Footings are often founded on multi-layered soil profiles. Real soil profiles are often multi-layered with material constantly varying with depth, which affects the footing response significantly. Furthermore, the properties of the soil are known to vary with location. The spatial variability of soil can be described by random field theory and geostatistics. The research presented in this thesis focuses on quantifying the effect of soil variability on the bearing capacity of rough strip footings on single and two layered, purely-cohesive, spatially variable soil profiles. This has been achieved by using Monte Carlo analysis, where the rough strip footings are founded on simulated soil profiles are analysed using finite element limit analysis. The simulations of virtual soil profiles are carried out using Local Average Subdivision (LAS), a numerical model based on the random field theory. An extensive parametric study has been carried out and the results of the analyses are presented as normalized means and coefficients of variation of bearing capacity factor, and comparisons between different cases are presented. The results indicate that, in general, the mean of the bearing capacity reduces as soil variability increases and the worst case scenario occurs when the correlation length is in the range of 0.5 to 1.0 times the footing width. The problem of estimating the bearing capacity of shallow strip footings founded on multi-layered soil profiles is very complex, due to the incomplete knowledge of interactions and relationships between parameters. Much research has been carried out on single- and two-layered homogeneous soil profiles. At present, the inaccurate weighted average method is the only technique available for estimating the bearing capacity of footing on soils with three or more layers. In this research, artificial neural networks (ANNs) are used to develop meta-models for bearing capacity estimation. ANNs are numerical modelling techniques that imitate the human brain capability to learn from experience. This research is limited to shallow strip footing founded on soil mass consisting of ten layers, which are weightless, purely cohesive and cohesive-frictional. A large number of data has been obtained by using finite element limit analysis. These data are used to train and verify the ANN models. The shear strength (cohesion and friction angle), soil thickness, and footing width are used as model inputs, as they are influencing factors of bearing capacity of footings. The model outputs are the bearing capacities of the footings. The developed ANN-based models are then compared with the weighted average method. Hand-calculation design formulae for estimation of bearing capacity of footings on ten-layered soil profiles, based on the ANN models, are presented. It is shown that the ANN-based models have the ability to predict the bearing capacity of footings on ten-layered soil profiles with a high degree of accuracy, and outperform traditional methods. / http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1368281 / Thesis (Ph.D.) - University of Adelaide, School of Civil, Environmental and Mining Engineering, 2009

Internal Symmetry Networks are a recently developed class of Cellular Neural Network inspired by the phenomenon of internal symmetry in quantum physics. Their hidden unit activations are acted on non-trivially by the dihedral group of symmetries of the square. Here, we extend Internal Symmetry Networks to include recurrent connections, and train them by backpropagation to perform a variety of image processing tasks, smoothing, sharpening, edge detection, synthetic image segmentation, texture segmentation and object recognition. By a large number of experiments, we find some guidelines to construct appropriate configurations of the net for different tasks.

Footings are often founded on multi-layered soil profiles. Real soil profiles are often multi-layered with material constantly varying with depth, which affects the footing response significantly. Furthermore, the properties of the soil are known to vary with location. The spatial variability of soil can be described by random field theory and geostatistics. The research presented in this thesis focuses on quantifying the effect of soil variability on the bearing capacity of rough strip footings on single and two layered, purely-cohesive, spatially variable soil profiles. This has been achieved by using Monte Carlo analysis, where the rough strip footings are founded on simulated soil profiles are analysed using finite element limit analysis. The simulations of virtual soil profiles are carried out using Local Average Subdivision (LAS), a numerical model based on the random field theory. An extensive parametric study has been carried out and the results of the analyses are presented as normalized means and coefficients of variation of bearing capacity factor, and comparisons between different cases are presented. The results indicate that, in general, the mean of the bearing capacity reduces as soil variability increases and the worst case scenario occurs when the correlation length is in the range of 0.5 to 1.0 times the footing width. The problem of estimating the bearing capacity of shallow strip footings founded on multi-layered soil profiles is very complex, due to the incomplete knowledge of interactions and relationships between parameters. Much research has been carried out on single- and two-layered homogeneous soil profiles. At present, the inaccurate weighted average method is the only technique available for estimating the bearing capacity of footing on soils with three or more layers. In this research, artificial neural networks (ANNs) are used to develop meta-models for bearing capacity estimation. ANNs are numerical modelling techniques that imitate the human brain capability to learn from experience. This research is limited to shallow strip footing founded on soil mass consisting of ten layers, which are weightless, purely cohesive and cohesive-frictional. A large number of data has been obtained by using finite element limit analysis. These data are used to train and verify the ANN models. The shear strength (cohesion and friction angle), soil thickness, and footing width are used as model inputs, as they are influencing factors of bearing capacity of footings. The model outputs are the bearing capacities of the footings. The developed ANN-based models are then compared with the weighted average method. Hand-calculation design formulae for estimation of bearing capacity of footings on ten-layered soil profiles, based on the ANN models, are presented. It is shown that the ANN-based models have the ability to predict the bearing capacity of footings on ten-layered soil profiles with a high degree of accuracy, and outperform traditional methods. / http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1368281 / Thesis (Ph.D.) - University of Adelaide, School of Civil, Environmental and Mining Engineering, 2009

Internal Symmetry Networks are a recently developed class of Cellular Neural Network inspired by the phenomenon of internal symmetry in quantum physics. Their hidden unit activations are acted on non-trivially by the dihedral group of symmetries of the square. Here, we extend Internal Symmetry Networks to include recurrent connections, and train them by backpropagation to perform a variety of image processing tasks, smoothing, sharpening, edge detection, synthetic image segmentation, texture segmentation and object recognition. By a large number of experiments, we find some guidelines to construct appropriate configurations of the net for different tasks.

“Winner-take-all” networks typically pick as winners that alternative with the largest excitatory input. This choice is far from optimal when there is uncertainty in the strength of the inputs, and when information is available about how alternatives may be related. In the Social Choice community, many other procedures will yield more robust winners. The Borda Count and the pair-wise Condorcet tally are among the most favored. Their implementations are simple modifications of classical recurrent networks.

Broken fences is a big security risk for any facility or area with strict security standards. In this report we suggest a machine learning approach to automate the surveillance for chain-linked fences. The main challenge is to classify broken and non-broken fences with the help of a convolution neural network. Gathering data for this task is done by hand and the dataset is about 127 videos at 26 minutes length total on 23 different locations. The model and dataset are tested on three performances traits, scaling, augmentation improvement and false rate. In these tests we concluded that nearest neighbor increased accuracy. Classifying with fences that has been included in the training data a false rate that was low, about 1%. Classifying with fences that are unknown to the model produced a false rate of about 90%. With these results we concludes that this method and dataset is useful under the right circumstances but not in an unknown environment.

Object recognition systems have significant influences on modern life. Face, iris and finger point recognition applications are commonly applied for the security purposes; ASR (Automatic Speech Recognition) is commonly implemented on speech subtitle generation for various videos and audios, such as YouTube; HWR (Handwriting Recognition) systems are essential on the post office for cheque and postcode detection; ADAS (Advanced Driver Assistance System) are well applied to improve drivers’, passages’ and pedestrians’ safety. Object recognition techniques are crucial and valuable for academia, commerce and industry. Accuracy and efficiency are two important standards to evaluate the performance of recognition techniques. Accuracy includes how many objects can be indicated in real scene and how many of them can be correctly classified. Efficiency means speed for system training and sample testing. Traditional object detecting methods, such as HOG (Histogram of orientated Gradient) feature detector combining with SVM (Support Vector Machine) classifier, cannot compete with frameworks of neural networks in both efficiency and accuracy. Since neural network has better performance and potential for improvement, it is worth to gain insight into this field to design more advanced recognition systems. In this thesis, we list and analyze sophisticated techniques and frameworks for object recognition. To understand the mathematical theory for network design, state-of-the-art networks in ILSVRC (ImageNET Large Scale Visual Recognition Challenge) are studied. Based on analysis and the concept of edge detectors, a simple CNN (Convolutional Neural Network) structure is designed as a trail to explore the possibility to utilize the network of high width and low depth for region proposal selection, object recognition and target region refining. We adopt Le-Net as the template, taking advantage of multi-kernels of GoogLe-Net. We made experiments to test the performance of this simple structure of the vehicle and face through ImageNet dataset. The accuracy for the single object detection is 81% in average and for plural object detection is 73.5%. We refined networks through many aspects to reach the final accuracy 95% for single object detection and 89% for plural object detection.

In this thesis, the neural network, a powerful tool which has demonstrated its ability in many fields, is studied for the indoor localization system and channel prediction system. This thesis first proposes a received signal strength indicator (RSSI) fingerprinting-based indoor positioning system for the widely deployed WiFi environment, using deep neural networks (DNN). To reduce the computing time as well as improve the estimation accuracy, a two-step scheme is designed, employing a classification network for clustering and several regression networks for final location prediction. A new fingerprinting, which utilizes the similarity in RSSI readings of the nearby reference points (RPs) is also proposed. Real-time tests demonstrate that the proposed algorithm achieves an average distance error of 43.5 inches. Then this thesis extends the ability of the neural network to the physical layer communications by introducing a recurrent neural network (RNN) based approach for real-time channel prediction which uses the recent history channel state information (CSI) estimation for online training before prediction, to adapt to the continuously changing channel to gain a more accurate CSI prediction compared to the other conventional methods. Furthermore, the proposed method needs no additional knowledge, neither the internal properties of the channel itself nor the external features that affect the channel propagation. The proposed approach outperforms the other methods in a changing environment in the simulation test, validating it a promising method for channel prediction in wireless communications. / Graduate

AN ABSTRACT OF THE THESIS OF SOROOSH SOHANGIR, for the MASTER OF SCIENCE degree in COMPUTER SCIENCE, presented on 9 th November 2011, at Southern Illinois University Carbondale. TITLE: OPTIMIZED FEATURE SELECTION USING NEUROEVOLUTION OF AUGMENTING TOPOLOGIES (NEAT) MAJOR PROFESSOR: Dr. Shahram Rahimi Feature selection using the NeuroEvolution of Augmenting Topologies (NEAT) is a new approach. In this thesis an investigation had been carried out for implementation based on optimization of the network topology and protecting innovation through the speciation which is similar to what happens in nature. The NEAT is implemented through the JNEAT package and Utans method for feature selection is deployed. The performance of this novel method is compared with feature selection using Multilayer Perceptron (MLP) where Belue, Tekto, and Utans feature selection methods is adopted. According to unveiled data from this thesis the number of species, the training, accuracy and number of hidden neurons are notably improved as compared with conventional networks. For instance the time is reduced by factor of three.

Made available in DSpace on 2014-06-11T19:31:37Z (GMT). No. of bitstreams: 0 Previous issue date: 2003Bitstream added on 2014-06-13T20:22:35Z : No. of bitstreams: 1 nagaoka_me_dr_botfca.pdf: 501587 bytes, checksum: a5d05cfa41f21298548d31b5d95dc6b1 (MD5) / Este trabalho apresenta a aplicação de um sistema inteligente utilizando redes neurais artificiais para estimar valores de densidade do solo, a partir de parâmetros referentes à resistência do solo à penetração. Foram considerados solos preparados e não preparados, os não preparados foram os seguintes : teor de argila menor que 30 % (solo tipo 1), de 30 a 50 % (solo tipo 2) e maior que 50 % (solo tipo 3). Os preparados foram os seguintes: um com teor de argila menor que 30 % (solo tipo 1) e o outro com teor de argila maior que 50 % (solo tipo 3). O objetivo principal deste trabalho foi implementar diversas redes neurais do tipo perceptron multicamadas, alimentando-as com resistência do solo à penetração, teor de água e teor de argila, tendo como variável de saída a densidade do solo. Cada rede foi treinada variando o número de camadas escondidas e também variando o número de neurônios, de 10 a 40, em cada camada. Para cada arquitetura, a rede foi treinada 10 vezes, escolhendo-se no final do treinamento a arquitetura com menor erro relativo médio e menor variância em relação aos dados de validação. As análises realizadas mostraram que as arquiteturas de rede com apenas uma camada escondida forneceram melhores resultados. Todas as redes tiveram melhor desempenho em solo não preparado do que em solo preparado. A rede de arquitetura de 3 entradas, uma camada escondida com 30 neurônios e 1 saída forneceu excelente resultado para solo não preparado (com teor de argila entre 30 e 50 %). Constatou-se que a rede quando treinada com dados do solo preparado, juntamente com dados do solo não preparado, melhorou os resultados de estimação para o solo preparado, mas piorou para os solos não preparados. Constatou também que a rede quando treinada junto com dados que contém solo solto fornece resultados imprecisos. O mesmo ocorreu para dados com teor de água elevado. / This work presents the development of an intelligent system using artificial neural networks to estimate values of soil density. Prepared and non-prepared soils were considered in this work. The non-prepared soils were the following ones: clay content lesser than 30 % (soil type 1), 30 to 50 % (soil type 2) and larger than 50 % (soil type 3). The prepared soils were the following ones: soil with clay content lesser than 30 % (soil type 1) and soil with clay content larger than 50 % (soil type 3). The main objective of this work was to implement several neural networks of type multilayer perceptron, feeding them with data concerning to the soil compaction characteristics. The output computed by the neural network was the respective density of these soils. Each neural network was trained varying both number of hidden layers and number of neurons, which was changed from 10 to 40 neurons in each layer. In each architecture the network was trained 10 times and selected architecture was always that having either the least mean relative error or the least variance in relation to validation data. The carried out analyses showed that the neural architectures having only a hidden layer were those that provided the best results. All neural networks have presented more efficient results for non-prepared soils than prepared soils. The neural network constituted by three inputs and one output, having 30 neurons at hidden layer, has provided excellent results for non-prepared soils (clay content between 30 and 50 %). It was also verified that the neural network when trained with data referent to non-prepared and soils, which were put in the same data set, it became the results referent to prepared soils more efficient, but the results for non-prepared soils become worse. Another observed point was when the network had been trained with data constituted by soft soil... (Complete abstract, click electronic address below).