This thesis focuses on detecting, classifying and locating faults on electric power transmission lines. Fault detection, fault classification and fault location have been achieved by using artificial neural networks. Feedforward networks have been employed along with backpropagation algorithm for each of the three phases in the Fault location process. Analysis on neural networks with varying number of hidden layers and neurons per hidden layer has been provided to validate the choice of the neural networks in each step. Simulation results have been provided to demonstrate that artificial neural network based methods are efficient in locating faults on transmission lines and achieve satisfactory performances.

In this contributon we evaluate on-line and off-line techniques to train a single hidden layer neural network classifier with logistic hidden and softmax output transfer functions on a multispectral pixel-by-pixel classification problem. In contrast to current practice a multiple class cross-entropy error function has been chosen as the function to be minimized. The non-linear diffierential equations cannot be solved in closed form. To solve for a set of locally minimizing parameters we use the gradient descent technique for parameter updating based upon the backpropagation technique for evaluating the partial derivatives of the error function with respect to the parameter weights. Empirical evidence shows that on-line and epoch-based gradient descent backpropagation fail to converge within 100,000 iterations, due to the fixed step size. Batch gradient descent backpropagation training is superior in terms of learning speed and convergence behaviour. Stochastic epoch-based training tends to be slightly more effective than on-line and batch training in terms of generalization performance, especially when the number of training examples is larger. Moreover, it is less prone to fall into local minima than on-line and batch modes of operation. (authors' abstract) / Series: Discussion Papers of the Institute for Economic Geography and GIScience

Feedforward is known to be one of the best methods for power amplifier linearization due to its superior linearization performance and broadband stable operation. However feedforward systems have relatively poor power efficiency and are complicated due to the presence of two nonlinear amplifiers and the requirements of amplitude, phase and delay matching within two different loops. In this thesis stochastic characterization of a simple feedforward system with autocorrelation analysis has been presented for Code Division Multiple Access (CDMA) applications taking the amplitude and delay mismatches into consideration. It has been assumed that, the input signal can be represented as Gaussian noise, main and error amplifiers can be modeled with third order AM/AM nonlinearities and there exists no phase mismatch within the loops. Hence closed form expressions, which relate the main channel and distorted adjacent channel power at any point in the feedforward circuitry to the system parameters, have been obtained. Consequently, a mathematical handy tool is achieved towards specifying the circuit parameters rapidly for optimum linearity performance and efficiency. The developed analytical model has been verified by Radio Frequency (RF) and system simulations. An alternative approach towards modeling feedforward systems for arbitrary signals has also been brought into consideration and has been verified with system simulations.

Characterization of nonlinear systems is a challenging task as the output can not be expressed simply in terms of input signal. Therefore, a universal analysis method is essential to simplify this procedure. Modeling of the input signal is a crucial part of such analysis. In this thesis, multi-tone representation is employed to model arbitrary, stochastically not well-defined input signals and thereafter characterize nonlinear systems. In order to verify the validity of multitone representation, multi-tone modeling concept is primarily applied to real life amplifier characterization in single amplifier configuration. This experiment demonstrated potential of multi-tone modeling concept in nonlinear system characterization and encouraged application of the concept to analysis of feedforward linearizers, which are complicated systems due to the presence of two nonlinear amplifiers and the requirement of strict amplitude, phase and delay matching within two loops of the circuit. It has been assumed that main and error amplifiers can be modeled with third order AM/AM nonlinearities and there exists no delay mismatch within the loops. Hence, closed form expressions relating the main and adjacent channel power at the output of the feedforward system to the system parameters are obtained. The developed model is verified by RF and system simulations. As a result, a mathematical handy tool to specify circuit parameters rapidly for optimum linearity performance and efficiency is achieved.

Bibliography: leaves 176-188 / xvii, 188 leaves : ill ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / Thesis (Ph.D.)--University of Adelaide, Dept. of Electrical and Electronic Engineering, 1992?

Thesis (Ph. D.)--University of Adelaide, Dept. of Electrical and Electronic Engineering, 1992? / Includes bibliographical references (leaves 176-188).

Thesis (Ph. D.)--University of California, San Diego, 1997. / Vita. Includes bibliographical references.

<p>Syftet med arbetet är att simulera tävlingar på medeldistans mellan löpare med en strategi att vinna och undvika muskeltrötthet. Löparna ses som agenter vars strategi realiseras med ett artificiellt neuronnät (ANN) som med sensorer, avstånd till mål och agentens trötthet beräknar bidragande kraft och styrriktning. Agentens ANN tränas med en belöningsbaserad inlärning baserad på genetiska algoritmer och trötthetsalgoritmen är en uppskattning av hur mjölksyra påverkar muskeltrötthet.</p><p>Resultaten visar att av alla agenter som utvecklats för tävling mot klockan i s.k. time trial har alla haft samma strategi och hittat samma ideala kraft för att minimera tiden. Utvecklingen av agenter för simulation av flera agenter samtidigt har varit mer komplicerad eftersom agenterna påverkar varandra och agenternas strategi har varit olika. Multiagenterna blev också mindre robusta än singelagenterna men utvecklade beteenden som påminner om en realistisk tävling i medeldistanslöpning.</p>

Thesis (doctoral)--Helsinki University of Technology, 2007. / Includes bibliographical references (p. 142-151). Also available on the World Wide Web.

In this thesis, I describe a quantitative model that accounts for the circuits and computations of the feedforward path of the ventral stream of visual cortex. This model is consistent with a general theory of visual processing that extends the hierarchical model of (Hubel & Wiesel, 1959) from primary to extrastriate visual areas. It attempts to explain the first few hundred milliseconds of visual processing and “immediate recognition”. One of the key elements in the approach is the learning of a generic dictionary of shape-components from V2 to IT, which provides an invariant representation to task-specific categorization circuits in higher brain areas. This vocabulary of shape-tuned units is learned in an unsupervised manner from natural images, and constitutes a large and redundant set of image features with different complexities and invariances. This theory significantly extends an earlier approach by (Riesenhuber & Poggio, 1999) and builds upon several existing neurobiological models and conceptual proposals.First, I present evidence to show that the model can duplicate the tuning properties of neurons in various brain areas (e.g., V1, V4 and IT). In particular, the model agrees with data from V4 about the response of neurons to combinations of simple two-bar stimuli (Reynolds et al, 1999) (within the receptive field of the S2 units) and some of the C2 units in the model show a tuning for boundary conformations which is consistent with recordings from V4 (Pasupathy & Connor, 2001). Second, I show that not only can the model duplicate the tuning properties of neurons in various brain areas when probed with artificial stimuli, but it can also handle the recognition of objects in the real-world, to the extent of competing with the best computer vision systems. Third, I describe a comparison between the performance of the model and the performance of human observers in a rapid animal vs. non-animal recognition task for which recognition is fast and cortical back-projections are likely to be inactive. Results indicate that the model predicts human performance extremely well when the delay between the stimulus and the mask is about 50 ms. This suggests that cortical back-projections may not play a significant role when the time interval is in this range, and the model may therefore provide a satisfactory description of the feedforward path.Taken together, the evidences suggest that we may have the skeleton of a successful theory of visual cortex. In addition, this may be the first time that a neurobiological model, faithful to the physiology and the anatomy of visual cortex, not only competes with some of the best computer vision systems thus providing a realistic alternative to engineered artificial vision systems, but also achieves performance close to that of humans in a categorization task involving complex natural images. / PhD thesis