Neste trabalho é proposta uma plataforma robótica móvel, concebida de maneira modular e hierárquica, visando o estudo de diversos aspectos aplicados à navegação, tanto autônoma quanto semi-autônoma, em ambientes internos. O sistema proposto possibilita a implementação de arquiteturas reativas e híbridas com aprendizagem, sendo a importância e limitações desta última discutidas. Utilizando a plataforma desenvolvida, uma aplicação de navegação robótica com aprendizagem supervisionada é realizada, usando sensores de ultra-som e através de tele-operação. O objetivo é fazer com que o agente associe, em tempo real, suas próprias respostas sensoriais com as ações motoras realizadas pelo tele-operador, permitindo que a tarefa seja repetida autonomamente com alguma generalização. Para realizar tal mapeamento, uma rede de função de base radial (RBF), usando um algoritmo de aprendizado seqüencial, é apresentada e utilizada. / This work presents a mobile robotic platform, built as a modular and hierarchical approach, aiming at the study of several aspects of indoor navigation. The proposed system allows the implementation of reactive and hybrid architectures with learning, for autonomous or semi-autonomous navigation. The importance and limitations of the learning characteristics are discussed. An application of robotic navigation with supervised learning is implemented using ultrasonic sensors and teleoperation. The aim is the agent to associate, in real time, its own sensorial perception to the motor actions realized by a teleoperator, allowing the task to be repeated in an autonomous way, with some generalization. To make the corresponding mapping, a radial basis function network (RBF), trained by a sequential learning algorithm, is presented and used.

Because blades in jet engine compressors are subject to dynamic loads based on the engine's speed, it is essential that the blades are properly "tuned" to avoid resonance at those frequencies to ensure safe operation of the engine. The tuning process can be time consuming for designers because there are many parameters controlling the geometry of the blade and, therefore, its resonance frequencies. Humans cannot easily optimize design spaces consisting of multiple variables, but optimization algorithms can effectively optimize a design space with any number of design variables. Automated blade tuning can reduce design time while increasing the fidelity and robustness of the design. Using surrogate modeling techniques and gradient-free optimization algorithms, this thesis presents a method for automating the tuning process of an airfoil. Surrogate models are generated to relate airfoil geometry to the modal frequencies of the airfoil. These surrogates enable rapid exploration of the entire design space. The optimization algorithm uses a novel objective function that accounts for the contribution of every mode's value at a specific operating speed on a Campbell diagram. When the optimization converges on a solution, the new blade parameters are output to the designer for review. This optimization guarantees a feasible solution for tuning of a blade. With 21 geometric parameters controlling the shape of the blade, the geometry for an optimally tuned blade can be determined within 20 minutes.

<p>This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.</p>

The Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special cases. In the RBF case, the SV algorithm automatically determines centers, weights and threshold such as to minimize an upper bound on the expected test error. The present study is devoted to an experimental comparison of these machines with a classical approach, where the centers are determined by $k$--means clustering and the weights are found using error backpropagation. We consider three machines, namely a classical RBF machine, an SV machine with Gaussian kernel, and a hybrid system with the centers determined by the SV method and the weights trained by error backpropagation. Our results show that on the US postal service database of handwritten digits, the SV machine achieves the highest test accuracy, followed by the hybrid approach. The SV approach is thus not only theoretically well--founded, but also superior in a practical application.

This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.

The vector finite element method has gained great attention since overcoming the deficiencies incurred by the scalar basis functions for the vector Helmholtz equation. Most implementations of vector FEM have been non-adaptive, where a mesh of the domain is generated entirely in advance and used with a constant degree polynomial basis to assign the degrees of freedom. To reduce the dependency on the users' expertise in analyzing problems with complicated boundary structures and material characteristics, and to speed up the FEM tool, the demand for adaptive FEM grows high. For efficient adaptive FEM, error estimators play an important role in assigning additional degrees of freedom. In this proposal study, hierarchical vector basis functions and four error estimators for p-refinement are investigated for electromagnetic applications.

No description available.

Pagrindinis darbo tikslas – atlikti kelių tiesioginio sklidimo neuroninių tinklų sistemų lyginamąją analizę siekiant įvertinti jų funkcionalumą. Šiame darbe apžvelgiama: biologinio ir dirbtinio neuronų modeliai, neuroninių tinklų klasifikacija pagal jungimo konstrukciją (tiesioginio sklidimo ir rekurentiniai neuroniniai tinklai), dirbtinių neuroninių tinklų mokymo strategijos (mokymas su mokytoju, mokymas be mokytojo, hibridinis mokymas). Analizuojami pagrindiniai tiesioginio sklidimo neuroninių tinklų metodai: vienasluoksnis perceptronas, daugiasluoksnis perceptronas realizuotas „klaidos skleidimo atgal” algoritmu, radialinių bazinių funkcijų neuroninis tinklas. Buvo nagrinėjama 14 skirtingų tiesioginio sklidimo neuroninių tinklų sistemos. Programos buvo suklasifikuotos pagal kainą, tiesioginio sklidimo neuroninių tinklo mokymo metodų taikymą, galimybę vartotojui keisti parametrus prieš apmokant tinklą ir techninį programos įvertinimą. Programos buvo įvertintos dešimtbalėje vertinimo sistemoje pagal mokymo metodų įvairumą, parametrų keitimo galimybes, programos stabilumą, kokybę, bei kainos ir kokybės santykį. Aukščiausiu balu įvertinta „Matlab” programa (10 balų), o prasčiausiai – „Sharky NN” (2 balai). Detalesnei analizei pasirinktos keturios programos („Matlab“, „DTREG“, „PathFinder“, „Cortex“), kurios buvo įvertintos aukščiausiais balais, galėjo apmokyti tiesioginio sklidimo neuroninį tinklą daugiasluoksnio perceptrono metodu ir bent dvi radialinių bazinių funkcijų... [toliau žr. visą tekstą] / The main aim – to perform a comparative analysis of several feedforward neural system networks in order to identify its functionality. The work presents both: biological and artificial neural models, also classification of neural networks, according to connections’ construction (of feedforward and recurrent neural networks), studying strategies of artificial neural networks (with a trainer, without a trainer, hybrid). The main methods of feedforward neural networks: one-layer perceptron, multilayer perceptron, implemented upon “error feedback” algorithm, also a neural network of radial base functions have been considered. The work has included 14 different feedforward neural system networks, classified according its price, application of study methods of feedforward neural networks, also a customer’s possibility to change parameters before paying for the network and a technical evaluation of a program. The programs have been evaluated from 1 point to 10 points according to the following: variety of training systems, possibility to change parameters, stability, quality and ratio of price and quality. The highest evaluation has been awarded to “Matlab” (10 points), the lowest – to “Sharky NN” (2 points). Four programs (”Matlab“, “DTREG“, “PathFinder“,”Cortex“) have been selected for a detail analysis. The best evaluated programs have been able to train feedforward neural networks using multilayer perceptron method, also at least two radial base function networks. “Matlab“ and... [to full text]

Šio darbo tyrimų sritis yra duomenų tyryba remiantis daugiamačių duomenų vizualia analize. Tai leidžia tyrėjui betarpiškai dalyvauti duomenų analizės procese, geriau pažinti sudėtingus duomenis ir priimti geriausius sprendimus. Disertacijos tikslas yra sukurti metodą tokios duomenų projekcijos radimui plokštumoje, kad tyrėjas galėtų pamatyti ir įvertinti daugiamačių taškų tarpgrupinius panašumus/skirtingumus. Šiam tikslui pasiekti yra pasiūlytas radialinių bazinių funkcijų ir daugiasluoksnio perceptrono, turinčio ,,butelio kaklelio“ neuroninio tinklo savybes, junginys. Naujas tinklas naudojamas vizualiai daugiamačių duomenų analizei, kai atidėjimui plokštumoje arba trimatėje erdvėje taškai gaunami paskutinio paslėpto neuronų sluoksnio išėjimuose, kai į tinklo įėjimą paduodami daugiamačiai duomenys. Šio tinklo ypatybė yra ta, kad gautas vaizdas plokštumoje labiau atspindi bendrą duomenų struktūrą (klasteriai, klasterių tarpusavio artumas, taškų tarpklasterinis panašumas) nei daugiamačių taškų tarpusavio išsidėstymą. / The area of research is data mining based on multidimensional data visual analysis. This allows researcher to participate in the process of data analysis directly, to understand the complex data better and to make the best decisions. The objective of the dissertation is to create a method for making a multidimensional data projection on the plane such that the researcher could see and assess the intergroup similarities and differences of multidimensional points. In order to achieve the target, a new hybrid neural network is proposed and investigated. This neural network integrates the ideas both of the radial basis function neural network and that of a multilayer perceptron, which has the properties of a ''bottleneck'' neural network. The new network is used for the visual analysis of multidimensional data in such a way that the output values of the neurons of the last hidden layer are the two-dimensional or three-dimensional projections of the multidimensional data, when the multidimensional data is given to the network. A peculiarity of the network is that the visualization results on the plane reflect the general structure of the data (clusters, proximity between clusters, intergroup similarities of points) rather than the location of multidimensional points.

The area of research is data mining based on multidimensional data visual analysis. This allows researcher to participate in the process of data analysis directly, to understand the complex data better and to make the best decisions. The objective of the dissertation is to create a method for making a multidimensional data projection on the plane such that the researcher could see and assess the intergroup similarities and differences of multidimensional points. In order to achieve the target, a new hybrid neural network is proposed and investigated. This neural network integrates the ideas both of the radial basis function neural network and that of a multilayer perceptron, which has the properties of a ''bottleneck'' neural network. The new network is used for the visual analysis of multidimensional data in such a way that the output values of the neurons of the last hidden layer are the two-dimensional or three-dimensional projections of the multidimensional data, when the multidimensional data is given to the network. A peculiarity of the network is that the visualization results on the plane reflect the general structure of the data (clusters, proximity between clusters, intergroup similarities of points) rather than the location of multidimensional points. / Šio darbo tyrimų sritis yra duomenų tyryba remiantis daugiamačių duomenų vizualia analize. Tai leidžia tyrėjui betarpiškai dalyvauti duomenų analizės procese, geriau pažinti sudėtingus duomenis ir priimti geriausius sprendimus. Disertacijos tikslas yra sukurti metodą tokios duomenų projekcijos radimui plokštumoje, kad tyrėjas galėtų pamatyti ir įvertinti daugiamačių taškų tarpgrupinius panašumus/skirtingumus. Šiam tikslui pasiekti yra pasiūlytas radialinių bazinių funkcijų ir daugiasluoksnio perceptrono, turinčio ,,butelio kaklelio“ neuroninio tinklo savybes, junginys. Naujas tinklas naudojamas vizualiai daugiamačių duomenų analizei, kai atidėjimui plokštumoje arba trimatėje erdvėje taškai gaunami paskutinio paslėpto neuronų sluoksnio išėjimuose, kai į tinklo įėjimą paduodami daugiamačiai duomenys. Šio tinklo ypatybė yra ta, kad gautas vaizdas plokštumoje labiau atspindi bendrą duomenų struktūrą (klasteriai, klasterių tarpusavio artumas, taškų tarpklasterinis panašumas) nei daugiamačių taškų tarpusavio išsidėstymą.