In medical volume visualization, one of the main goals is to reveal clinically relevant details from the CT study by classification of the data, i.e. the coronary arteries, without obscuring them with less significant parts. Usually, the classification is carried out by defining multi-dimensional transfer functions which assign specific visual attributes to the voxels which express the features of interest. Unfortunately, this can become a fairly complex task, generally accomplished by trial and error even for the experienced user. Many sophisticated semi-automatic and automatic approaches for volume classification have been published in the past, which rely either on the overall quality of the rendered image or on a general boundary detection between different materials rather than on an insight as to what makes the transfer function appropriate for a specific feature in the dataset. This paper presents an efficient way for automatic transfer function generation based on neural networks. We describe how to use neural networks to detect distinctive features of the volume data and how this information can be used to provide the user with a semantic view on the automatic data classification.

This paper examines capabilities of Artificial Neural Network (ANN) regarding control of a heavy vehicle seat with semi-active damper. Matlab and its sub-application Simulink are used as a tool for developing simulation model of the driver seat in the heavy vehicles. The seat model with semiactive damper is built modularly by forming each of its components separately. Designed control model was tested in Matlab/Simulink, and then was verified on experimental setup, installed on the Department for Automatic Control of the Friedrich Alexander University in Erlangen Nuirnberg. After introductory remarks, this work considers description of the seat with semi active damper including mechanical characteristics and mathematical description of major components, theoretical remark about ANNs, control system description and implementation on experimental setup, using dSPACE module.

This paper presents capabilities of fuzzy logic in longitudinal vehicle guidance. Two aspects in automated driving are presented. The first is trajectory generation for longitudinal vehicle guidance, where the real driver is replaced by fuzzy inference system. The second aspect is design of fuzzy controller which can be implement for leading ideal trajectory in longitudinal direction. Design of fuzzy system is realized in MATLAB environment where the vehicle dynamic is known. This dynamic is result of identification methods realized on the Institute of Automatic Control at the University of Erlangen-Nurnberg. Experimental results for the longitudinal vehicle guidance have been obtained by use of the Audi test vehicle equipped with sensors and control devices.

The possibility of using different kind of cruise control algorithms in the vehicle tracking style adjustment was shown in this paper. These vehicle tracking styles ranged from extremely comfort to extremely sportive ones and different from each other respect to acceleration signals of the tracking vehicle. First, short overview of a neural network based algorithm was shown in order to achieve desired level of the tracking comfort. Also, the possibility of the tracking style adjustment was presented using Pipes and linear optimal control model. The appropriate parameter space regions for different level of comfort have been found with respect to the given cost function of the tracking style.

Bosnia and Herzegovina is very rich with cultural heritage sites. Perhaps the most famous of these are the stecaks; the monumental gravestones of Bosnian Heretic Christians. The orientation of the stećaks was important to the ancient Bosnians, Unfortunately, their orientation towards the sun has been changed when they were moved from their original locations to more secure sites at museums. This is particularly true of the stećak from Donje Zgosce, one of the most beautiful stećaks in B&H. Using high-fidelity graphics techniques we have created a detailed virtual reconstruction of this stećak and produced a sun simulation in Maya This enables archaeologists to be able to investigate the interaction of the light with the stećak’s carvings as it may have appeared in 14 century.

In this paper, capabilities of a feed-forward neural network regarding control of the complex object are investigated. Neural controllers have been trained by a genetic algorithm with adaptive mutation and crossover probabilities. A specific model of aggressive selection operator is proposed along with one way of co-evolution of the crossover and mutation rates. Also, different mechanisms of operator adaptation were compared in sense of resulting controller performance. Finally, the measurement results, taken from the object (hydraulically driven two-joint robot arm) are presented.

The purpose of this paper is to show a simple ability of using neural networks in longitudinal vehicle guidance. The main motivation is an opportunity of neural networks to learn from acquired real driver data, as well as to reproduce many driver behaviour styles raging from extremely comfort to extremely sportive ones. This possibility is shown with a simulated model based longitudinal trajectory generation. This model has used an adjustable comfort parameter for different sorts of driver behaviour. Experiment results, obtained with Audi test vehicle, are also presented.

In terms of reducing efforts of an animator in creating facial animation keyframes we developed a system for automatic keyframe generation using MaxScript control script. Input parameter for the script is a parameter file containing phonemes of the prerecorded soundtrack and their durations. Recognition of phonemes is done by an LVQ neural network. After keyframes are created by the script, the animator is able to perform fine tuning and adding facial expressions of the emotions.

The purpose of this paper is to show a simple ability of a neural network usage in longitudinal vehicle guidance for the comfort adjustment. It gives a short overview of a trajectory generation algorithm as well as comfort adjustment for longitudinal movement using neural networks. The algorithm for longitudinal trajectory generation was implemented in AUDI test vehicle and the results have been shown. Also, two concepts of comfort adjustment using neural networks were also presented. The comfort adjustment was associated with the certain driver tracking style ranging from extremely comfort to extremely sportive ones

Thepurpose ofthis paperistoshowasimple ability ofa neuralnetworkusageinlongitudinal vehicle guidance forthecomfortadjustment. Itgivesa short overview ofa trajectory generation algorithm aswellas comfort adjustment forlongitudinal movementusing neural networks.The algorithm for longitudinal trajectory generation wasimplemented inAUDItestvehicle andthe results havebeen shown.Also,twoconcepts ofcomfort adjustment using neural networks werealsopresented. The comfort adjustment wasassociated withthecertain driver tracking style ranging fromextremely comfort toextremely sportive ones.

In this paper we establish equivalence between a theory of fuzzy functional dependences and a fragment of fuzzy logic. We give a way to interpret fuzzy functional dependences as formulas in fuzzy logic. This goal is realized in four steps. Truth assignment of attributes is defined in terms of closeness between two tuples in a fuzzy relation. A corresponding fuzzy formula is associated to a fuzzy functional dependence. It is proved that if a relation satisfies a fuzzy functional dependence, then the corresponding fuzzy formula is satisfied and vice verse. Finally, equivalence of a fuzzy formulas and a set fuzzy functional dependence is demonstrated. Thus we are in position to apply the rule of resolution from fuzzy logic, while calculating fuzzy functional dependences.

Accurate facial animation is rapidly becoming a key feature in computer animation, from movie production to software agents. A lot of practical work in computer animation presently is done by 3ds max software. An advantage of this system is that one of the hardest part of an animator's work, creating key frames based on prerecorded soundtrack, can be automated using MaxScript control script. However, to achieve realistic results, any generated facial animations must be manually fine tuned by adding facial expressions and emotions. This paper analyses different methods for reducing the problem of phonemes in speech animation for virtual characters. Through examples created using a control parametrization approach, the paper discusses different levels of phoneme reduction, their look and application in several areas of computer animation production.

In this paper we establish equivalence between a theory of fuzzy functional dependences and a fragment of fuzzy logic. We give a way to interpret fuzzy functional dependences as formulas in fuzzy logic. This goal is realized in a few steps. Truth assignment of attributes is defined in terms of closeness between two tuples in a fuzzy relation. A corresponding fuzzy formula is associated to a fuzzy functional dependence. It is proved that if a relation satisfies a fuzzy functional dependence, then the corresponding fuzzy formula is satisfied and vice verse. Finally, equivalence of a fuzzy formulas and a set fuzzy functional dependence is demonstrated. Thus we are in position to apply the rule of resolution from fuzzy logic, while calculating fuzzy functional dependences.