Journal of Intelligent & Fuzzy Systems - Volume 17, issue 6

Authors: Bidargaddi, Niranjan P. | Chetty, Madhu | Kamruzzaman, Joarder

Article Type: Research Article

Abstract: The formulation of the classical profile HMMs is made under statistical independence assumption of the probability theory which is a limitation for modeling protein sequences because of a high degree of interdependency among homologous sequences of the same family. Fuzzy measure theory which is an extension of the additive theory, is developed by replacing the additive requirement of classical measures with weaker properties of continuity, monotonicity and semi-continuity. The strong interdependencies and …the sequence preferences involved in the proteins make models based on fuzzy architecture better candidates for building profiles of a given family. In this paper, we investigate the characteristics and compare the performances of three different fuzzy profile HMMs based on possibility, λ and belief measures on globin and kinase families. The performances of the fuzzy models are also compared with profile HMMs. The results obtained in terms of Z-score plots, alignment analysis and ROC curves establish the superior performance of models based on fuzzy measures over classical models. It is shown that the possibility measure based fuzzy profile HMM has the best performance amongst all the models. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 541-556, 2006

Authors: Mozafari, B. | Ranjbar, A.M. | Amraee, T. | Mirjafari, M. | Shirani, A.R.

Article Type: Research Article

Abstract: In Particle Swarm Optimization (PSO) algorithm, although taking an active role to guide particles moving toward optimal solution, the most-fit candidate does not have a guide itself and only moves along its velocity vector in every iteration. This may yield a noticeable number of agents converge into local optima if the guide (i.e. the most fit candidate) agent cannot explore the best solution. In this paper, an attempt is made to get the advantage of the …Ant Colony Optimization (ACO) methodology to assist the PSO algorithm for choosing a proper guide for each particle. This will strengthen the PSO abilities for not getting involved in local optima. As a result, we present a promising new hybrid particle swarm optimization algorithm, called ACPSO. The capability of the presented algorithm to solve a nonlinear optimization problem is demonstrated using different case studies carried out for optimal reactive power procurement. The IEEE 14-bus and 118-bus systems are adopted for reactive power market simulation. The main objective of the market is to minimize total generation costs of reactive power and transmission losses at different voltage stability margins. Based on the GAMS modeling language and the CONOPT solver, solutions are obtained for different models using a conventional non-linear optimization technique. Compared with the solutions found by the GAMS, Genetic Algorithm (GA) and the original PSO, the proposed ACPSO algorithm can provide promising results in terms of robustness and overall efficiency when it is applied to the reactive power market. Show more

Keywords: Particle swarm optimization, ant colony optimization, deregulation, OPF, reactive power market, system security

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 557-574, 2006

Authors: Bargieła, Andrzej | Homenda, Władysław

Article Type: Research Article

Abstract: This paper introduces a new framework for processing Natural Language statements. The parallel is drawn between the Natural Language processing and the Data Mining technology of information granulation. The formalism affords consistent representation of a well-known phenomenon of 'approximate' grammatical correctness of Natural Language statements. The ontology-based information structuring is a natural complement of the syntactical information granulation. The approach is validated on some simple Natural Language statements and the directions for …the future development of the system are outlined. The paper focuses on conceptual framework only and, as such, is intended to stimulate further research into the various implementation considerations that are prerequisite of large-scale applications. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 575-581, 2006

Authors: Mendez, Gerardo M. | Cavazos, Alberto | Soto, Rogelio | Leduc, Luis

Article Type: Research Article

Abstract: In Hot Strip Mills, on-line estimation of rolling variables is of crucial importance in order to Set-Up the Finishing Mill, i.e. setting initial working references for the in-bar regulators, and hence fulfilling quality requirements. This paper presents the experimental results of the application of type-2 fuzzy logic systems for scale breaker entry temperature prediction in a real hot strip mill. Since in the literature only back-propagation has been proposed for type-2 fuzzy logic systems, a hybrid …learning algorithm has been developed. Such algorithm is also presented. The algorithm uses back-propagation with recursive least-squares and back propagation with square-root filter methods. The systems were tested for three types of inputs: a) interval singleton b) interval type-1 non-singleton, c) interval type-2 non-singleton. The experiments were carried out for three different types of coils. Experimental results show the feasibility of the systems developed here for scale breaker entry temperature prediction. Comparison with type-1 fuzzy logic systems shows the hybrid learning type-2 fuzzy logic systems improve performance in scale breaker entry temperature prediction under the tested condition. Show more

Keywords: Type-2 fuzzy inference systems, type-2 neuro-fuzzy systems, hybrid learning, uncertain rule-based fuzzy logic systems, temperature modeling and prediction

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 583-596, 2006

Authors: Ma, Z.M. | Shen, Derong

Article Type: Research Article

Abstract: In this paper, we focus on conceptual data modeling and logical database modeling of fuzzy information. The IFO data model is extended with fuzzy set theory to cope with imperfect as well as with complex objects in the real world at a conceptual level. Concerning the logical database modeling of fuzzy information, we focus on the object-oriented database model. Some major notions in the object-oriented databases such as objects, classes, objects-classes relationships, supertype/subtype, and multiple inheritances …are extended under fuzzy information environment, and a generic model for fuzzy object-oriented databases is developed. In particular, we develop the formal approach to mapping a fuzzy IFO (IF_{2} O) model to a fuzzy object-oriented database schema. Therefore, one can conduct the conceptual design of a database model with fuzzy information and then transform it into the logical database model. Show more

Keywords: Conceptual data modeling, object-oriented databases, fuzzy data, fuzzy object-oriented database model, fuzzy database design

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 597-612, 2006

Authors: Davvaz, B.

Article Type: Research Article

Abstract: The main aim of this work is to construct a general scheme that would permit to "insert" the notion of roughness into polygroups. We consider the factor polygroup P/N and interprete the lower and upper approximations as subsets of the factor polygroup P/N. Then we introduce the concept of factor rough subpolygroups. Also, using the concept of fuzzy set, we introduce and discuss the concept of fuzzy rough polygroup and then we obtain the relation between …fuzzy rough subpolygroups and level rough sets. This relation is expressed in terms of a necessary and sufficient condition. Show more

Keywords: Fuzzy set, rough set, lower approximation, upper approximation, polygroup, subpolygeoup, normal subpolygroup, factor polygroup

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 613-621, 2006

Authors: Reaz, M.B.I. | Choong, F. | Sulaiman, M.S. | Mohd-Yasin, F.

Article Type: Research Article

Abstract: This paper presents a new intelligent system incorporating wavelet transform, artificial neural network and fuzzy logic to automate the classification of power quality disturbance. This novel and efficient method in hardware, based on FPGA technology showed improved performance over existing approaches for power quality disturbance detection and classification on six types of disturbances including sag, swell, transient, fluctuation, interruption and normal waveform. The approach obtained an average classification accuracy of 98.19%. The …design was successfully implemented, tested and validated on Altera APEX EP20K200EBC652-1X FPGA utilizing 1209 logic cells and achieved a maximum frequency of 263.71 MHz. Show more

Keywords: Artificial neural network, wavelet transform, fuzzy logic, power quality, field programmable gate array

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 623-631, 2006

Authors: Chang, Wen-Jer | Chang, Wei

Article Type: Research Article

Abstract: Recently, the Takagi-Sugeno (T-S) fuzzy model has become one of the most useful control approaches for complex systems. It provides an effective representation of complex nonlinear systems in terms of fuzzy sets. In this paper, the stability and stabilization issues of continuous time-delay affine T-S fuzzy models are presented. Based on Lyapunov stability criterion and Razumikhin theorem, an Iterative Linear Matrix Inequality (ILMI) algorithm is used to solve the Bilinear Matrix Inequalities (BMI) problem. Also, ILMI …can be used to find feasible solutions for the synthesis of the continuous time-delay affine T-S fuzzy models. Finally, a numerical simulation for a delayed inverted pendulum system is given to show the applications of the present approach. Show more

Keywords: Takagi-Sugeno fuzzy model, time-delay systems, S-procedure, Iterative Linear Matrix Inequality

Citation: Journal of Intelligent & Fuzzy Systems, vol. 17, no. 6, pp. 633-647, 2006