Solving complex combinatorial optimization problems using classical algorithms is not efficient related to resources and time. To overcome the problem, we used optimal parameters selection based on Ant Colony Optimization (ACO) algorithms. In this paper, we present algorithm for solving telecommunication network using ACO for searching optimal ring star network topology. We analyzed ant's optimization ability based on shortest path between the nest and food location. In our research we used: Ant System, Elitist Ant System, Rank-Based Ant System, and MAX-MIN Ant System. The program is developed using GNU C++ to prove the algorithm theoretical convergence through simulation on variety of topologies regarding to node numbers. The algorithm was adapted to solve design of telecommunication network, which connects terminals to concentrators using point-to-point connections. The algorithm's output is a star topology showing connections of concentrators in a ring creating Digital Data Service. Algorithm uses seventeen parameters, with thirteen metrics to evaluate configurations. Program validation is performed using three different network node configurations for all four ACO algorithms, only changing two control parameters: speed of pheromone evaporation and existence of local search. The best path was evaluated based on: total time, number of iterations, ring size, and value of topology.

The purpose of this study is to present novel GAANFIS expert system prototype for tar detection in cigarettes during manufacturing process. The proposed system combines capabilities of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Genetic Algorithm (GA).The data recorded for different type of cigarettes are collected by special control quality equipment in real conditions inside cigarette factory. GA-ANFIS system performs optimization in two steps. In the first step it generates six different ANFIS structures, and after that, we have second level of GA optimization using given ANFIS structures resulting in optimal fuzzy model structure. Modeling and validation of the GA-ANFIS system approach is performed in MATLAB environment using validation data set that were not used in the process of training. Our earlier research results based on two different approaches (ANFIS and High-performance liquid chromatography (HPLC)) are also introduced. Performances of these three approaches are compared and novel expert system prototype shows better result related to training, testing and validation errors. It also more precisely shows that low yield tar cigarettes contain similar levels of nicotine opposite to high yield tar cigarettes while benzene, toluene, and xylene (BTX) levels rise along with increasing tar yields.

There is an increasing number of diabetic diseases in the population. Early diagnosis increases possibility of healing and decreases healing expenses. This paper is focused on modeling of an expert system for assessing diabetes risk using artificial intelligence methods. The model is hierarchical with neuro-fuzzy blocks and voting on the output. Model optimization (learning) is done using the data of real patients acquired in a one public health institution. The expert system is implemented in the Matlab/Simulink environment. Validation of the system shows high sensitivity of 100% which is important for early diagnoses. Specificity is lower - only 90% which means that some patients are sent to further diagnoses although they are healthy. Results indicate that this modeling approach is applicable on assessing diabetes risk. The medical domain knowledge and experience contained in the real data is successfully transferred in the solution model - the proposed expert system. Validation of the proposed expert system indicates that such a system can be used as an auxiliary expert for early diagnoses of diabetes and improve the quality of health systems with lower diagnostic expenses.

This paper presents a XML-based specification of the fuzzy system (FS) with objective to facilitate FS development by separation of the Fuzzy Inference System (FIS) implementation and a problem domain description. Generic FIS application is implemented in Java, and XML schema for domain knowledge specification is developed. Study case supporting the experimental evaluation of the proposed solution is software quality evaluation.

Building a system for the detection and prevention of intrusions into computer networks is a major challenge. Huge amounts of network traffic that process these systems are characterized by diversity and the data are described by a number of attributes. In addition, input data are often changing in a relatively short period of time, creating a completely new traffic patterns. This significantly complicates the identification of potentially unwanted network traffic. The aim of this paper is to present and analyze the effects of combined application of Self Organizing Map (SOM), Adaptive Neuro Fuzzy Inference System (ANFIS), Subtractive Clustering (SC) and Voting Mechanism (VM) in building systems for intrusion detection in computer networks in order to maintain an acceptable level of efficiency of data processing and increased system adaptivity.

Clustering is a crucial step in the analysis of gene expression data. Its goal is to identify the natural clusters and provide a reliable estimate of the number of distinct clusters in a given data set. In this paper we propose new hybrid algorithm for clustering of microarray data based on spectral clustering and k-means. Our algorithm consist of four steps, including preprocessing or filtering step, and finding optimal number of clusters by using two different clustering methods based on hierarchical and partition-based approaches. Then, we cluster data based on similarity/dissimilarity metrics with spectral clustering. In the final step, we select centroid genes based on kmeans results. The proposed method was tested on six data sets from GEMS microarray database. When compared with existing single or combination of clustering methods, our results indicate about 10% improvement in selection of representative genes.

This paper presents two approaches in isolation of vibrations of driver's seat . The first approach shows the ability of Fuzzy Logic Controller (FLC) to adjust the stiffness of the air spring, which is implemented between cabin floor and the seat together with damper in order to isolate the vertical vibrations. The second approach is based on Artificial Neural Network Controller (ANNC) with purpose of improvement vibration isolation producing appropriate voltage for valve flow diameter control of semi-active damper. The quality of isolation is measured using standardized technique. The results of simulation in Matlab/Simulink, as well as the results of implemented controllers on a real experimental model are presented.

This paper describes the capabilities of fuzzy logic based controllers in the process of pneumatic active suspension of a heavy vehicle seat vibrations. The pneumatic active suspension system is introduced to solve conflicting requirements of comfort and handling. The air spring is used as an active element and the damper is used as passive element for reducing vibrations. The usage of the active air spring enhances passenger comfort by comparison with passive, semi-active and active hydraulic suspension, during long time drives at a very bumpy road. Description of the seat, including its mechanical characteristics, is given in the paper. The mathematical model was created according to the physical setup of the vehicle seat at the testing laboratory. MATLAB and Simulink are used as tools for developing the simulation model of the driver seat. Control system description and implementation at the experimental setup using dSPACE module, are also explained. The SEAT value is used for the validation of control quality. The obtained simulations show that the developed road adaptive suspension controllers provide superior driver's comfort for most difficult types of road.

This paper presents results in cloning Fuzzy Inference System (FIS) component behavior using an Artificial Neural Network (ANN) component. Both FIS and ANN components are part of the intelligent framework VIMAS developed in Java programming language. VIMAS objective is to enable integration of the computational methods in a holistic manner. The FIS component generates training set for the ANN component containing a sequence of representative input combinations accompanied with the respective output. The FIS component sends necessary configuration data and training set data to the ANN component. After the training, the ANN component is presented with input data, and results are compared.

The aim of this work is to explore the method of fuzzy clustering applied for classification of spatial objects or generic geospatial analysis and cluster analysis as a classification of objects by mutual similarities and organize data into groups. Clustering techniques fall into unsupervised methods, meaning that they do not use predefined class identifiers. The biggest potential of clustering is in recognizing the basic data structures, not only for classification and identification of samples, but also the reduction of models and optimization.

This paper presents a novel hybridization of the fuzzy logic, the neural network and the coevolutionary algorithm for building a fuzzy-neural system (or a Mamdani fuzzy system) from data. The novel hybridization uses the coevolution of many species, and proposes the coevolution of groups of similar species, both for the optimization of the structure of the fuzzy-neural network. In the fuzzy-neural network the coevolution changes the number of nodes and their parameters, which indirectly change the number of fuzzy sets and their parameters and the number of rules and their parameters. Specific backpropagation that supports the Mamdani type of fuzzy system is proposed for small size optimization of fuzzy sets parameters. The backpropagation is active while the average absolute error is small, otherwise the backpropagation stops and the coevolution is active. To be able to guide the coevolution based on three criteria the coevolution uses three level of the fitness. It is possible to control the overfitting through these criteria. The proposed hybridization and its Matlab implementation can be used for creating Mamdani fuzzy-neural systems or simply Mamdani fuzzy systems, from data. This is an alternative for ANFIS and similar hybridizations. It offers to users possibility of building a Mamdani fuzzy-neuro system from data, automatically, with optimizing the number of rules, controlling the overfitting, working with large data sets and many variables, using simple triangular fuzzy sets, the result with high function approximation and good knowledge presentation, the result that can be used as the Mamdani fuzzy system (Matlab FIS object) or as the neural network (internal presentation format and feedforward function). This paper also presents the results of testing with the Wisconsin Breast Cancer Database, from UCI Machine Learning Repository ([http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science).

A study is presented for the detection of nicotine impact in different cigarette type, using recorded data and Computational Intelligence techniques. Recorded puffs are processed using Continuous Wavelet Transform and used to extract time-frequency features for normal and abnormal puffs conditions. The wavelet energy distributions are used as inputs to classifiers based on Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Genetic Algorithms (GAs). The number and the parameters of Membership Functions are used in ANFIS along with the features from wavelet energy distributionare selected using GAs, maximising the diagnosis success. GA with ANFIS (GANFIS) are trained with a subset of data with known nicotine conditions. The trained GANFIS are tested using the other set of data (testing data). A classical method by High-Performance Liquid Chromatography is also introduced to solve this problem, respectively. The results as well as the performances of these two approaches are compared. A combination of these two algorithms is also suggested to improve the efficiency of this solution procedure. Computational results show that this combined algorithm is promising.

This paper describes how a non-stationary multi-objective optimization model can be used for synthesis of control of mobile robot in unknown environment. The modelled problem is solved using multi-objective genetic algorithm (MOGA). Results of experiments conducted in simulation environment demonstrate the application of the described approach.

This document proposes an approach for financial statements' anomalies detection by using on-line evolving clustering [1]. Official records of the financial activities of a business are called financial statements and they are recorded in journals and general ledger in a supervised process. Anomalies in financial statements are caused by human mistakes during forming of financial statements, or as a result of changes in the software that produced un-expected errors, or as possible financial fraud.