The application of neural networks in the area of signal processing is examined. Two major areas are identified and suitable neural networks are developed. In the first area, neural networks are used as a tool for the design of digital filters. In the second area, neural networks are used for processing bathymetric data. The field of artificial neural networks is first introduced with an emphasis on Hopfield networks. The optimizing capabilities of such networks are noted. Based on these networks, a feedback neural network is developed for the design of 1-D finite-duration impulse response (FIR) filters on the basis of given amplitude responses. A suitable cost function is formulated first and an associated network is developed. This work is then extended to the design of two more networks for the design of FIR filters based on given amplitude and phase responses and prescribed specifications. The idea is extended to the design of 2-D FIR filters. Two networks are presented for designing 2-D FIR filters on the basis of a given amplitude response and prescribed specifications. The design of 1-D infinite-duration impulse response (IIR) filters is studied next and two networks are developed. The first one is to design filters with prescribed specifications in the magnitude-squared domain. The other network designs IIR filters for a given frequency response. A network for designing equiripple 1-D FIR filters based on the weighted least-squares technique is presented next. A new updating algorithm is developed for this network. Two different neural networks are proposed for classifying lidar waveforms into various categories. A single-layer network is developed for classifying lidar waveforms representing milt of varied densities. A fast version of the supervised learning algorithm is presented. A threshold term is also introduced in the recall phase to give the user flexibility to accept or reject any waveform. A two-stage, multi-layer network is presented next which uses waveform characteristics to assign a signature number to the waveform. This network extracts various ocean parameters from the waveforms as well. The issue of implementing the feedback neural network is addressed next. Basic building blocks for implementing such networks are identified and a network is constructed from circuits existing in the literature. The network is simulated in Cadence using 0.8 μ BICMOS technology. The results show that these networks have a high potential to be implemented in analog VLSI for real-time signal processing. / Graduate

Resumo: O presente trabalho oferece contribuições à modelagem da rugosidade da peça em processos de usinagem por meio de redes neurais artificiais. Propõe-se um método para o projeto de redes. Perceptron Multi-Camada (Multi-Layer Percepton, ou MLO) e Função de Base radial Radial Basis Function, ou RBF) otimizadas para a predição da rugosidade da pela (Ra). Desenvolve-se um algoritmo que utiliza de forma hibrida a metodologia do projeto de experimentos por meio das técnicas dos fatoriais completose de Variações Evolucionária em Operações (EVOP). A estratégia adotada é a de utilizar o projeto de experimentos na busca de configurações de rede que favoreçam estatisticamente o desempenho na tarefa de predição. Parâmetro de corte dos processos de usinagem são utilizados como entradas das redes. O erro médio absoluto em porcentagem (MAE %) do decil inferioir das observações de predição para o conjunto de testes é utilizado como medida de desempnho dos modelos. Com o objetivo de validar o métido proposto são empregados casos de treinamento gerados a partir de daods obtidos de trabalhos de literatura e de experimentos de torneamento do aço ABNT 121.13. O método proposto leva á redução significativa do erro de predição da rugosidade nas operações de usinagem estudadas, quando se compara seu desempenho ao apresentado por modelos de regressão, aos resultados relatados pela literatura e ao desempenho de modelos neurais propostos por um pacotecomputacional comercial para otimização de configurações de rede. As redes projetadas segundo o método proposto possuem dispersão dos erros de predição significativamente reduzidos na comparação. Observa-se ainda que rede MLP atingem resultados estatisticamente superior aos obtidos pelas melhores redes RBF / Abstract: The present work offers some contributions to the area of surface roughness modeling by Artificial Neural Network in machining processes. Ir proposes a method for the project networks of MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) architectures optimized for prediction of Average Surface Roughness (Ru). The methid is expressed in the format of an algorithm employing two techniques from the DOE (Design of Experiments) methodology: Full factorials and Evolutionary Operations(EVOP). The strategy adopted consists in the sistematic use of DOE in a search for network configurations that benefits performance in roughess prediction. Cutting para meters from machining operations are employed as network inputs. Themean absolute error in percentage (MAE%) of the lower decile of the predictions for the test set is used as a figure of merit for network performance. In order to validate the method, data sets retrieved from literature, as well as results of experiments with AISI/SAE free-machining steel, are employed to form training and test data sets for the networks. The proposed algorithm leads to significant reduction in prediction error for surface roughness when compared to the performance delivred by a regression model, by the networks proposed by the original studies data was borrowed from and when compared models proposed by a software package intend to search automatically for optimal network configurations. In addition, networks designed acording to the proposed algorithm displayed reduced dispersion of prediction error for surface roughness when compared to the performance delivered by a regression model, by the networks proposed by the original studies data was borrowed from and when compared to neural models proposed by a software package intended to searchautomatically for optimal network configurations. In addition, networks designed according to the proposed algorith ... (Complete abstract click electronic access below) / Orientador: Messias Borges Silva / Coorientador: Anderson Paulo de Paiva / Banca: Marcos Valério Ribeiro / Banca: Marcela A. G. Machado de Freitas / Banca: Domingos Sávio Giordani / Banca: João Roberto Ferreira / Doutor

M.Ing. (Electrical And Electronic Engineering) / Please refer to full text to view abstract

M.Ing. / A great deal of work has been done in the field of hexapodous autonomous agents. However, in this dissertation the locomotion of a more complex organism - the octopod - will be studied. Biological neural behaviour will present a basis for the leg controllers, while classic backpropagation networks will be used to implement pattern generators. Full simulation of the biological scorpion leg will be implemented, thus a simulated leg consisting of six joint angles with 6 degrees of freedom. Simple locomotion on a flat substrate will be considered. In this dissertation the scorpion will be used as basis of simulation mainly due to the interesting leg architecture and intricate locomotory patterns during locomotion, hunting and burrowing. The locomotory models developed here may be modified to facilitate other terrestial octopodous agents.

M. Ing. / This dissertation describes the development of a feedforwa.rd neural network, trained by means of an accelerated backpropagation algorithm, used for the short term load forecasting on real world data. It is argued that the new learning algorithm. I-Prop, - is a faster training - algorithm due to the fact that the learning rate is optimally predicted and changed according to a more efficient formula (without the need for extensive memory) which speeds up the training process. The neural network developed was tested for the month of December 1994, specifically to test the artificial neural network's ability to correctly predict the load during a Public Holiday, as well as the change over from Public Holiday to 'Normal' working day. In conclusion, suggestions are made towards further research in the improvement of the I-Prop algorithm as well as improving the load forecasting technique implemented in this dissertation.

Spread F is a phenomenon of the ionosphere in which the pulses returned from the ionosphere are of a much greater duration than the transmitted ones. The occurrence of spread F can be predicted using the technique of Neural Networks (NNs). This thesis presents the development and evaluation of NN based models (two single station models and a regional model) for predicting the occurrence of spread F over selected stations within the Brazilian sector. The input space for the NNs included the day number (seasonal variation), hour (diurnal variation), sunspot number (measure of the solar activity), magnetic index (measure of the magnetic activity) and magnetic position (latitude, magnetic declination and inclination). Twelve years of spread F data measured during 1978 to 1989 inclusively at the equatorial site Fortaleza and low latitude site Cachoeira Paulista are used in the development of an input space and NN architecture for the NN models. Spread F data that is believed to be related to plasma bubble developments (range spread F) were used in the development of the models while those associated with narrow spectrum irregularities that occur near the F layer (frequency spread F) were excluded. The results of the models show the dependency of the probability of spread F as a function of local time, season and latitude. The models also illustrate some characteristics of spread F such as the onset and peak occurrence of spread F as a function of distance from the equator. Results from these models are presented in this thesis and compared to measured data and to modelled data obtained with an empirical model developed for the same purpose.

This thesis describes the search for a temporal model for predicting the peak ionospheric electron density-(foF2). Existing models, such as the International Reference Ionosphere (IRI) and 8KYCOM, were used to predict the 12 noon foF2 value over Grahamstown (26°E, 33°8). An attempt was then made to find a model that would improve upon these results. The traditional method of linear regression was used as a first step towards a new model. It was found that this would involve a multi variable regression that is reliant on guessing the optimum variables to be used in the final equation. An extremely complicated modelling equation involving many terms would result. Neural networks (NNs) are introduced as a new technique for predicting foF2. They are also applied, for the first time, to the problem of determining the best predictors of foF2. This quantity depends upon day number, level of solar activity and level of magnetic activity. The optimum averaging lengths of the solar activity index and the magnetic activity index were determined by appling NNs, using the criterion that the best indices are those that give the lowest rms error between the measured and predicted foF2. The optimum index for solar activity was found to be a 2-month running mean value of the daily sunspot number and for magnetic activity a 2-day averaged A index was found to be optimum. In addition, it was found that the response of foF2 to magnetic activity changes is highly non-linear and seasonally dependent. Using these indices as inputs, the NN trained successfully to predict foF2 with an rms error of 0.946 MHz on the daily testing values. Comparison with the IRI showed an improvement of 40% on the rms error. It is also shown that the NN will predict the noon value of foF2 to the same level of accuracy for unseen data of the same type.

M.Ing. (Mechanical Engineering) / Please refer to full text to view abstract

M.Ing. (Mechanical Engineering) / This thesis involves the development of a Neural Network software package within a Windows environment. This package is called NetPro. It contains most of the standard tools used in existing neural network packages e.g. shuffling of facts, automatic test file facts extraction, randomizing of weights values (before and during training), automatic/manual construction of network files, logging of network properties during training, noise can be added to inputs, etc. NetPro has three additional tools: (a) time delay actions on inputs, (b) a neural network calculator, and (c) automatic saving of the best network during training. The calculator is used to calculate the number of training facts needed for optimum generalization ...

In the domain of strategic game playing, the use of statistical techniques such as the Upper Confidence for Trees (UCT) algorithm, has become the norm as they offer many benefits over classical algorithms. These benefits include requiring no game-specific strategic knowledge and time-scalable performance. UCT does not incorporate any strategic information specific to the game considered, but instead uses repeated sampling to effectively brute-force search through the game tree or search space. The lack of game-specific knowledge in UCT is thus both a benefit but also a strategic disadvantage. Pattern recognition techniques, specifically Neural Networks (NN), were identified as a means of addressing the lack of game-specific knowledge in UCT. Through a novel hybridisation technique which combines UCT and trained NNs for pruning, the UCTNN algorithm was derived. The NN component of UCT-NN was trained using a UCT self-play scheme to generate game-specific knowledge without the need to construct and manage game databases for training purposes. The UCT-NN algorithm is outlined for pruning in the game of Go-Moku as a candidate case-study for this research. The UCT-NN algorithm contained three major parameters which emerged from the UCT algorithm, the use of NNs and the pruning schemes considered. Suitable methods for finding candidate values for these three parameters were outlined and applied to the game of Go-Moku on a 5 by 5 board. An empirical investigation of the playing performance of UCT-NN was conducted in comparison to UCT through three benchmarks. The benchmarks comprise a common randomly moving opponent, a common UCTmax player which is given a large amount of playing time, and a pair-wise tournament between UCT-NN and UCT. The results of the performance evaluation for 5 by 5 Go-Moku were promising, which prompted an evaluation of a larger 9 by 9 Go-Moku board. The results of both evaluations indicate that the time allocated to the UCT-NN algorithm directly affects its performance when compared to UCT. The UCT-NN algorithm generally performs better than UCT in games with very limited time-constraints in all benchmarks considered except when playing against a randomly moving player in 9 by 9 Go-Moku. In real-time and near-real-time Go-Moku games, UCT-NN provides statistically significant improvements compared to UCT. The findings of this research contribute to the realisation of applying game-specific knowledge to the UCT algorithm.