Abstract: Neuro-fuzzy systems have attracted growing interest of researchers in various scientific and engineering areas due to the increasing need of intelligent systems. This paper evaluates the use of two popular soft computing techniques and conventional statistical approach based on Box–Jenkins autoregressive integrated moving average (ARIMA) model to predict electricity demand in the State of Victoria, Australia. The soft computing methods considered are an evolving fuzzy neural network (EFuNN) and an artificial neural network (ANN) trained using scaled conjugate gradient algorithm (CGA) and backpropagation (BP) algorithm. The forecast accuracy is compared with the forecasts used by Victorian Power Exchange (VPX) and the actual energy demand. To evaluate, we considered load demand patterns for 10 consecutive months taken every 30 min for training the different prediction models. Test results show that the neuro-fuzzy system performed better than neural networks, ARIMA model and the VPX forecasts. © 2001 Elsevier Science B.V. All rights reserved.

Abstract: As private transport concerns, the global challenge of this millennium is the reduction of carbon dioxide emissions from passenger cars by improving fuel economy without sacrificing the vehicle performance. Hybrid electric vehicles powertrain, combining electric motor with an auxiliary power unit, can improve effectively the vehicle performance and fuel economy, reducing at the same time the effects of the use of private cars on the air quality of the cities. These advantages can be achieved only if the design of the powertrain is inspired to the minimisation of the main figures of merit holding in consideration many general aspects and variables. As supporting methodology in developing this difficult activity, a genetic-based sizing methodology will be presented. It will be aimed to minimise a function objective which takes into account not only technical specifications but also environmental, social, and economic aspects. Some interesting simulation results will be reported to prove the validity of the methodology, which will contribute to a substantial reduction of the pollutant emissions from hybrid electric vehicles.

Abstract: This paper deals with the problem of rule interpolation and rule extrapolation for fuzzy and possibilistic systems. Such systems are used for representing and processing vague linguistic If-Then-rules, and they have been increasingly applied in the field of control engineering, pattern recognition and expert systems. The methodology of rule interpolation is required for deducing plausible conclusions from sparse (incomplete) rule bases. For this purpose the well-known fuzzy inference mechanisms have to be extended or replaced by more general ones. The methods proposed so far in the literature for rule interpolation are mainly conceived for the application to fuzzy control and miss certain logical characteristics of an inference. First, a set of axioms is proposed in this paper. With this, a definition is given for the notion of interpolation, extrapolation, linear interpolation and linear extrapolation of fuzzy rules. The axioms include all the conditions that have been of interest in the previous attempts and others which either have logical characteristics or try to capture the linearity of the interpolation. A new method for linear interpolation and extrapolation of compact fuzzy quantities of the real line is suggested and analyzed in the spirit of the given definition. The method is extended to non-linear interpolation and extrapolation as well.

Abstract: Designing effective control strategies for asynchronous transfer mode (ATM) networks is known to be difficult because of the complexity of the structure of networks, nature of the services supported, and variety of dynamic parameters involved. Additionally, the uncertainties involved in identification of the network parameters cause analytical modeling of ATM networks to be almost impossible. This renders the application of classical control system design methods (which rely on the availability of these models) to the problem even harder. Consequently, a number of researchers are looking at alternative non-analytical control system design and modeling techniques that have the ability to cope with these difficulties to devise effective, robust ATM network management schemes. Those schemes employ artificial neural networks, fuzzy systems and design methods based on evolutionary computation. In this survey, the current state of ATM network management research employing these techniques as reported in the technical literature is summarized. The salient features of the methods employed are reviewed.

Abstract: Fuzzy classification systems is defined in this paper as an aggregative model, in such a way that Ruspini classical definition of fuzzy partition appears as a particular case. Once a basic recursive model has been accepted, we then propose to analyze relevance and redundancy in order to allow the possibility of learning from previous experiences. All these concepts are applied to a real picture, showing that our approach allows to check quality of such a classification system.

Abstract: Electronic circuit production is a significant industry. Ever more complex behaviors are being demanded from electronic circuits, fuelled by relentless improvements in circuit embodiment technologies. Consequently a bottleneck is developing at the point of circuit design. Traditional circuit design methodologies rely on rules that have been developed over many decades. However the need for human input to the increasingly complex design process means that modern circuit production takes one of two paths. The first is to employ more designers with greater expertise. This is expensive. The second is to simplify circuit design by imposing greater and greater abstraction to the design space. An example of this is the use of hardware description languages. This results in mounting waste of potential circuit behavior.

Abstract: The use of evolutionary computing techniques in coevolutionary/multi-agent systems is becoming increasingly popular. This paper presents simple models of the genetic algorithm in such systems, with the aim of examining the effects of different types of interdependence between individuals. Using the model it is shown that, for a fixed amount of interdependence between coevolving individuals, the existence of partner gene variance and the level at which fitness is applied can have significant effects, as does the evaluation partnering strategy used.

Abstract: QSAR (quantitative structure activity relationship) is a discipline within computational chemistry that deals with predictive modeling, often for relatively small datasets where the number of features might exceed the number of data points, leading to extreme dimensionality problems. The paper addresses a novel feature selection procedure for QSAR based on genetic algorithms to reduce the curse of dimensionality problem. In this case the genetic algorithm minimizes a cost function derived from the correlation matrix between the features and the activity of interest that is being modeled. From a QSAR dataset with 160 features, the genetic algorithm selected a feature subset (40 features), which built a better predictive model than with full feature set. The results for feature reduction with genetic algorithm were also compared with neural network sensitivity analysis.

Abstract: We describe in this paper a new method for adaptive model-based control of non-linear dynamic plants using Neural Networks, Fuzzy Logic and Fractal Theory. The new neuro-fuzzy-fractal method combines Soft Computing (SC) techniques with the concept of the fractal dimension for the domain of Non-Linear Dynamic Plant Control. The new method for adaptive model-based control has been implemented as a computer program to show that our neuro-fuzzy-fractal approach is a good alternative for controlling non-linear dynamic plants. We illustrate in this paper our new methodology with the case of controlling biochemical reactors in the food industry. For this case, we use mathematical models for the simulation of bacteria growth for several types of food. The goal of constructing these models is to capture the dynamics of bacteria population in food, so as to have a way of controlling this dynamics for industrial purposes.

Abstract: This paper describes the application of genetic algorithms (GA) to identify a class of nonlinear SISO models composed of a memoryless nonlinearity in series with a linear transfer function. In contrast with recent literature on the considered problem, we encode in the chromosomes also the structure of the model (type of nonlinearity, number of zeros and poles), and use the GA to identify both the optimal structure and the associated parameters. New operators for mutation and crossover to deal with chromosomes with variable length are introduced. The effectiveness of the approach is tested on a set of case studies derived from literature.

Abstract: In this article we investigate a problem within Dempster–Shafer theory where 2 q −1 pieces of evidence are clustered into q clusters by minimizing a metaconflict function, or equivalently, by minimizing the sum of weight of conflict over all clusters. Previously one of us developed a method based on a Hopfield and Tank model. However, for very large problems we need a method with lower computational complexity. We demonstrate that the weight of conflict of evidence can, as an approximation, be linearized and mapped to an antiferromagnetic Potts spin model. This facilitates efficient numerical solution, even for large problem sizes. Optimal or nearly optimal solutions are found for Dempster–Shafer clustering benchmark tests with a time complexity of approximately O(N 2log2 N). Furthermore, an isomorphism between the antiferromagnetic Potts spin model and a graph optimization problem is shown. The graph model has dynamic variables living on the links, which have a priori probabilities that are directly related to the pairwise conflict between pieces of evidence. Hence, the relations between three different models are shown.

Abstract: This paper presents a novel hybrid of the two complimentary technologies of soft computing viz. neural networks and fuzzy logic to design a fuzzy rule based pattern classifier for problems with higher dimensional feature spaces. The neural network component of the hybrid, which acts as a pre-processor, is designed to take care of the all-important issue of feature selection. To circumvent the disadvantages of the popular back propagation algorithm to train the neural network, a meta-heuristic viz. threshold accepting (TA) has been used instead. Then, a fuzzy rule based classifier takes over the classification task with a reduced feature set. A combinatorial optimisation problem is formulated to minimise the number of rules in the classifier while guaranteeing high classification power. A modified threshold accepting algorithm proposed elsewhere by the authors (Ravi V, Zimmermann H.-J. (2000) Eur J Oper Res 123: 16–28) has been employed to solve this optimization problem. The proposed methodology has been demonstrated for (1) the wine classification problem having 13 features and (2) the Wisconsin breast cancer determination problem having 9 features. On the basis of these examples the results seem to be very interesting, as there is no reduction in the classification power in either of the problems, despite the fact that some of the original features have been completely eliminated from the study. On the contrary, the chosen features in both the problems yielded 100% classification power in some cases.

Abstract: Adleman showed that hybridization of pairs of complementary DNA strands could be used for molecular computation. We have explored the possibility that a neural network in which the usual axons and neurons are replaced by the diffusion and molecular recognition of DNA is a possible route to fault-tolerant molecular computation. In this paper we review our model for a DNA analog neural network, estimate the ultimate speed of DNA computations, present an enzymatic representation of DNA matrix algebra and show some exploratory experimental results. We discuss the basis for our optimism on the prospects for practical DNA computing.

Abstract: A new neural network technology was developed to improve the diagnosis of breast cancer using mammogram findings. The paradigm, adaptive boosting (AB), uses a markedly different theory in solving the computational intelligence (CI) problem. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than "random" performance (i.e., approximately 55%) when processing a mammogram training set. By successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves performance of the basic evolutionary programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization, focused on improving specificity and positive predictive value at very high sensitivities, with an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, this hybrid, on average, was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.

Abstract: The pseudo MV-algebras were defined in [12] as non-commutative extensions of MV-algebras. In this paper we define the local pseudo MV-algebras and we suggest a classification for these structures. The subclass of perfect pseudo MV-algebras is deeply investigated. Extending the Di Nola–Lettieri result for MV-algebras [8], we prove that the category of l-groups is equivalent to a subcategory of perfect pseudo MV-algebras.

Abstract: In this paper we show two new learning algorithms for a fuzzy min–max neural network. The top down fuzzy min–max (TDFMM) algorithm modifies the classic Simpson's learning algorithm overcoming its main difficulties: the dependence on the presentation order of the patterns and the poor resolutive adaptation to the characteristics of input space. The top down fuzzy min–max regressor (TDFMMR) algorithm extends our neural network to solve regression problems by using a hybrid fuzzy classifier and a gradient descent algorithm.

Abstract: This short paper has two goals. The first is to show a new axiomatic system of product fuzzy logic with only one non-BL axiom which has only two variables. The second goal is to prove that there cannot be any axiomatic system of the product fuzzy logic with single non-BL axiom with only one variable.

Abstract: Swarm intelligence is a new challenging branch of artificial life which takes advantage of the collective behaviour of animals with limited intellectual faculties (insects, flocking birds, schools of fish) to solve algorithmically complex problems. Recently a new routing method based on the way that ants are communicating with each other has been applied to solve routing problems in telecommunication networks. This paper examines the behavior of an ant based decentralised router using an adequate set of commonly acceptable and some newly introduced metrics.

Abstract: A computer-aided diagnosis system for pneumoconiosis using a neural network is presented. The rounded opacities on the pneumoconiosis X-ray photographs are picked up quickly through a backpropagation (BP) neural network with several typical training patterns. Training patterns from 0.6 to 4.0 mm in diameter are made as simple circles. The main problem for automatic pneumoconiosis diagnosis in the past has been to reject unnecessary parts, like ribs and blood vessel shadows. In this paper, such unnecessary parts are rejected well by a special technique called "moving normalization". This new technique has been developed in order to make an appropriate bi-level region-of-interest (ROI) image. The total evaluation is done from the size and figure categorization. Many simulation examples show that the proposed method gives much more reliable results than the traditional methods do.

Abstract: Fuzzy Mathematical Morphology aims to extend the binary morphological operators to grey-level images. In order to define the basic morphological operations fuzzy erosion, dilation, opening and closing, we introduce a general method based upon fuzzy implication and inclusion grade operators, including as particular case, other ones existing in related literature. In the definition of fuzzy erosion and dilation we use several fuzzy implications (Annexe A, Table of fuzzy implications), the paper includes a study on their practical effects on digital image processing. We also present some graphic examples of erosion and dilation with three different structuring elements B(i,j)=1, B(i,j)=0.7, B(i,j)=0.4, i,j I {1,2,3} and various fuzzy implications.

Abstract: Computational intelligence techniques have been successfully used for solving control problems in packet-switching network architectures. The introduction of active networking adds a high degree of flexibility in customizing the network infrastructure and introducing new functionality. Therefore, there is a clear need for investigating both the applicability of computational intelligence techniques in this new networking environment, as well as the provisions of active networking technology that computational intelligence techniques can exploit for improved operation. We report on the characteristics of these technologies, their synergy and on outline recent efforts in the design of a computational intelligence toolkit and its application to routing on a novel active networking environment.

Abstract: In the standard fuzzy arithmetic, the vagueness of fuzzy quantities always increases. G. J. Klir [2, 3] suggests an alternative – the constrained fuzzy arithmetic – which reduces this effect. On the other hand, it significantly increases the complexity of computations in comparison to the classical calculus of fuzzy quantities. So far, little attention was paid to the problems of implementation of the constrained fuzzy arithmetic, especially to its computational efficiency. We point out the related problems and outline the ways of their solution. We suggest to decompose the whole expression, classify all its subexpressions with respect to their individual computational complexity and precompute the corresponding subresults according to this classification.

Abstract: This paper presents the use of genetic algorithms to develop smartly tuned fuzzy logic controllers in multicriteria complex problems. This tuning approach has some specific restrictions that make it very particular and complex because of the large time requirements existing due to the need of considering multiple criteria -which enlarges the solution search space-, and to the long computation time models usually used for fitness assessment. To solve these restrictions, two efficient genetic tuning strategies considering different multicriteria approaches have been developed and tested in a real-world problem for fuzzy control of HVAC Systems.

Abstract: Complex natural processes may often be expressed in terms of networks of computational components, such as Boolean logic gates or artificial neurons. The interaction of biological molecules and the flow of information controlling the development and behaviour of organisms is particularly amenable to this approach, and these models are well-established in the biological community. However, only relatively recently have papers appeared proposing the use of such systems to perform useful, human-defined tasks. Rather than merely using the network analogy as a convenient technique for clarifying our understanding of complex systems, it may now be possible to harness the power of such systems for the purposes of computation. In this paper we review several such proposals, focusing on the molecular implementation of fundamental computational elements.

Abstract: This paper proposes a decision-theoretic intelligent agent model to solve a herding problem and studies the learning from experience capabilities of the agent model. The proposed intelligent agent model is designed by combining Bayesian networks (BN) and influence diagrams (ID). The online Bayesian network learning method is proposed to accomplish the learning from experience. Intelligent agent software, IntelliAgent, is written to realize the proposed intelligent agent model and to simulate the agents in a problem domain. The same software is then used to simulate the herding problem with one sheep and one dog. Simulation results show that the proposed intelligent agent is successful in establishing a goal (herding) and learning other agents' behaviors.

Abstract: The uncertain and inexact nature of the chemical reactions used to implement DNA computations can be turned into an advantage for implementing robust soft computing systems. The key feature of DNA hybridization that makes it appropriate for fuzzy computing is the uncertainty and incompleteness in the formation of a double-stranded duplex from single-stranded oligonucleotides. To implement fuzzy computing, a set of encoding DNA molecules is given that reproduces a specific membership function in the energetics of the DNA duplex. In addition, a fuzzy inference system implemented with DNA hybridization on solid supports is discussed. The ultimate success of this idea as a general technique, however, is dependent on the actual geometry of the Gibbs free-energy landscapes in the space of all duplex formations. Elucidating this problem is undoubtedly of great importance for biomolecular implementation of soft-computing because it may, in particular, shed light on the true import of fuzzy models in biological processes fundamental to life.

Abstract: A population of committees of agents that learn by using neural networks is implemented to simulate the stock market. Each committee of agents, which is regarded as a player in a game, is optimised by continually adapting the architecture of the agents using genetic algorithms. The committees of agents buy and sell stocks by following this procedure: (1) obtain the current price of stocks; (2) predict the future price of stocks; (3) and for a given price trade until all the players are mutually satisfied. The trading of stocks is conducted by following these rules: (1) if a player expects an increase in price then it tries to buy the stock; (2) else if it expects a drop in the price, it sells the stock; (3)and the order in which a player participates in the game is random. The proposed procedure is implemented to simulate trading of three stocks, namely, the Dow Jones, the Nasdaq and the S&P 500. A linear relationship between the number of players and agents versus the computational time to run the complete simulation is observed. It is also found that no player has a monopolistic advantage.

Abstract: Elements of evolutionary computation and molecular biology are combined to design a DNA evolutionary computation. The traditional test problem for evolutionary computation, OneMax problem is addressed. The key feature is the physical separation of DNA strands consistent with OneMax “fitness.”