a borítólapra  Súgó epa Copyright 
Acta polytechnica HungaricaVolume 4, Issue No. 3 (2007.)


Tematikus cím:Special Issue on Applied Computational Intelligence and Informatics - Guest Editors: Imre J. Rudas and Stefan Preitl
  • Sándor Tihamér Brassai ,
    László Bakó :

    Abstract: The hardware implementation of neural networks is a new step in the evolution and use of neural networks in practical applications. The CMAC cerebellar model articulation controller is intended especially for hardware implementation, and this type of network is used successfully in the areas of robotics and control, where the real time capabilities of the network are of particular importance. The implementation of neural networks on FPGA’s has several benefits, with emphasis on parallelism and the real time capabilities.This paper discusses the hardware implementation of the CMAC type neural network, the architecture and parameters and the functional modules of the hardware implemented neuro-processor.

    Keywords: Neural networks, CMAC, Neural networks hardware implementation, FPGA

  • László Horváth ,
    Imre J. Rudas ,
    Simona Vaivoda ,
    Zsuzsa Preitl :

    Abstract: Engineering for development, production, and other product related company activities are being organized in virtual systems for lifecycle management of product data. This new age of engineering is a result of the continuous development for step-by-step moving of product design, analysis and other production engineering activities from conventional environments to modeling environments during the eighties and nineties. However, more developments were needed in knowledge based decision assistance in order to realize modeling of human intent, increasingly complex product structures, and efficient communication of product data. In recent years, a great change of engineering methodology and software produced program products in knowledge technology and advanced local and global communication. Group work of engineers is increasingly organized around special portals for engineering on the Internet. Although intensive research activities produced outstanding methods in knowledge-based solutions for engineering, these methods have not widespread in the industrial modeling practice. This paper attempts to evaluate the possibility that recent communication and knowledge intensive engineering modeling can be developed into communication and knowledge intensive virtual space technology. Paper starts with a discussion on integrated application of different groups of product modeling techniques. Following this, methods are evaluated for the management of product data (PDM). Next section emphasizes aspects, contexts, and intents as primary issues in modeling for relationships in product data and decisions by engineers. Finally, methods for the management of engineering activities for lifecycle of products are summarized, considering communities of engineers around Internet portals.

  • Claudiu Pozna :
    An Introduction on Cognition System Design 33-47en [261.57 kB - PDF]EPA-02461-00011-0030

    Abstract: Present work is an introduction on cognition system design. This work is structured in two parts: the first consists on a phenomenological analyze of Artificial Intelligence collocation which will generate seven questions needed in cognition system design; the second part represents possible answers for the first questions. The last part represents also is the opportunity to present the plausible reasoning theory and to solve two examples.

    Keywords: plausible reasoning, Bayesian theory, model

  • András Rövid ,
    Takeshi Hashimoto :
    Improved High Dynamic Range Image Reproduction Method49-59en [583.02 kB - PDF]EPA-02461-00011-0040

    Abstract: High dynamic range (HDR) of illumination may cause serious distortions and other problems in viewing and further processing of digital images. This paper describes a new algorithm for HDR image creation based on merging images taken with different exposure time. There are many fields, in which HDR images can be used advantageously, with the help of them the accuracy, reliability and many other features of the certain image processing methods can be improved.

    Keywords: high dynamic range, multiple exposures, segmentation

  • Marius Crisan :
    Chaos and Natural Language Processing61-74en [157.49 kB - PDF]EPA-02461-00011-0050

    Abstract: The article explores the possibility to construct a unified word feature out of the component features of letters. Each letter is modeled by a different attractor and finally embedded in a quadratic iterated map. The result is the word feature that can account for the meaning extraction process of language understanding. This is a new approach in natural language processing based on the deterministic chaotic behavior of dynamical systems.

  • Zsuzsa Preitl ,
    Péter Bauer ,
    József Bokor :

    Abstract: In this paper a hybrid electric vehicle is considered, which contains both an internal combustion engine and an electric motor (EM). Without focusing on the other components of the vehicle, the EM is treated in detail, both regarding modelling aspects and control solutions. After a brief modelling of the plant, two cascade speed control solutions are presented: first a classical PI+PI cascade control solution is presented. The control systems related to traction electric motors (used in vehicle traction) must be able to cope with different requests, such as variation of the reference signal, load disturbances which depend on the transport conditions and parametric disturbances regarding changes in the total mass of the vehicle. For this purpose, in the design of the speed controller (external loop) a specific methodology based on extension of the symmetrical optimum method is presented. The controllers are developed using the Modulus–Optimum method for the inner loop, and the Extended Symmetrical Optimum Method, corrected based on the 2p-SO-method, for the outer loop (for a more efficient disturbance rejection). In order to force the behaviour of the system regarding the reference input, a correction term is introduced as a non-homogenous structured PI controller solution. Simulations were performed using numerical values taken from a real application consisting in a hybrid vehicle prototype, showing satisfactory behaviour.

    Keywords: Electric Hybrid Vehicle, Driving system, Speed control, Extended Symmetrical Optimum method, 2p-SO-m

  • Doina Dragulescu ,
    Adriana Albu :
    Medical Predictions System89-101en [271.06 kB - PDF]EPA-02461-00011-0070

    Abstract: Health has a strong impact upon all activities and human experts must have the ability to decide, in any circumstances, what is the illness level of a patient, which is the adequate treatment and which will be the evolution of the patient during the treatment. But medical decision making may be a very difficult activity. There are a lot of applications in artificial intelligence domain that try to help human experts offering solutions for a problem. This paper describes an expert system developed in order to make some predictions regarding the hepatitis infection.

    Keywords: hepatitis infection, expert system, logical inference, statistical inference, artificial neural networks

  • Zoltán Vámossy :

    Abstract: The paper describes a map building module, where the image sequences of the omnidirectional camera are transformed into virtual top-view ones and melted into the global dynamic map. After learning the environment from training images, a current image is compared to the training set by appearance-based matching. Appropriate classification strategies yield an estimate of the robot's current position.

    Keywords: PAL (Panoramic Annular Lens), omnidirectional vision, appearance-based navigation

  • Shih-Yang Yang ,
    Po-Zung Chen ,
    Chu-Hao Sun :
    Using Petri Nets to Enhance Web Usage Mining113-125en [251.83 kB - PDF]EPA-02461-00011-0090

    Abstract: Precise analysis of the web structure can facilitate data processing and enhance the accuracy of the mining results in the procedure of web usage mining. Many researchers have identified that pageview identification and path completion are of great importance in the result of web usage mining. Currently, there is still a lack of an effective and systematic method to analyze and deal with the two steps. In the present study, we propose the application of Petri Nets (PN), a model used to analyze the framework of webpages in a website. We adopt Place in the PN model to represent webpage on the websites and use Transition to represent hyperlink. The study explores how to undergo the pageview identification after we use the PN model to conduct the analysis of the framework and then obtain incident matrix. Likewise, we use reachability property in the model to undergo path completion.

    Keywords: Petri nets, Web usage mining, Data Preprocessing

  • Marius-Lucian Tomescu ,
    Stefan Preitl ,
    Radu-Emil Precup ,
    József K. Tar :

    Abstract: This paper presents a new stability analysis method for nonlinear processes with Takagi-Sugeno (T-S) fuzzy logic controllers (FLCs). The design of the FLCs is based on heuristic fuzzy rules. The stability analysis of these fuzzy control systems is performed using LaSalle’s invariant set principle with non-quadratic Lyapunov candidate function. This paper proves that if the derivative of Lyapunov function is negative semi-definite in the active region of each fuzzy rule, then the overall system will be asymptotically stable in the sense of Lyapunov (ISL). The stability theorem suggested in the paper ensures sufficient stability conditions for fuzzy control systems controlling a class of nonlinear processes. The end of the paper contains an illustrative example that describes an application of the stability analysis method.

    Keywords: Fuzzy logic controller, Lyapunov stability, nonlinear system, LaSalle’s invariant set principle