Skip to main content
main-content

Über dieses Buch

This volume covers the state-of-the art of the research and development in various aspects of computational intelligence and gives some perspective directions of development. Except the traditional engineering areas that contain theoretical knowledge, applications, designs and projects, the book includes the area of use of computational intelligence in biomedical engineering. „Aspects of Computational Intelligence: Theory and Applications” is a compilation of carefully selected extended papers written on the basis of original contributions presented at the 15th IEEE International Conference on Intelligence Engineering Systems 2011, INES 2011 held at June 23.-26. 2011 in AquaCity Poprad, Slovakia.

Inhaltsverzeichnis

Frontmatter

Diagnostics, Performance Monitoring and Conditional - Based Maintenance

Residual Generator for a Class of Nonlinear Systems Described by Takagi-Sugeno Models

The paper presents the principle of fuzzy-observer-based residual generator design for a class of continuous-time nonlinear systems represented by Takagi-Sugeno models, and measurable, as well as un-measurable premise variables. The problem addressed can be indicated as approach giving sufficient design conditions outlined in the terms of linear matrix inequalities, and possess a global stable structure. Simulation results illustrate the design procedures and demonstrate the basic performances of the proposed residual generator structures.
Dušan Krokavec, Anna Filasová, Vratislav Hladký

Lead-Lag Controller-Based Iterative Learning Control Algorithms for 3D Crane Systems

This chapter deals with the application of two Iterative Learning Control (ILC) structures to the position control of 3D crane systems. The control system structures are based on Cascade Learning (CL) and Previous and Current Cycle Learning (PCCL) which improve the control system performance with frequency domain designed lead-lag controllers for the x-axis and for the y-axis. The parameters of continuous-time real PD learning rules which are also implemented in real-world applications as lead-lag controllers are set such that to fulfill the convergence conditions of CL and PCCL. Elements of anti-swing control for the PCCL structure are discussed. Experimental results are given to solve the crane position control problem of a 3D crane system laboratory equipment.
Radu-Emil Precup, Florin-Cristian Enache, Mircea-Bogdan Rădac, Emil M. Petriu, Stefan Preitl, Claudia-Adina Dragoş

Algorithms for Pitch Distance Determination

The paper describes algorithms used for the determination of pitch distances in the calibration of optical scales on a calibration machine. Two groups of algorithms are used: the non-contextual and the contextual ones. The first group is used to calculate the position of the edges in the digital image captured by the camera is either based on the gradient or the so called Laplacian method without any prior knowledge of the shape of the object. The contextual group of algorithm make use of the a priori knowledge of the edge or shape and its position. The information carried by gray level values of the pixelsenables us to reach subpixel resolution. The algorithms in the second group calculate the centreline of the graduation or measuring line either using Gabor transformation or from the centre of gravity formed by the gray values of the individual pixels. The resistance of the algorithms to various distortions on the scale was investigated. Finally the whole calibration system was described, uncertainty components are enumerated and experimental results are given.
Gyula Hermann

Objects for Visualization of Process Data in Supervisory Control

Supervisory control system represents a central unifying part of information and control system of industrial plant processes. Particularly at present, supervisory control applications even allocates a big share of factory software investments. The fundamental goal of projecting supervisory application is to establish stable and fast communication with technological process level to obtain data from processes and to design visualization screens in a suitable form to ensure readily visible information and control functions of processes in a plant. That is realized by visualization screens developed using graphical objects from different fields of industries which gives system builders much more effective tools for designing of visualization application and better visibility of process elements on screen. It is very closely related to trend objects used in visualization as monitoring components. This article presents concept of trend objects used in visualization screens of supervisory control application using software products from Wonderware Corp.
Iveta Zolotová, Roman Mihal’, Rastislav Hošák

Mesurement of Energy Flows and CO2 Emissions Balance of the Low-Potential Heat Source in Combination with a Cogeneration Unit

Traditional ways of heating with natural gas or electric energy can be effectively replaced or supplemented by alternative heating which can utilise heat from the ambient environment. Improving the energy efficiency and developing the renewable energy which closely relate to the general economy and social policy in most countries. They have a real potential to contribute to the sustainable development and economic growth and can influence all areas of economic activity and are one of the sophisticated method out of the economic crisis. The article is devoted to the use of non-traditional energy sources, which are the method of heating and hot water preparation using heat pumps in combination with a cogeneration unit. The experimental part balances the system of heat pump and cogeneration unit, the effect of the different parameters of the system operation in running of the whole system.
Natália Jasminská

New Approaches in Mechatronics, Modeling and Human Knowledge

Frontmatter

Intelligent Supervisory System for Small Turbojet Engines

The paper deals with design of an intelligent supervisory system usable in the area of engineering applications of small turbojet engines. Such supervisory system consists of diagnostic and control system applied in different phases of the engine’s operation. In order to design it we need to know the object and its models that will be realized by means of situational modeling concept and neural networks. Diagnostic system will be based on these types of models applied into the majority voting method of online diagnostic. Intelligent supervisory system will also include off-line pre-start diagnostics for such engine with perspective health monitor database.
Rudolf Andoga, Ladislav Madarász, Tomáš Karol’, Ladislav Főző, Vladimír Gašpar

Product Definition Using Knowledge in Human Influence Representation

Joining to a recent trend for including human defined active knowledge in product model to replace direct definition of product objects the authors of this chapter defined a new method for the representation of human participation in product model construction. This is one of the results authors achieved in the topic of human request driven product model definition. The proposed model representation applies human request based active knowledge and assists handling information for the lifecycle of product as a contribution to Product Lifecycle Management (PLM) technology. Current PLM technology represents well-proven engineering practice utilized at so many leading companies. Recognizing this situation, the authors proposed implementation of the proposed modeling in professional PLM environments using application programming interface tools. In this chapter, product model space and contextual engineering process are introduced. Outside affects on product definition, contextual chain for outside affects and connections with actual product definition are explained. Because current product modeling had not capabilities for description of human thinking process in the product model, a new solution was conceptualized that use knowledge based contextual chain for product definition. The authors introduced extended model space where extension spaces constitute a contextual chain and map content to product features in model space.
László Horváth, Imre J. Rudas

Usage Dependent Rehabilitation and Maintenance Model for Special Engineering Structures

An engineering structures rehabilitation and maintenance model is presented. The problem is to give the maintenance and rehabilitation action for each year of the planning period. There are given several conditions to fulfill. Two objectives should be presented: the system optimum is to minimize the total action cost, the user optimum is to maximize the user benefit. The problem is to determine such an optimum which fulfill the given conditions and either user or system optimum.
There are several models to solve this problem: linear or integer programming, heuristic, stochastic etc. In the paper two models are presented. The first is a stochastic programming model which is formulated for maintenance and rehabilitation of a road network. The other model is a linear programming which was formulated for other engineering structures.
Kornélia Ambrus-Somogyi, András Bakó

Course and Engineering Model Integration for Teaching Automation

By changing environment of engineering activities to extensive and highly integrated models in unlimited computer systems, more and more expert consider integration of product modeling, higher education, and industrial practice in a common environment in which recent shortage of problem solving based education of engineers can be decreased. Joining to the efforts in order to achieve this, the authors of this chapter revised and applied their earlier concepts and approaches and prepared a new approach to the above integration. This chapter starts with an opinion for the future of integration of engineering higher education processes and practice. Relevant works are cited to introduce important concepts and approaches. Following this, the three computer system based technologies are proposed to integrate in advanced higher education courses, communication of processes in the proposed integrated modeling is discussed, and computer model description of higher education system including information for the related areas is explained. Finally, Possibility for implementation in teaching-learning environment, where understanding of real industrial problems motivates problem solving is outlined as future plan.
József Gáti, Gyula Kártyás, Marián Bučko

Dynamics and Control of a Snake Robot Rectilinear Motion

The paper deals with a snake robot rectilinear motion on the flat surface. At first, biological snake rectilinear motion observed in the nature is introduced. Based on this the transformation of biological snake body to the mechanical system is established. After pattern gait design and motion conditions introduction the mathematical model of snake robot rectilinear motion is established. Subsequently an average velocity of motion is derived. From the equation of average velocity the optimal number of masses is derived in order to maximum system velocity. The average velocity courses for different pairs of materials in the graph are shown. In the next section a feedback control system for masses displacement is introduced. For this purpose PD regulator is used. In conclusion the summary of study and simulation are done.
Alexander Gmiterko, Michal Kelemen, Ivan Virgala, Róbert Surovec, Martina Vacková, Erik Prada

Computational Intelligence, Web Technologies and Data Mining

Frontmatter

Smart and Cooperative Neighbourhood for Spatial Routing in Wireless Sensor Networks

The outcome of applying relations and set theories instead of functions when staging the proposed routing algorithm is an appearance of choice in Wireless Sensor Network nodes. This research presents a model that is universal, practical, and mathematically sound. In its essence, the model promotes the emergence of a smart and cooperative neighbourhood. Central, to a rise of emergent properties in WSN, is the deployment of nodes within neighbourhood that are equipped with some form of collective intelligence. While defining the concept of spatial routing, we unfold the rules of smart neighbourhood for relaying data in a dynamic and evolving environment. The most interesting aspect of the proposed concept of neighbourhood smartness is its support for a certain form of stigmergy that allows neighbourhoods behavioural flexibility in WSN. The network routing paths adapt to the level of interference and thus avoiding areas of increased disturbance. By using Link Quality Indicator parameters, it is possible to choose the best consecutive relay. This allows adjusting our choices to the disturbance levels and thus circumventing the area of interference. In the end; this ensures a successful transmission even in the most adverse environmental conditions.
Jan Nikodem, Zenon Chaczko, Maciej Nikodem, Ryszard Klempous

Elimination of Dynamic Errors of Thermocouples in Aircraft Engines Using Neural Networks

The article is focused on diagnostics in the field of aviation turbo-jet engines. Evaluation of their technical status, and potential failures and pre-failure processes can be improved by monitoring their thermally loaded components. Part of the research in the given area also involves mathematical modeling of the channel measuring the exhaust gases temperature, using neural networks to compensate for dynamic errors of slow thermocouples used in such measurements.
František Adamčík, Rudolf Andoga, Ladislav Madarász, Peter Krajňák

Special Aspects of Teaching in Virtual Learning Environments

In the Information Society in the 21st century the ever evolving information technological innovations and challenges force education to introduce these innovations in the teaching and learning processes. Students expect stimuli and challenges and are not satisfied any more with the traditional and conventional ways of learning.  Thus the launch and spreading of 3D virtual learning environments is a must in public and higher education as well and will expectedly boom in the next decade. This paper outlines the special aspects to be considered when developing and introducing virtual learning environments considering both the student and the teacher sides.
Andrea Tick

Weights Aging in Social Networks

This paper describes basic approaches for modeling collaboration social networks. Some of the new extensions are described – new approach for weighting of the ties among event participants; and temporal based method for modeling of network evolution – aging of the ties among actors in passing time. We evaluate proposed methods by two experiments with the real data set and we compare our modeled network with the reference data gathered from people’s opinions expressed in targeted inquiries.
Gabriel Tutoky, Ján Paralič

Methodologies, Methods and Algorithms

Frontmatter

The HOSVD Based Canonical Form of Functions and Its Applications

The paper deals with the theoretical background of the higher order singular value decomposition (HOSVD) based canonical form of functions. Furthermore in special case it describes the relation between the canonical form and the Hilbert-Schmidt type integral operators. The described techniques have a variety of applications, e.g. image processing, system identification, data compression, filtering, etc. As an example of application from the field of intelligent systems, a tensor-product based concept is introduced useful for approximating the behavior of a strongly non-linear system by locally tuned neural network models. The proposed approach may be a useful tool for solving many kind of black-box like identification problems. The weights in the corresponding layers of the input local models are jointly expressed in tensor-product form such a way ensuring the efficient approximation. Similar concept has been used by the authors for approximating the system matrix of linear parameter varying systems in state space representation. We hope that the proposed concept could be an efficient compromised modeling view using both the analytical and heuristic approaches.
András Rövid, László Szeidl, Péter Várlaki

Anytime Extension of Generalized Fuzzy Neural Network Models with Non-singleton Consequents

Nowadays practical solutions of engineering problems involve model-integrated computing. Model based approaches offer a challenging way to integrate a priori knowledge into the procedure. Recently, Artificial Neural Networks (ANNs) has become popular because they are able to learn complex mappings from the input/output data and are relatively easy to implement in any application. Generalized Neural Network (GNN) based models may have an exceptional role at many fields, where the problem to be solved is complex, highly nonlinear or when only partial, uncertain and/or inaccurate data is available, however their high complexity, and in certain cases unknown accuracy, can limit the applicability, especially in time critical situations. Combining GNNs with anytime techniques may offer a solution to the complexity problem, but only in cases when the error of the reduced models can be estimated. In this paper, author gives error bounds for a new class of GNNs where the nonlinear transfer functions are approximated by product-sum-gravity fuzzy systems with non-singleton consequents (NGFNN) thus extending the range of possible anytime soft computing models. The model complexity can flexibly be reduced to cope with the temporal, possibly dynamically changing resource, time, and data availability. It is shown that the accuracy of the reduced models can be upper-bounded and thus, the error is always known, and further, monotonously decreases parallel with the increase of the complexity of the used model. These features make NGFNNs suitable for anytime use.
Annamária R. Várkonyi-Kóczy

On Probabilistic Correlation Coefficients for Fuzzy Numbers

In this paper we introduce alternative definitions for the measure of interactivity between fuzzy numbers by defining non-uniform probability distributions on the γ-level sets (γ-cuts) of their joint possibility distribution. These probability distributions are determined by the shape function of the joint possibility distribution if we consider this as a probability density function (with an appropriate constant multiplier), so we use only the information contained in the joint possibility distribution. We also show some detailed examples for the calculation when the joint possibility distributions are defined by well-known t-norms, such as Mamdani, Lukasiewicz and Larsen t-norms.
Robert Fullér, István Á. Harmati, Péter Várlaki

Differential Evolution Algorithm in Optimal Design of Microstrip Filter

This chapter describes utilization of differential evolution algorithm in process of optimal design of microstrip filters. Main part of the chapter is dedicated to the definition of cost function, where filter design criteria are inserted to the process by tolerance scheme and mathematical model used for evaluation of microstrip filter magnitude response. The solution found is evaluated and compared to a conventional design in the concluding part of the chapter. Discussion of difference between realized samples and mathematical model is also presented at the end of this chapter.
Juraj Paleček, Peter Vestenický, Martin Vestenický, Juraj Spalek

P-Single Operators in Pipeline System of DF-KPI Architecture

There has been a resurgence of interest in data flow architectures, because the dataflow model of execution offers attractive properties for parallel processing. In data flow architectures the computing process is managed by the operands flow accessed on different levels for executing instructions of dataflow program. Data flow architectures have been traditionally classified as either static or dynamic. The architecture described in this article belongs to a class of dynamic data flow architectures, in which the operand process control significantly affects the performance parameters as well as the system characteristics of the given architecture. From the many types of operators, this article provides microprogram managing for P-single operators in pipeline system of DF-KPI architecture.
Liberios Vokorokos, Norbert Ádám, Branislav Madoš

Potential Application of P-Graph-Based Workflow in Logistics

The free movement of goods and the liberalization of the markets in Europe resulted in heavy transport and overloading of motorways and public roads, definitely putting an obstacle to economic growth in the European Union. The further construction and reconstruction of such roads cannot keep pace with the increasing demand, furthermore, puts a heavy burden on the states’ budget. Since traffic cannot be increased further more some other solutions must be found. Such an alternative solution could be to develop optional models for logistics. This paper examines the possible usage of the P-graph-based workflow for modeling logistical problems. The application of P-graph-based workflow is justified by the fact that it has already been applied successfully in other fields of industry. Further, the paper will examine the opportunities of P-graph modeling in a specific field of logistics Supply Chain Management, and will also introduce a new term the P-graph based Supply Chain Model.
József Tick

Softcomputing in Biomedical Engineering

Frontmatter

Linear Surgical Instrument for Bipolar Multielectrode Radiofrequency Ablation

The aim of the work is about the design and realization of linear surgical instrument for bipolar multielectrode radiofrequency ablation. The Radiofrequency intervention is more used in an abdomen surgical technique. The present tools are universal for most of the operation with several disadvantages for large ablation. Our designed and tested surgical tool consist of ten needles linear electrodes bipolar driven by existing standard used generators. Proposed surgical tool, in comparison with existing tools, used in extended ablation saves significant part of healthy tissue and also operational time.
Marek Penhaker, Petr Vavra, Milada Hlavackova, Jan Kracmar, Tadeusz Sikora, Lukas Prokop

Biomedical Applications of Diagnostics and Measurements by Industrial Computer Tomography

The aim of presented study is a review on biomedical applications of industrial computed tomography (CT). Industrial CT enables in contrast to medical CT scanning of technical materials (plastic materials, low density metals, wood, etc.) but also living tissues in vitro. Important parameters for scanning are maximum size of the part 300 x 300 x 300 mm; and the best obtainable resolution of the digitalized scan is 9 μm. The termination for the scanning is also density of material, where low density medical materials like titanium or medical polymers are applicable. Presented review shows potentials of industrial CT for biomedical applications; an assembly inspection, damage analysis, inspection of materials, porosity analyses, conventional defect, and the reverse engineering.
Paper presents several biomedical studies realized by industrial CT, including epithetic foot and obtained 3D model for inner structures and materials analysis, epithetic hand glove for material homogeneity analysis, where recent thickness is required, reverse engineering of human teeth to get the STL file for further applications (fabrication by additive manufacturing), animal skulls scanning and digitalization for preservation of museum exhibits, scanning of orthosis and total hip replacements. The end of the study shows the full process of porous implant design, using metrotomographic bone-like porous structure.
Radovan Hudák, Jozef Živčák, Peter Kat’uch, Bruno Goban

Infrared Thermography in the Evaluation of Carpal Tunnel Syndrome

The Aim of the study was to identify the temperature difference between physiologically healthy and pathologically hand affected by carpal tunnel syndrome (CTS). For the purposes of this study were created two databases of 190 thermograms of dorsal side of hands. The first database consists of normal thermograms of physiologically healthy hands called reference group (RG n= 174). The second is the database with 16 pathological hands ( CTS n=16) with clinically diagnosed CTS in 9 patients. Pre-surgical thermograms of the volunteers’ hands affected by CTS were obtained using infrared thermography (Thermocamera Fluke Ti55/20). We have observed the temperature distribution in the entire hand and partial temperatures for two years. The main significant areas for this study were the center point of carpals (T1) and the area of distal phalanges on middle fingers (T5). The Index of Median Nerve (D MI=(T1-T5) were determined based on resulting data. Test results obtained from measurements of the two points on the dorsal side of hands have showed that the temperature of CTS hands is typically higher in the phalanges as opposed to the wrist (D MI0; 75,0%), while the temperature is the lowest in the distal phalanges (T5) of healthy hands (D MI>0, 68.4%). The calculated sensitivity of diagnostic test with the confidence interval 0,750±0.202 and the specificity of diagnostic test with the confidence interval 0,684±0.069 show that thermography could be a promising method in the diagnostic process of CTS.
Mária Tkáčová, Radovan Hudák, Jozef Živčák, Ivana Živčáková

Determination of Conditions and Positions for Obtaining Thermographic Atlas

The study is concerned with the basic conditions to create a thermographic atlas of the human body. The main goal of research had been measurement and comparison in temperature distribution of healthy human bodies which were obtained by infrared thermography for one year. It was used Infrared Imager with detector type 320x240 Focal Plane Array. For the purposes of research, we created a database of 570 healthy thermograms, which were taken from 30 volunteers (ni=30) in nineteen positions (j).The database of atlas consisted of 15 healthy men (15 male, Mn=15) and 15 healthy women (15 female, Fn=15). The average age of volunteers was 22,8 years. The average BMI was 22,7 (normal weight).By thermography, we have obtained temperature maps on bodies. In the process of analyzing the thermograms we obtained qualitative and quantitative data on areas of interest. The database can be helpful for comparison in the diagnostics of many neurovascular and musculoskeletal diseases or injuries.
Mária Tkáčová, Radovan Hudák, Jozef Živčák, Patrícia Čekanová, Štefan Medvecký

Determining the Calibration Element Location in Planning of Surgical Interventions

At the present time in many countries of the world preoperative planning of interventions for lumbar joint is realized with caliper, protractor, plastic templates and x-ray images. From these reasons the measurement is time consuming with many errors. Over the past few years, an increasing appreciation of the usefulness of digital technology has emerged among various field of medicine. CoXaM offers a simple solution to the problem of using digital X-ray images and handmade plastic templates. The developed software combines digital X-ray images with digital templates for planning the implantation or re-implantation of hip joints. The technique is reliable, cost-effective and acceptable to patients and radiographers. It can easily be used in any radiography department after a few simple calculations and preparation of appropriately sized discs. The CoXaM software provides several advantages for orthopedic surgery. X-ray film is no longer necessary, and there are no radiographs to store, lose or misplace. Significant clinical studies are planned to confirm statistically the qualitative value of the software and the quantitative precision of the output parameters.
Monika Michalíková, Teodor Tóth, Lucia Bednarčíková, Jozef Živčák

Application of Magnetic Microwires in Titanium Implants – Conception of Intelligent Sensoric Implant

The idea of intelligent sensoric implant which enables to scan parameters from the human body wireless comes from analysis of studies descrbing reasons of implants rejection or loosening. Inflamations and incorrect biomechanical load are offen the reasons for surgery, where implant has to be removed or replaced. Presented study shows a concept of intelligent dental implant, where magnetic microwires are placed and fixed into titanium dental implant to get parameters from implant, tissue, or implant-tissue interaction. A part of the study shows preparation of magnetic microwires, measurement of physical quantities using bistabile magnetic microwires and realisation of the functional model of the sensor and experiments. Obtained results show, that utilization of magnetic microwires in implants for scanning of selected physiological or physical parameters is promising. The further researches in the field of fabrication technology, magnetic wires preparation and scanning processes to confirm an intelligent sensoric implant concept is necessary.
Radovan Hudák, Rastislav Varga, Jozef Živčák, Jozef Hudák, Josef Blažek, Dušan Praslička

Backmatter

Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise