad Politécnica de Madrid Department of Computer Systems Architecture and Technology, Facultad de Informática Madrid Spain
    • Víctor Robles, Universidad Politécnica de Madrid Department of Computer Systems Architecture and Technology, Facultad de Informática Madrid Spain

A neural network-based multi-agent classifier system with a Bayesian formalism for trust measurement

Abstract  In this paper, a neural network (NN)-based multi-agent classifier system (MACS) utilising the trust-negotiation-communication
(TNC) reasoning model is proposed. A novel trust measurement method, based on the combination of Bayesian…

Abstract  

In this paper, a neural network (NN)-based multi-agent classifier system (MACS) utilising the trust-negotiation-communication
(TNC) reasoning model is proposed. A novel trust measurement method, based on the combination of Bayesian belief functions,
is incorporated into the TNC model. The Fuzzy Min-Max (FMM) NN is used as learning agents in the MACS, and useful modifications
of FMM are proposed so that it can be adopted for trust measurement. Besides, an auctioning procedure, based on the sealed
bid method, is applied for the negotiation phase of the TNC model. Two benchmark data sets are used to evaluate the effectiveness
of the proposed MACS. The results obtained compare favourably with those from a number of machine learning methods. The applicability
of the proposed MACS to two industrial sensor data fusion and classification tasks is also demonstrated, with the implications
analysed and discussed.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0592-0
  • Authors
    • Anas Quteishat, Al-Balqa’ Applied University Department of Computer Engineering, Faculty of Engineering Technology Al-Salt Jordan
    • Chee Peng Lim, University of Science Malaysia School of Electrical and Electronic Engineering Engineering Campus, 14300 Nibong Tebal Penang Malaysia
    • Junita Mohamad Saleh, University of Science Malaysia School of Electrical and Electronic Engineering Engineering Campus, 14300 Nibong Tebal Penang Malaysia
    • Jeffrey Tweedale, University of South Australia School of Electrical and Information Engineering Adelaide Australia
    • Lakhmi C. Jain, University of South Australia School of Electrical and Information Engineering Adelaide Australia

State operators on GMV algebras

Abstract  Flaminio and Montagna recently introduced state

MV
algebras as

MV
algebras with an internal state in the form of a unary operation. Di Nola and Dvurečenskij further presented a stronger variation
of state

MV
algebras call…

Abstract  

Flaminio and Montagna recently introduced state

MV

algebras as

MV

algebras with an internal state in the form of a unary operation. Di Nola and Dvurečenskij further presented a stronger variation
of state

MV

algebras called state-morphism

MV

algebras. In the paper we present state

GMV

algebras and state-morphism

GMV

algebras which are non-commutative generalizations of the mentioned algebras.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0568-0
  • Authors
    • Jiří Rachůnek, Palacký University Department of Algebra and Geometry, Faculty of Sciences Tomkova 40 779 00 Olomouc Czech Republic
    • Dana Šalounová, VŠB-Technical University Ostrava Department of Mathematical Methods in Economy, Faculty of Economics Sokolská 33 701 21 Ostrava Czech Republic

Clustering of protein expression data: a benchmark of statistical and neural approaches

Abstract  Clustering issues are fundamental to exploratory analysis of bioinformatics data. This process may follow algorithms that
are reproducible but make assumptions about, for instance, the ability to estimate the global structure by su…

Abstract  

Clustering issues are fundamental to exploratory analysis of bioinformatics data. This process may follow algorithms that
are reproducible but make assumptions about, for instance, the ability to estimate the global structure by successful local
agglomeration or alternatively, they use pattern recognition methods that are sensitive to the initial conditions. This paper
reviews two clustering methodologies and highlights the differences that result from the changes in data representation, applied
to a protein expression data set for breast cancer (n = 1,076). The two clustering methodologies are a reproducible approach to model-free clustering and a probabilistic competitive
neural network. The results from the two methods are compared with existing studies of the same data set, and the preferred
clustering solutions are profiled for clinical interpretation.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0596-9
  • Authors
    • I. H. Jarman, Liverpool John Moores University School of Computing and Mathematical Sciences Liverpool UK
    • T. A. Etchells, Liverpool John Moores University School of Computing and Mathematical Sciences Liverpool UK
    • D. Bacciu, University of Pisa Department of Computer Science Pisa Italy
    • J. M. Garibaldi, University of Nottingham School of Computer Science Nottingham UK
    • I. O. Ellis, University of Nottingham Department of Histopathology, School of Molecular Medical Sciences Nottingham UK
    • P. J. G. Lisboa, Liverpool John Moores University School of Computing and Mathematical Sciences Liverpool UK

Simulated annealing for supervised gene selection

Abstract  Genomic data, and more generally biomedical data, are often characterized by high dimensionality. An input selection procedure
can attain the two objectives of highlighting the relevant variables (genes) and possibly improving clas…

Abstract  

Genomic data, and more generally biomedical data, are often characterized by high dimensionality. An input selection procedure
can attain the two objectives of highlighting the relevant variables (genes) and possibly improving classification results.
In this paper, we propose a wrapper approach to gene selection in classification of gene expression data using simulated annealing
along with supervised classification. The proposed approach can perform global combinatorial searches through the space of
all possible input subsets, can handle cases with numerical, categorical or mixed inputs, and is able to find (sub-)optimal
subsets of inputs giving low classification errors. The method has been tested on publicly available bioinformatics data sets
using support vector machines and on a mixed type data set using classification trees. We also propose some heuristics able
to speed up the convergence. The experimental results highlight the ability of the method to select minimal sets of relevant
features.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0597-8
  • Authors
    • Maurizio Filippone, University of Glasgow Department of Computing Science Sir Alwyn Williams Building G12 8QQ Glasgow UK
    • Francesco Masulli, University of Genova Department of Computer and Information Sciences Genoa Italy
    • Stefano Rovetta, University of Genova Department of Computer and Information Sciences Genoa Italy

Continuous-action reinforcement learning with fast policy search and adaptive basis function selection

Abstract  As an important approach to solving complex sequential decision problems, reinforcement learning (RL) has been widely studied
in the community of artificial intelligence and machine learning. However, the generalization ability of …

Abstract  

As an important approach to solving complex sequential decision problems, reinforcement learning (RL) has been widely studied
in the community of artificial intelligence and machine learning. However, the generalization ability of RL is still an open
problem and it is difficult for existing RL algorithms to solve Markov decision problems (MDPs) with both continuous state
and action spaces. In this paper, a novel RL approach with fast policy search and adaptive basis function selection, which
is called Continuous-action Approximate Policy Iteration (CAPI), is proposed for RL in MDPs with both continuous state and
action spaces. In CAPI, based on the value functions estimated by temporal-difference learning, a fast policy search technique
is suggested to search for optimal actions in continuous spaces, which is computationally efficient and easy to implement.
To improve the generalization ability and learning efficiency of CAPI, two adaptive basis function selection methods are developed
so that sparse approximation of value functions can be obtained efficiently both for linear function approximators and kernel
machines. Simulation results on benchmark learning control tasks with continuous state and action spaces show that the proposed
approach not only can converge to a near-optimal policy in a few iterations but also can obtain comparable or even better
performance than Sarsa-learning, and previous approximate policy iteration methods such as LSPI and KLSPI.

  • Content Type Journal Article
  • DOI 10.1007/s00500-010-0581-3
  • Authors
    • Xin Xu, National University of Defense Technology College of Mechatronics and Automation, Institute of Automation ChangSha Hunan 410073 People’s Republic of China
    • Chunming Liu, National University of Defense Technology College of Mechatronics and Automation, Institute of Automation ChangSha Hunan 410073 People’s Republic of China
    • Dewen Hu, National University of Defense Technology College of Mechatronics and Automation, Institute of Automation ChangSha Hunan 410073 People’s Republic of China