Global ETD Search

51	Umělé neuronové sítě a jejich využití při extrakci znalostí / Artificial Neural Networks and Their Usage For Knowledge Extraction Petříčková, Zuzana January 2015 (has links) Title: Artificial Neural Networks and Their Usage For Knowledge Extraction Author: RNDr. Zuzana Petříčková Department: Department of Theoretical Computer Science and Mathema- tical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc., Department of Theoretical Computer Science and Mathematical Logic Abstract: The model of multi/layered feed/forward neural networks is well known for its ability to generalize well and to find complex non/linear dependencies in the data. On the other hand, it tends to create complex internal structures, especially for large data sets. Efficient solutions to demanding tasks currently dealt with require fast training, adequate generalization and a transparent and simple network structure. In this thesis, we propose a general framework for training of BP/networks. It is based on the fast and robust scaled conjugate gradient technique. This classical training algorithm is enhanced with analytical or approximative sensitivity inhibition during training and enforcement of a transparent in- ternal knowledge representation. Redundant hidden and input neurons are pruned based on internal representation and sensitivity analysis. The performance of the developed framework has been tested on various types of data with promising results. The framework provides a fast training algorithm,...
52	Realizace rozdělujících nadploch / The decision boundary Gróf, Zoltán January 2012 (has links) The main aim of this master's thesis is to describe the subject of the implementation of decision boundaries with the help of artificial neural networks. The objective is to present theoretical knowledge concerning this field and on practical examples prove these statements. The work contains basic theoretical description of the field of pattern recognition and the field of feature based representation of objects. A classificator working on the basis of Bayes decision is presented in this part, and other types of classificators are named as well. The work then deals with artificial neural networks in more detail; it contains a theoretical description of their function and their abilities in the creation of decision boundaries in the feature plane. Examples are shown from literature for the use of neural networks in corresponding problems. As part of this work, the program ANN-DeBC was created using Matlab, for the generation of practical results about the usage of feed-forward neural networks for the implementation of decision boundaries. The work contains a detailed description of this program, and the achieved results are presented and analyzed. It is shown as well, how artificial neural networks are creating decision boundaries in the form of geometrical shapes. The effects of the chosen topology of the neural network and the number of training samples on the success of the classification are observed, and the minimal values of these parameters are determined for the successful creation of decision boundaries at the individual examples. Furthermore, it's presented how the neural networks behave at the classification of realistically distributed training samples, and what methods can affect the shape of the created decision boundaries.
53	Modeling and Design of Modular MultilevelConverters for Grid Applications Ilves, Kalle January 2012 (has links) Grid-connected high-power converters are found in high-voltage direct current transmission (HVDC), static compensators (STATCOMs), and supplies for electric railways. Such power converters should have a high reliability, high efficiency, good harmonic performance, low cost, and a small footprint. Cascaded converters are promising solutions for high-voltage high-power converters since they allow the combination of excellent harmonic performance and low switching frequencies. A high reliability can also be achieved by including redundant submodules in the chain of cascaded converters. One of the emerging cascaded converter topologies is the modular multilevel converter (M2C). This thesis aims to bring clarity to the dimensioning aspects and limiting factors of M2Cs. The dc-capacitor in each submodule is a driving factor for the size and weight of the converter. It is found that the voltage variations across the submodule capacitors will distort the voltage waveforms and also induce alternating components in the current that is circulating between the phase-legs. It is, however, shown that it is possible to control the alternating voltage by feed-forward control. It is also shown that if the circulating current is controlled, the injection of a second-order harmonic component can extend the operating region of the converter. The reason for this is that when the converter is operating close to the boundary of overmodulation the phase and amplitude of the second-order harmonic is chosen such that the capacitors are charged prior to the time when a high voltage should be inserted by the submodules. The controller that is used must be able to balance the sbmodule capacitor voltages. Typically, an increased switching frequency will enhance the performance of the balancing control scheme. In this thesis it is shown that the capacitor voltages can be balanced with programmed modulation, even if fundamental switching frequency is used. This will, however, increase the voltage ripple across the aforementioned capacitors. In order to quantify the requirements on the dc-capacitors a general analysis is provided in this thesis which is based on the assumption that the capacitor voltages are well balanced. It is found that for active power transfer, with a 50 Hz sinusoidal voltage reference, the capacitors must be rated for a combined energy storage of 21 kJ/MW if the capacitor voltages are allowed to increase by 10% above their nominal values. / <p>QC 20121127</p> Modular multilevel converter feed-forward control modulation switching frequency energy storage Annan elektroteknik och elektronik
54	Comparison of linear regression and neural networks for stock price prediction Karlsson, Nils January 2021 (has links) Stock market prediction has been a hot topic lately due to advances in computer technology and economics. One economic theory, called Efficient Market Hypothesis (EMH), states that all known information is already factored into the prices which makes it impossible to predict the stock market. Despite the EMH, many researchers have been successful in predicting the stock market using neural networks on historical data. This thesis investigates stock prediction using both linear regression and neural networks (NN), with a twist. The inputs to the proposed methods are a number of profit predictions calculated with stochastic methods such as generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive integrated moving average (ARIMA). By contrast the traditional approach was instead to use raw data as inputs. The proposed methods show superior result in yielding profit: at best 1.1% in the Swedish market and 4.6% in the American market. The neural network yielded more profit than the linear regression model, which is reasonable given its ability to find nonlinear patterns. The historical data was used with different window sizes. This gives a good understanding of the window size impact on the prediction performance. Stock market Stock market prediction prediction neural network feed forward neural network artificial neural network linear regression finance efficient market hypothesis EMH Engineering and Technology Teknik och teknologier
55	Feed-Forward Air-Fuel Ratio Control during Transient Operation of an Alternative Fueled Engine Garcia, Andrew Michael 09 August 2013 (has links) No description available. Mechanical Engineering Automotive Engineering air-fuel ratio control tailpipe emissions reduction feed-forward air-fuel ratio control model-based calibration intake manifold modeling Forward Euler approximation
56	The Effect of Tactile and Audio Feedback in Handheld Mobile Text Entry Edman, Christopher L. 30 August 2016 (has links) No description available. Communication Computer Engineering Computer Science Design Engineering Experiments Industrial Engineering Information Technology Physiological Psychology Psychology Systems Design Systems Science Technology text entry texting mobile handheld hand held hand-held feedback feed back feed-forward feed forward tactile haptic audio typing interface touchscreen touch-screen touch screen iPhone skilled skill-based behavior Gibson Rasmussen
57	Neurale netwerke as moontlike woordafkappingstegniek vir Afrikaans Fick, Machteld 09 1900 (has links) Text in Afrikaans / Summaries in Afrikaans and English / In Afrikaans, soos in NederJands en Duits, word saamgestelde woorde aanmekaar geskryf. Nuwe woorde word dus voortdurend geskep deur woorde aanmekaar te haak Dit bemoeilik die proses van woordafkapping tydens teksprosessering, wat deesdae deur rekenaars gedoen word, aangesien die verwysingsbron gedurig verander. Daar bestaan verskeie afkappingsalgoritmes en tegnieke, maar die resultate is onbevredigend. Afrikaanse woorde met korrekte lettergreepverdeling is net die elektroniese weergawe van die handwoordeboek van die Afrikaanse Taal (HAT) onttrek. 'n Neutrale netwerk ( vorentoevoer-terugpropagering) is met sowat. 5 000 van hierdie woorde afgerig. Die neurale netwerk is verfyn deur 'n gcskikte afrigtingsalgoritme en oorfragfunksie vir die probleem asook die optimale aantal verborge lae en aantal neurone in elke laag te bepaal. Die neurale netwerk is met 5 000 nuwe woorde getoets en dit het 97,56% van moontlike posisies korrek as of geldige of ongeldige afkappingsposisies geklassifiseer. Verder is 510 woorde uit tydskrifartikels met die neurale netwerk getoets en 98,75% van moontlike posisies is korrek geklassifiseer. / In Afrikaans, like in Dutch and German, compound words are written as one word. New words are therefore created by simply joining words. Word hyphenation during typesetting by computer is a problem, because the source of reference changes all the time. Several algorithms and techniques for hyphenation exist, but results are not satisfactory. Afrikaans words with correct syllabification were extracted from the electronic version of the Handwoordeboek van die Afrikaans Taal (HAT). A neural network (feedforward backpropagation) was trained with about 5 000 of these words. The neural network was refined by heuristically finding a suitable training algorithm and transfer function for the problem as well as determining the optimal number of layers and number of neurons in each layer. The neural network was tested with 5 000 words not the training data. It classified 97,56% of possible points in these words correctly as either valid or invalid hyphenation points. Furthermore, 510 words from articles in a magazine were tested with the neural network and 98,75% of possible positions were classified correctly. / Computing / M.Sc. (Operasionele Navorsing) Neural networks Backpropagation Feed-forward Training algorithm Transfer function Resilient backpropagation Early termination Encoding Hyphenation Syllabification 410.285 Afrikaans language -- Syllabication Afrikaans language -- Data processing Syllabication -- Data processing Neural networks (Computer science)
58	Neurale netwerke as moontlike woordafkappingstegniek vir Afrikaans Fick, Machteld 09 1900 (has links) Text in Afrikaans / Summaries in Afrikaans and English / In Afrikaans, soos in NederJands en Duits, word saamgestelde woorde aanmekaar geskryf. Nuwe woorde word dus voortdurend geskep deur woorde aanmekaar te haak Dit bemoeilik die proses van woordafkapping tydens teksprosessering, wat deesdae deur rekenaars gedoen word, aangesien die verwysingsbron gedurig verander. Daar bestaan verskeie afkappingsalgoritmes en tegnieke, maar die resultate is onbevredigend. Afrikaanse woorde met korrekte lettergreepverdeling is net die elektroniese weergawe van die handwoordeboek van die Afrikaanse Taal (HAT) onttrek. 'n Neutrale netwerk ( vorentoevoer-terugpropagering) is met sowat. 5 000 van hierdie woorde afgerig. Die neurale netwerk is verfyn deur 'n gcskikte afrigtingsalgoritme en oorfragfunksie vir die probleem asook die optimale aantal verborge lae en aantal neurone in elke laag te bepaal. Die neurale netwerk is met 5 000 nuwe woorde getoets en dit het 97,56% van moontlike posisies korrek as of geldige of ongeldige afkappingsposisies geklassifiseer. Verder is 510 woorde uit tydskrifartikels met die neurale netwerk getoets en 98,75% van moontlike posisies is korrek geklassifiseer. / In Afrikaans, like in Dutch and German, compound words are written as one word. New words are therefore created by simply joining words. Word hyphenation during typesetting by computer is a problem, because the source of reference changes all the time. Several algorithms and techniques for hyphenation exist, but results are not satisfactory. Afrikaans words with correct syllabification were extracted from the electronic version of the Handwoordeboek van die Afrikaans Taal (HAT). A neural network (feedforward backpropagation) was trained with about 5 000 of these words. The neural network was refined by heuristically finding a suitable training algorithm and transfer function for the problem as well as determining the optimal number of layers and number of neurons in each layer. The neural network was tested with 5 000 words not the training data. It classified 97,56% of possible points in these words correctly as either valid or invalid hyphenation points. Furthermore, 510 words from articles in a magazine were tested with the neural network and 98,75% of possible positions were classified correctly. / Computing / M.Sc. (Operasionele Navorsing) Neural networks Backpropagation Feed-forward Training algorithm Transfer function Resilient backpropagation Early termination Encoding Hyphenation Syllabification 410.285 Afrikaans language -- Syllabication Afrikaans language -- Data processing Syllabication -- Data processing Neural networks (Computer science)
59	Využití prostředků umělé inteligence na kapitálových trzích / The Use of Means of Artificial Intelligence for the Decision Making Support on Stock Market Vaško, Jan January 2011 (has links) Diploma thesis deals with analyzing the possibility of using artificial intelligence, specifically artificial neural networks and fuzzy logic, on the capital markets as a tool to support decision making in business. The Matlab software is used for this purpose. The work is divided into three parts. The first part deals with theoretical knowledge, brief description of the current situationin is covered in a second part and the theoretical solutions are applied to the system in the third section.
60	Aplikace lokálních aproximátorů pro řízení reálného mechatronického systému / Application of local approximators for control of real mechatronic system Palaj, Lukas January 2011 (has links) Cieľom práce je aplikácia lokálnych aproximátorov pre riadenie reálnych mechatronických sústav pomocou metódy dopredného riadenia predstavujúcej zaujímavú alternatívu k metódam využívajúcim globálne aproximátory. Po ukážkových príkladoch funkcie lokálnych aproximátorov bol navrhnutý algoritmus implementovaný pre riadenie dvoch sústav, elektronickej škrtiacej klapky a výukového modelu magnetickej levitácie, predstavujúcich vysoko nelineárne a nestabilné sústavy. Skúmali sme, či riadiaci algoritmus bude mať pozitívny vplyv na presnosť regulácie, ďalej bola skúmaná jeho schopnosť prispôsobiť sa zmene parametrov sústavy a tiež prípadná možnosť jeho implementácie pre mikrokontrolér znížením vzorkovacej frekvencie. Výsledky ukázali, že riadenie založené na lokálnych modeloch zlepšilo riadenie v porovnaní s jednoduchým PID regulátorom a že má schopnosť adaptability. Veľmi výhodné sa zdá byť jeho použitie pre zariadenia umožnujúce vzorkovaciu frekvenciu do 1 kHz.

Search results