Contents of Volume 18 (2008)

1/2008 2/2008 3/2008 4/2008 5/2008


  • [1] Űbeyli E. D. (Turkey): Use of the internet in medical decision-making: a model developed for diabetes prediction, 427-436.

    The Internet has become an important source of information for physicians seeking immediate data for the management of patients and for those developing decision-making methodologies and guidelines for clinical practice. In this study, components and subsystems of a medical decision support system are presented. An artificial neural network model, which is one of the subsystems of the differential diagnosis component, has been proposed as a reasoning tool to support medical diagnosis. The input data of artificial neural network models used in different medical diagnosis can be obtained via the Internet. The present study is concerned with the application of artificial neural network model to diabetes prediction. Demographic and medical data of diabetics and non-diabetics obtained via the Internet were used as the artificial neural network inputs. The accuracy of the neural network's results has shown that the diabetes prediction is feasible by the neural network described in this study.

  • [2] Luaces M. M., Pazos J., Rocha C. G., Rodríguez-Patón A. (Spain): The social side and time dimension of self-representation in agents using modular neural networks, 437-458.

    An important cognitive feature –shared only by humans and a few other species– is self-consciousness. It has been defined as “the possession of the concept of the self and the ability to use this concept in thinking about oneself”. Self-consciousness undoubtedly depends on some kind of self-representation, although the nature of this self-representation in intelligent beings is still unknown. In recent years, several cognitive scientists have proposed self-representation models. Nevertheless, usually these models only represent the current state of consciousness. In this paper, we introduce the time dimension to extend self-representation models in order to represent the development of individual self-representation over time.

    Another important cognitive feature of both humans and animals is that they have a sense of belonging. It has been defined as “the process by which an individual understands that other beings are like himself (herself)”. We focus on the social side of self-consciousness and self-representation by defining self-consciousness as a specialization of the sense of belonging.

    In this paper, we use modular artificial neural networks for implementation. To test models, we implemented a simulator with modular neural networks composed of self-organized maps (SOM) and time delayed neural networks (TDNN). In this multi-agent system, agents were equipped with a simplified model of sensory perception, personality, sense of belonging and self-consciousness. Agent interaction is tested in different hypothetical social scenarios. The simulator structure and its MANN components are described in detail. The relation between a sense of belonging and self-consciousness is also discussed. Quantitative results are analyzed and conclusions stated.

  • [3] Long Li, Wei Wu, Jie Yang, Yan Liu (China): Finite convergence of a fuzzy δ rule for a fuzzy perceptron, 459-467.

    This paper considers a fuzzy perceptron that has the same topological structure as the conventional linear perceptron. A learning algorithm based on a fuzzy δ rule is proposed for this fuzzy perceptron. The inner operations involved in the working process of this fuzzy perceptron are based on the max-min logical operations rather than conventional multiplication and summation, etc. The initial values of the network weights are fixed as 1. It is shown that each network weight is non-increasing in the training process and remains unchanged once it is less than 0.5. The learning algorithm has an advantage, as proved in this paper, that it converges in a finite number of steps if the training patterns are fuzzily separable. This result generalizes a corresponding classical result for conventional linear perceptrons. Some numerical experiments for the learning algorithm are provided to support our theoretical findings.

  • [4] Kramosil I. (Czech Republic): Locally sensitive lattice-valued possibilistic entropy functions, 469-488.

    Given a possibilistic distribution on a nonempty space Ω with possibility degrees in a chained complete lattice, the lattice-valued entropy function for such distribution is defined as the expected value (in the sense of Sugeno possibilistic integral) of the lattice-valued function ascribing to each ωeΩ the possibilistic measure of its complement Ω-{ω}.

    However, such an entropy function seems to be little sensitive or flexible in the sense that it ascribes the same and supremum value to a rather wide class of different lattice-valued possibilistic distributions so that the choice of the most adequate, in a sense, distribution (for the purposes of decision making under uncertainty) is rather limited. In this paper, we propose and analyze a refined version of this entropy, which splits the wide class of possibilistic distributions mentioned above into a rich spectre of narrower classes of distributions to which different but mutually comparable values of the refined entropy function are ascribed.

  • [5] Svítek M. (Czech Republic): Investigation to Heisenberg's uncertainty limit, 489-498.

    In the paper, we first present derivation of Heisenberg's uncertainty limit that comes from the non-local Fourier transform. Next we derive a theory yielding into the definition of inner structure of the measuring signal/device that performs resolution beyond Heisenberg's limit. The mathematical theory can be repeated again and again and the computing algorithm can be designed to achieve the predefined resolution precision. At the end of paper, some application examples are introduced.

  • [6] Montera L., do Carmo Nicoletti M., Henrique-Silva F., Dellamano M. (Brazil): ISAS: An interactive software for assisting shuffling process, 499-514.

    This paper presents ISAS (Interactive Software for Assisting Shuffling Process), software that has been designed and developed by the authors as a tool for assisting users conducting DNA shuffling experiments in laboratories. ISAS can be defined as a new friendly dialog box-based environment which provides many different functions for DNA analyses, including (a) the evaluation of the adequacy of parental sequences as candidates for undergoing shuffling processes and (b) the evaluation of the vast amount of sequences produced by a shuffling process in order to identify those that might be improved versions of the parental sequences. In order to exemplify some of ISAS's functionalities, the paper describes its use in assisting a laboratory shuffling experiment using two genes encoding cystatins (Cystatins are proteins which specifically inhibit cysteine proteases. They occur in plants and animals; in plants it is believed that they are part of a defence mechanism against some pathogens.) as parental sequences, one from sugarcane and the other from rice.

  • [7] Coufal D. (Czech Republic): A fuzzy logic based system for detection of car driver's vigilance level, 515-526.

    The paper presents an application of fuzzy logic modeling techniques for design and development of a classification system for car driver's vigilance level detection. Especially, the micro-sleeps detection is of our primary interest. Detection is based on a pattern analysis of EEG signal spectrograms, which are acquired by monitoring the driver during a driving process. The system is based on the concept of radial implicative fuzzy system, which can be treated as a logical system accommodating acquired knowledge in a structured form.

  • [8] Contents volume 18 (2008), 527-529.
  • [9] Author's index volume 18 (2008), 531-533.


  • [1] Guney K., Sarikaya N. (Turkey): Adaptive-network-based fuzzy inference system models for narrow aperture dimension calculation of optimum gain pyramidal horns, 341-363.

    A method based on the adaptive-network-based fuzzy inference system (ANFIS) is presented for computing the narrow aperture dimension of the pyramidal horn. Eight optimization algorithms, least-squares, hybrid learning, Nelder-Mead, genetic, differential evolution, particle swarm, simulated annealing, and clonal selection, are used to optimally determine the design parameters of the ANFIS. The narrow aperture dimension computed by using the ANFIS is used in the optimum gain pyramidal horn design. The computed gains of the designed pyramidal horns are in a very good agreement with the desired gains. When the performances of ANFIS models are compared with each other, the best result is obtained from the ANFIS model trained by the least-squares algorithm.

  • [1] Li L. K., Shao S. (China, USA): A neural network approach for global optimization with applications, 365-379.

    We propose a neural network approach for global optimization with applications to nonlinear least square problems. The center idea is defined by the algorithm that is developed from neural network learning. By searching in the neighborhood of the target trajectory in the state space, the algorithm provides the best feasible solution to the optimization problem. The convergence analysis shows that the convergence of the algorithm to the desired solution is guaranteed. Our examples show that the method is effective and accurate. The simplicity of this new approach would provide a good alternative in addition to statistics methods for power regression models with large data.

  • [1] Űbeyli E. D. (Turkey): Signal-to-noise ratios for measuring saliency of features extracted by eigenvector methods from ecg signals, 381-400.

    Medical diagnostic accuracies can be improved when the pattern is simplified through representation by important features. Features are used to represent patterns with minimal loss of important information. The feature vector, which is comprised of the set of all features used for describing a pattern, is a reduced-dimensional representation of that pattern. By identifying a set of salient features, the noise in a classification model can be reduced, resulting in more accurate classification. In this study, a signal-to-noise ratio (SNR) saliency measure was employed to determine saliency of input features of recurrent neural networks (RNNs) used in the classification of electrocardiogram (ECG) signals. In order to extract features representing four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database, eigenvector methods were used. The RNNs used in the ECG beats classification were trained for the SNR screening method. The results of the application of the SNR screening method to the ECG signals demonstrated that classification accuracies of the RNNs with salient input features are higher than those of the RNNs with salient and non-salient input features.

  • [1] Svítek M. (Czech Republic): Wave probabilisties and quantum entanglement, 401-406.

    The paper continues with the theory of wave probabilistic models and uses the inclusion-exclusion rule to describe quantum entanglement as a wave probabilities resonance principle. The achieved results are mathematically described and an illustrative example is shown to demonstrate the possible applications of the presented theory.

  • [1] Lorena A. C., Carvalho A. C. P. L. F. (Brazil): Hierarchical decomposition of multiclass problems, 407-425.

    Several popular Machine Learning techniques are originally designed for the solution of two-class problems. However, several classification problems have more than two classes. One approach to deal with multiclass problems using binary classifiers is to decompose the multiclass problem into multiple binary sub-problems disposed in a binary tree. This approach requires a binary partition of the classes for each node of the tree, which defines the tree structure. This paper presents two algorithms to determine the tree structure taking into account information collected from the used dataset. This approach allows the tree structure to be determined automatically for any multiclass dataset.


  • [1] Guney K., Basbug S. (Turkey): Phase-only pattern nulling of linear antenna arrays with the use of a bacterial foraging algorithm, 257-273.

    In this paper, a bacterial foraging algorithm (BFA) has been used for null steering in the antenna radiation pattern by controlling only the element phases of a linear array. The BFA is an optimization algorithm based on the foraging behavior of Escherichia (E.) coli bacteria in human intestine. Numerical examples of Chebyshev pattern with the single, multiple and broad nulls imposed at the directions of interference are given to show the accuracy and flexibility of the BFA. The sensitivity of the nulling patterns due to small variations of the element phases is also investigated.

  • [2] Sengur A., Turkoglu I., Ince M. C. (Elazig/Turkey): Wavelet oscillator neural networks for texture segmentation, 275-289.

    Texture can be defined as a local statistical pattern of texture primitives in observer's domain of interest. Texture analysis such as segmentation plays a critical role in machine vision and pattern recognition applications. The widely applied areas are industrial automation, biomedical image processing and remote sensing. This paper describes a novel system for texture segmentation. We call this system Wavelet Oscillator Neural Networks (WONN). The proposed system is composed of two parts. A second-order statistical wavelet co-occurrence features are the first part of the proposed system and an oscillator neural network is in the second part of the system. The performance of the proposed system is tested on various texture mosaic images. The results of the proposed system are found to be satisfactory.

  • [3] Tuckova J., Sebesta V. (Czech Republic): Prosody optimisation of a Czech language synthesizer, 291-308.

    Each national language is described by specific grammatical rules. But rule-based knowledge representations alone cannot be used for the natural flow of speech.

    In this paper, optimisation of the naturalness of speech, i.e. the optimal choice of phonetic and phonologic parameters for prosody modelling is sought. We will try to find relevant features (speech parameters) having the basic influence on the fundamental frequency and duration of speech units. If the prosody of the synthesizer is controlled by an artificial neural network (ANN), optimisation of the ANN topology is necessary.

    The topology of the ANN is also dependent on the number of input neurons which represent the most important speech parameters. The pruning of the ANN based on the several approaches (GUHA method, sensitivities of the synaptic weights, etc.) is a suitable tool for reducing the ANN structure.

  • [4] Monfared M., Daryani A. M., Abedi M. (Iran): Online tuning of genetic based PID controller in LFC systems using RBF neural network and VSTLF technique, 309-322.

    In this paper, a novel control strategy for the load frequency control (LFC) system is proposed. The developed method includes a genetic algorithm (GA) based self-tuned PID controller for online application. The new method is presented in order to regulate PID controller coefficients by a radial basis function neural network (RBFN). Furthermore, a very short time load forecasting (VSTLF) scheme is also employed as a novel approach for the system load variations to be considered in the LFC system. For validation of the proposed method, several comparative case studies are presented. The simulation results indicate that the proposed strategy improves the system dynamics remarkably.

  • [5] Xiaogang Zang, Xinbao Gong, Xiaogfeng Ling, Cheng Chang, Bin Tang (China): An evolutionary RBF network configuration using adaptive width adjustment based on vaccination, 323-339.

    In this paper, a mechanism of adaptive width adjustment based on immunological vaccination is proposed for the evolutionary training of RBF neural networks. Inspired by the vaccination process of the natural immune system, the algorithm implements an individual-orientated adaptation of the width in training stages to optimize the potential solutions, therefore reinforces the evolutionary capability and efficiency. A two-layer genotype-coding scheme, which enables a simultaneous evolution of network structure and parameters, is presented to achieve a compact and consistent-in-form solution. The proposed learning strategy is tested on several benchmark problems and results demonstrate promise.


  • [1] Dongpo Xu, Zhengxue Li, Wei Wu (China): Convergence of approximated gradient method for Elman network, 171-180.

    An approximated gradient method for training Elman networks is considered. For the finite sample set, the error function is proved to be monotone in the training process, and the approximated gradient of the error function tends to zero if the weights sequence is bounded. Furthermore, after adding a moderate condition, the weights sequence itself is also proved to be convergent. A numerical example is given to support the theoretical findings.

  • [2] Al-Qaheri H., Hassanien A. E., Abraham A. (Kuwait, Egypt, Norway): Discovering stock price prediction rules using rough sets, 181-198.

    The use of computational intelligence systems such as neural networks, fuzzy set, genetic algorithms, etc., for stock market predictions has been widely established. This paper presents a generic stock pricing prediction model based on a rough set approach. To increase the efficiency of the prediction process, rough sets with Boolean reasoning discretization algorithm is used to discretize the data. The rough set reduction technique is applied to find all the reducts of the data which contains the minimal subset of attributes that are associated with a class label for prediction. Finally, rough sets dependency rules are generated directly from all generated reducts. Rough confusion matrix is used to evaluate the performance of the predicted reducts and classes. Using a data set consisting of the daily movements of a stock traded in Kuwait Stock Exchange, a preliminary assessment indicates that rough sets are shown to be applicable and is an effective tool to achieve this goal. For comparison, the results obtained using the rough set approach were compared to that of the neural networks algorithm and it was shown that the Rough set approach has a higher overall accuracy rate and generates more compact and fewer rules than the neural networks.

  • [3] Alsabbah S., Mughrabi T. (Jordan): Design of MLP NN-based SWGAD, 199-208.

    One of the most recent and perspective gas detectors is a smart wave\-guide acoustic detector, in which chromatogram represents the mass concentration of the gas to be detected. On the other hand, with respect to design criterions and limits (cost and size), an alternative numerical-based detector has been designed, using a multi-layer perceptron neural network to estimate the frequency and mass concentration of the unknown gas (sample). Experimental data were used for designing the database of the neural network-based detector. The proposed NN-based detector was compared with the real one to validate the proposal. Finally, numerical results were obtained to evaluate its performance.

  • [4] Xhafa F., Duran B., Abraham A., Dahal K. (Spain, Norway, UK): Tuning struggle strategy in genetic algorithms for scheduling in computational grids, 209-225.

    Job Scheduling in Computational Grids is gaining importance due to the need for efficient large-scale Grid-enabled applications. Among different optimization techniques designed for the problem, Genetic Algorithm (GA) is a popular class of solution methods. As GAs are high level algorithms, specific algorithms can be designed by choosing the genetic operators as well as the evolutionary strategies such as Steady State GAs and Struggle GAs. In this paper we focus on Struggle GAs and their tuning for scheduling of independent jobs in computational grids. Our results showed that a careful hash implementation for computing the similarity of solutions was able to alleviate the computational burden of Struggle GA and perform better than standard similarity measures. This is particularly interesting for the scheduling problem in Grid systems, which due to changeability over time, has demanding time restrictions on the computation of planning the jobs to resources.

  • [5] Sergin A. V., Sergin V. Ya. (Russia): Model of perception: The hierarchy of inclusive sensory characteristics and top-down cascade transfer of excitation, 227-244.

    The article offers a new view on the organization of the processes of human perception. It introduces the concept of inclusive sensory characteristic, which is a response of a given perceptual level to those features or characteristics of an underlying level whose spatial organization or specific temporal succession constitutes an adaptively meaningful entity. The sequence of inclusive characteristics forms a hierarchy: from features to the highest inclusive characteristics which bind sensory data into unified images and scenes. The highest inclusive characteristic is neither an image nor a scene, but a unique scheme of combination of underlying-level objects, which produces the image or the scene.

    Specific patterns of electric activity, which map inclusive characteristics, are relayed by feedbacks from upper to lower neuronal levels. This forms a cascade of top-down transfer of excitation, which stimulates those neuronal populations whose signals correspond to the highest inclusive characteristic of a given act of perception. Stimulation from above reduces the time of response of selected neurons at underlying levels to simultaneously arriving spikes to milliseconds. As a result, neuronal populations at the underlying levels, which are involved in a given act of perception, become, for a short time, coincidence detectors. The hierarchically arranged set of neuronal ensembles of coincidence detectors forms a fast sensory pathway, single and unique for each act of perception.

  • [6] Yonghui Sun, Jinde Cao (China): Novel criteria for mean square stability of stochastic delayed neural networks, 245-254.

    This paper investigates the mean square stability of a class of stochastic neural networks with time-varying delays. By virtue of the stochastic analysis method and linear matrix inequality (LMI) approach, a new sufficient condition is proposed where the feasibility of the conditions can be readily checked by the Matlab LMI control toolbox. Moreover, our method has the advantage of removing the restrictions on the time varying delays, so the derived results are less conservative than the previous works. A numerical example with simulations are provided to illustrate the effectiveness of the developed results.


  • [1] Faber J., Tichý T. (Czech Republic): Vigilance and hypnagogium determination of drivers by EEG analysis, 89-104.

    EEG activities with open eyes in a quiet state (OA), during the pseudo-Raven's test (PRA), in hypnagogic state (HYP) and in the course of REM sleep (REM) are characteristic by nearly flat curves. We observed the states with eyes closed (OC), with hyperventilation (HV), during mental activity of calculation (CAL) and in NONREM 1 sleep (NR 1). 24 tested persons (probands) were investigated. We have found 8 typical states of EEG signals, which all have relation to attention and mental activity. Consequently, the EEG analysis can help in the differentiation between the above eight states. Using similar analyses, it is possible to discriminate all stages of NONREM and REM sleep without polysomnography.

  • [2] Šimůnek M. (Czech Republic): Traffic control in virtual model of a real city, 105-117.

    The traffic control is an essential part of autonomous movement of different kinds of vehicles in a virtual model of a (real) city. By the traffic control we mean not only collisions avoiding and optimal setting of traffic lights. The movement should be realistic enough too, so traffic (together with changing day-time/night-time and seasons of the year) significantly improves feeling of reality for a virtual visitor. This paper describes some implementations of the city traffic in the project named Praha4D ( aimed at the city of Prague and its historical development.

  • [3] Khwaldeh A., Barazane L., Krishan M. M., El-Qawasmeh E. (Algeria, Jordan): Design of ANFIS speed controller for a novel variable structure control scheme of induction motor, 119-132.

    This paper concerns the application of neuro-fuzzy approach in order to perform the responses of the speed regulation and reduce the chattering phenomenon introduced by sliding mode control. So first, we conceived a sliding mode controller of the induction motor. A new approach is applied to the cascade structure is presented. For this purpose, a new decoupled and reduced model is first proposed. Then, a set of simple surfaces and associated control laws are synthesized. However, as the magnitude of the piecewise smooth function depends closely on the upper bound of uncertainties, which include parameter variations and external disturbances, we propose a new form of this piecewise smooth control function with a threshold which ensure a significant reduction of the chattering but could not eliminate it. To overcome such a limitation of this control, adaptive neuro fuzzy inference controllers (ANFIS) are designed. Simulation results reveal some very interesting features.

  • [4] Luan Shenggang, Zhong Shisheng, Li Yang (China): Hybrid recurrent process neural network for aero engine condition monitoring, 133-145.

    Aero engine condition monitoring (ECM) is essential in terms of improving availability and reducing life-cycle costs of the aero engine. Aero engine exhaust gas temperature (EGT) plays the most critical role in the ECM. By monitoring the EGT, maintenance crews can realize the aero engine health condition and speculate about the latent faults of the aero engine in advance. But it is difficult for traditional methods to predict the tendency of the EGT. So, a new model of hybrid recurrent process neural network (HRPNN) is proposed. The HRPNN acquires hidden-to-hidden and output-to-hidden feedbacks by introducing respectively the context units with self-feedback connections, and its inputs are time-varied functions. Hence, it can represent more states of the complicated nonlinear dynamical system such as aero engine more directly. A learning algorithm base on resilient backpropagation (Rprop) is developed for the HRPNN. To simplify the learning algorithm, a set of appropriate orthogonal basis functions are introduced to expand the input functions and the connection weight functions of the HRPNN. The method validation is proved by a benchmark of the Mackey-Glass chaos time series prediction. A practical utilization of the aero engine EGT prediction also demonstrates this point in terms of aero engine condition monitoring, the results indicate HRPNN can be used as an efficient ECM tool.

  • [5] Dong Hwa Kim, Ajith Abraham (Korea, Norway): Optimal learning of fuzzy neural network using artificial immune algorithm, 147-170.

    Fuzzy logic, neural network, fuzzy-neural networks play an important role in the linguistic modeling of intelligent control and decision making in complex systems. The Fuzzy-Neural Network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes an Artificial Immune Algorithm (AIA) based optimal learning fuzzy-neural network (IM-FNN). The proposed learning scheme includes the discovery of the fuzzy-neural network structure which can handle linguistic knowledge and the tuning of the membership function of the fuzzy inference system is achieved by AIA. The learning algorithm of the IM-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, immune algorithm is used for tuning the membership functions of the proposed model. This paper also suggests techniques in determining the values of the steady-state equivalent circuit parameters of a three-phase squirrel-cage induction machine using immune algorithm.


  • [1] Editorial, 1.
  • [2] Svitek M., Zelinka T. J. (Czech Republic): Communications multi-path access decision scheme, 3-14.

    Resolution of seamless switching within a set of available wireless access solutions applied in ITS (Intelligent Transport System) applications is presented. The CALM based system or specifically designed and configured L3/L2 switching can be an adequate solution for the multi-path access communication system. These systems have to meet requirements of the seamless secure communications functionality within even an extensive cluster of moving objects. Competent decision processes based on precisely quantified system requirements and each performance indicator tolerance range must be implemented to keep service up and running with no influence of continuously changing conditions in time and served space.

    The method of different paths service quality evaluation and selection of the best possible active communications access path is introduced. This method is studied within project STATVU (System Requirements and Architecture of the Universal Telematic Vehicle Unit is grant 2A-1TP1/138 of the Ministry of Industry and Trade of the Czech Republic.). The proposed approach is based on Kalman filtering which separates reasonable part of noise and also allows prediction of the individual parameters near future behavior. The presented classification algorithm applied on filtered measured data combined with deterministic parameters is trained using historical data, i. e. combination of parameters vectors line and relevant decisions. Quality of classification is dependent on the size and quality of the training data sets.

  • [3] Sadil J. (Czech Republic): Artificial intelligence methods used for predicting traction power consumption,15-22.

    In this paper some remarks on predictive modeling of traction power consumption and their use in intelligent control systems are stated. Special emphasis is put on discussing neural networks and genetic algorithms for such models described in the second Chapter. In the third Chapter, significant applications of neural networks and genetic algorithms in area of power consumption and train diagram are stated. A methodology of model development and assessment is presented in Chapter 4. In Chapter 5 there are up to now results of the author's traction power consumption prediction coming out from artificial neural network predictive models developed in Mathematica SW environment. Finally, summary and further work are stated in the last Chapter.

  • [4] Řeřucha Š. (Czech Republic): Distributed approach to neuroinformatics data interchange, 23-31.

    One of the problems during a great disaster is the breakdown of communication infra structure. One of the solutions is the use of mobile ad-hoc networks (MANET). In this paper, we consider the situation in a building after a big fire, explosion or earthquake. Rescue workers equipped with PDAs, which are wireless connected, explore the dynamically changing world. Each individual builds up a local world map based on their local exploration and observation. The local maps are fused via the MANET structure and provide an up to date map of the dynamically changing world. Such maps can be used for mitigation, escape or rescue work.

  • [5] Bĕlinová Z. (Czech Republic): Self-organizing aspects in transportation and their modelling, 33-38.

    The presented study deals with an object-relation mental model of drivers reasoning. The model stands on logic positions and brings a degree of logical proving into advanced microscopic models of road traffic. The future improvement of microscopic simulation is possible only by improvement of driver's behavior models, applying mental models of human drivers. The works are based on many sources: robotics, mathematical logic, cognitive science, computer science (ontologies, object oriented representation), and psychological researches from the fields of mental capacity, human problem solving, etc.

  • [6] Moos P. (Czech Republic): Operation safety and reliability improvement of large transport systems by complex sensitivity investigation, 39-43.

    Transportation system safety and reliability pertain to the dominant factors affecting present life of human society. In this paper, we describe the method for an analysis and further subsequent optimization of complex transportation system safety and reliability based on their complex sensitivity investigation. Reasonable applications of this theoretical tool can also be used for improvement of complex transportation system resistance against terrorist activities.

  • [7] Brandejsky T. (Czech Republic): The application of behavioral features model to road traffic modeling and analysis, 45-53.

    The presented study deals with an object-relation mental model of drivers reasoning. The model stands on logic positions and brings a degree of logical proving into advanced microscopic models of road traffic. The future improvement of microscopic simulation is possible only by improvement of driver's behavior models, applying mental models of human drivers. The works are based on many sources: robotics, mathematical logic, cognitive science, computer science (ontologies, object oriented representation), and psychological researches from the fields of mental capacity, human problem solving, etc.

  • [8] Eggenkamp G., Rothkrantz L. J. M. (The Netherlands): A knowledge based approach to dynamic route planning, 55-66.

    In this paper, an expert system that performs route planning using dynamic traffic data is introduced. Also an algorithmic approach is introduced to find the shortest path in a three-dimensional. Using both implementations, a comparison is made between the expert system approach and the algorithmic approach. It is concluded that the expert system shows great potential. The expert system indeed finds the best routes, and it outperforms the algorithm approach in computation time, too.

  • [9] L. J. M. Rothkrantz, M. van Velden, D. Datcu (The Netherlands): Fusion of local maps in mobile ad-hoc networks, 67-79.

    One of the problems during a great disaster is the breakdown of communication infra structure. One of the solutions is the use of mobile ad-hoc networks (MANET). In this paper, we consider the situation in a building after a big fire, explosion or earthquake. Rescue workers equipped with PDAs, which are wireless connected, explore the dynamically changing world. Each individual builds up a local world map based on their local exploration and observation. The local maps are fused via the MANET structure and provide an up to date map of the dynamically changing world. Such maps can be used for mitigation, escape or rescue work.

  • [10] Contents volume 17 (2007), 81-83.
  • [11] Author's index volume 17 (2007), 85-88.