The demand for electricity is increasing daily due to technological advancement, and ?luxurious lifestyles. Increasing utilization of electricity means the depletion of fossil fuel ?reserves. Thus, governments around the world are seeking alternative and sustainable ?sources of energy such as the solar powered system. The main purpose of this research is ?to develop a knowledge base on residential electric generation from the grid and solar ?energy. This paper examined the economic feasibility of using grid-tied residential ?photovoltaic (GRPV) system in Saudi Arabia with the HOMER software. Models ?forecasting the price of oil barrels through artificial neural networks (ANN) were also ?employed in the analysis. The study shows that an oil-rich country like Saudi Arabia has ?potential to utilize the GRPV system as an alternative source of energy. / This paper examined the economic feasibility of using grid-tied residential photovoltaic ??(GRPV) system in Saudi Arabia with the HOMER software. Models forecasting the ?price of oil barrels through artificial neural networks (ANN) were also employed in the ?analysis. The study shows that an oil-rich country like Saudi Arabia has potential to ?utilize the GRPV system as an alternative source of energy. This study provides a ?discussion of the potential for applying solar-powered and an assessment of the ?performance of existing systems based on collecting output data.?

This study presents different aspects on the use of deterministic methods including Artificial Neural Networks (ANNs), and linear and nonlinear regression, as well as probabilistic methods including Bayesian inference and Monte Carlo methods to develop reliable solutions for challenging problems in geotechnics. This study addresses the theoretical and computational advantages and limitations of these methods in application to: 1) prediction of the stiffness and strength of stabilized organic soils, 2) determination of unknown foundations for bridges vulnerable to scour, and 3) uncertainty quantification for one-dimensional diffusion processes. ANNs were successfully implemented in this study to develop nonlinear models for the mechanical properties of stabilized organic soils. ANN models were able to learn from the training examples and then generalize the trend to make predictions for the stiffness and strength of stabilized organic soils. A stepwise parameter selection and a sensitivity analysis method were implemented to identify the most relevant factors for the prediction of the stiffness and strength. Also, the variations of the stiffness and strength with respect to each factor were investigated. A deterministic and a probabilistic approach were proposed to evaluate the characteristics of unknown foundations of bridges subjected to scour. The proposed methods were successfully implemented and validated by collecting data for bridges in the Bryan District. ANN models were developed and trained using the database of bridges to predict the foundation type and embedment depth. The probabilistic Bayesian approach generated probability distributions for the foundation and soil characteristics and was able to capture the uncertainty in the predictions. The parametric and numerical uncertainties in the one-dimensional diffusion process were evaluated under varying observation conditions. The inverse problem was solved using Bayesian inference formulated by both the analytical and numerical solutions of the ordinary differential equation of diffusion. The numerical uncertainty was evaluated by comparing the mean and standard deviation of the posterior realizations of the process corresponding to the analytical and numerical solutions of the forward problem. It was shown that higher correlation in the structure of the observations increased both parametric and numerical uncertainties, whereas increasing the number of data dramatically decreased the uncertainties in the diffusion process.

This thesis proposes a modification to an air to surface guided munition (ASGM) from bang-bang control scheme to continuous control scheme with a little cost. In this respect, time domain system identification analysis is applied to the control actuation system (CAS) of ASGM in order to obtain its mathematical model and controller is designed using pulse width modulation technique. With this modification, canards would be deflected as much as it is commanded to. Seeker signals are also post-processed to obtain the angle between the velocity vector and target line of sight vector. The seeker is modeled using an artificial neural network. Non-linear flight simulation model is built using MATLAB Simulink and obtained seeker and CAS models are integrated to the whole flight simulation model having 6 degrees of freedom. As a flight control unit, fuzzy logic controller is designed, which is a suitable choice if an inertial measurement sensor will not be mounted on the munition. Finally, simulation studies are carried out in order to compare the performance of the &ldquo / ASGM&rdquo / and &ldquo / improved ASGM&rdquo / and the superiority of the new design is demonstrated.

As the size of image databases increases in time, the need for content based image indexing and retrieval become important. Image classification is a key to content based image indexing. In this thesis supervised learning with feed forward back propagation artificial neural networks is used for image classification. Low level features derived from the images are used to classify the images to interpret the high level features that yield semantics. Features are derived using detail histogram correlations obtained by Wavelet Transform, directional edge information obtained by Fourier Transform and color histogram correlations. An image database consisting of 357 color images of various sizes is used for training and testing the structure. The database is indexed into seven classes that represent scenery contents which are not mutually exclusive. The ground truth data is formed in a supervised fashion to be used in training the neural network and testing the performance. The performance of the structure is tested using leave one out method and comparing the simulation outputs with the ground truth data. Success, mean square error and the class recall rates are used as the performance measures. The performances of the derived features are compared with the color and texture descriptors of MPEG-7 using the structure designed. The results show that the performance of the method is comparable and better. This method of classification for content based image indexing is a reliable and valid method for content based image indexing and retrieval, especially in scenery image indexing.

Autonomous land vehicles (ALVs) have received considerable attention after their introduction into military and commercial applications. ALVs still stand as a challenging research topic. One of the main problems arising in ALV operations is the navigation accuracy while the other is the dynamic effects of road irregularities which may prevent the vehicle and its cargo to function properly. In this thesis, we propose intelligent solutions to these two basic problems of ALV. First, an intelligent method is proposed to enhance the performance of a coupled global positioning/inertial navigation system (GPS/INS) for land navigation applications during the GPS signal loss. Our method is based on using an artificial neural network (ANN) to intelligently aid the GPS/INS coupled navigation system in the absence of GPS signals. The proposed enhanced GPS/INS is used in the dynamic environment of a tour of an autonomous van and we provide the results here. GPS/INS+ANN system performance is thus demonstrated with the land trials. Secondly, our work focuses on the identification and enlargement of the stability region of the ALV. In this thesis, the domain of attraction of the ALV is found to be patched by chaotic and regular regions with chaotic boundaries which are extracted using novel technique of cell mapping equipped with measures of fractal dimension and rough sets. All image cells in the cellular state space, with their individual fractal dimension are classified as being members of lower approximation (surely stable), upper approximation (possibly stable) or boundary region using rough set theory. The obtained rough set with fractal dimension as its attribute is used to model the uncertainty of the regular regions. This uncertainty is then smoothed by a reinforcement learning algorithm in order to enlarge regular regions that are used for chassis control, critical in ALV in preventing vibration damages that can harm the payload. Hence, we will make ALV work in the largest safe area in dynamical sense and prevent the vehicle and its cargo.

Tsunamis are characterized as shallow water waves, with long periods and wavelengths. They occur by a sudden water volume displacement. Earthquake is one of the main reasons of a tsunami development. Historical data for an observation period of 3500 years starting from 1500 B.C. indicates that approximately 100 tsunamis occurred in the seas neighboring Turkey. Historical earthquake and tsunami data were collected and used to develop two artificial neural network models to forecast tsunami characteristics for future occurrences and to estimate the tsunami return period. Artificial Neural Network (ANN) is a system simulating the human brain learning and thinking behavior by experiencing measured or observed data. A set of artificial neural network is used to estimate the future earthquakes that may create a tsunami and their magnitudes. A second set is designed for the estimation of tsunami inundation with relation with the tsunami intensity, the earthquake depth and the earthquake magnitude that are predicted by the first set of neural networks. In the case study, Marmara and Aegean regions are taken into consideration for the estimation process. Return periods including the last occurred earthquake in the Turkish seas, which was the izmit (Kocaeli) Earthquake in 1999, were utilized together with the average earthquake depths calculated for Marmara and Aegean regions for the prediction of the earthquake magnitude that may create a tsunami in the stated regions for various return periods of 1-100 years starting from the year of 2004. The obtained earthquake magnitudes were used together with tsunami intensities and earthquake depth to forecast tsunami wave height at the coast. It is concluded that, Neural Networks predictions were a satisfactory first step to implement earthquake parameters such as depth and magnitude, for the average tsunami height on the shore calculations.

This dissertation presents the results of a Ph.D. research entitled as methodology development for SME based virtual enterprises. The research addresses the preparation and set up of virtual enterprises and enterprise networks. A virtual enterprise (VE) can be perceived as a customer solution delivery system created by a temporary and re-configurable information and communications technology (ICT) enabled aggregation of competencies. The main achievements of the research include: &amp / #8226 / Clarification and definition of the concept for virtual enterprises and enterprise networks including preparation of these. o A fast and efficient setup of virtual enterprises can be enabled through the establishment of an enterprise network in which an appropriate type and degree of work preparation can be established prior to the set up of virtual enterprises. &amp / #8226 / Development of a framework and a reference architecture for virtual enterprises named as Structured Methodology and ICT Reference Architecture respectively. o Structured Methodology structures the body of knowledge related to preparation, set up and operation of virtual enterprises and enterprise networks. o ICT reference architecture consists of three levels with seven layers to portray in a diagrammatic fashion how different enterprises may exchange and use information between their respective organizations&amp / #8217 / specific proprietary systems and a central server. &amp / #8226 / Development of a methodology for virtual enterprise named as Virtual Enterprise Methodology (VEM) o VEM consists of a set of guidelines, which systematically describes activities that enterprises should consider in relation to set up and preparation of own enterprise networks with the aim to set up virtual enterprises. &amp / #8226 / Testing and validation of the developed VEM with the realization of a virtual case study and establishment of a validation platform respectively. o Virtual case study demonstrates the application of the developed VE methodology with the illustration of the key activities related to setting up breeding environment, setting up &amp / operating VE and dissolution of VE. o The findings in the research can be validated through the various activities as meetings, conferences, presentations and publication of journals.

This study presents a new approach for nonlinear multi-scale constitutive models using artificial neural networks (ANNs). Three ANN classes are proposed to characterize the nonlinear multi-axial stress-strain behavior of metallic, polymeric, and fiber reinforced polymeric (FRP) materials, respectively. Load-displacement responses from nanoindentation of metallic and polymeric materials are used to train new generation of dimensionless ANN models with different micro-structural properties as additional variables to the load-deflection. The proposed ANN models are effective in inverse-problems set to back-calculate in-situ material parameters from given overall nanoindentation test data with/without time-dependent material behavior. Towards that goal, nanoindentation tests have been performed for silicon (Si) substrate with/without a copper (Cu) film. Nanoindentation creep test data, available in the literature for Polycarbonate substrate, are used in these inverse problems. The predicted properties from the ANN models can also be used to calibrate classical constitutive parameters. The third class of ANN models is used to generate the effective multi-axial stress-strain behavior of FRP composites under plane-stress conditions. The training data are obtained from coupon tests performed in this study using off-axis tension/compression and pure shear tests for pultruded FRP E-glass/polyester composite systems. It is shown that the trained nonlinear ANN model can be directly coupled with finite-element (FE) formulation as a material model at the Gaussian integration points of each layered-shell element. This FE-ANN modeling approach is applied to simulate an FRP plate with an open-hole and compared with experimental results. Micromechanical nonlinear ANN models with damage formulation are also formulated and trained using simulated FE modeling of the periodic microstructure. These new multi-scale ANN constitutive models are effective and can be extended by including more material variables to capture complex material behavior, such as softening due to micro-structural damage or failure.

A new method is developed to determine a set of informative and refined interface assertions satisfied by functions that are represented by feed-forward neural networks. Neural networks have often been criticized for their low degree of comprehensibility.It is difficult to have confidence in software components if they have no clear and valid interface description. Precise and understandable interface assertions for a neural network based software component are required for safety critical applications and for theintegration into larger software systems. The interface assertions we are considering are of the form &quote if the input x of the neural network is in a region (alpha symbol) of the input space then the output f(x) of the neural network will be in the region (beta symbol) of the output space &quote and vice versa. We are interested in computing refined interface assertions, which can be viewed as the computation of the strongest pre- and postconditions a feed-forward neural network fulfills. Unions ofpolyhedra (polyhedra are the generalization of convex polygons in higher dimensional spaces) are well suited for describing arbitrary regions of higher dimensional vector spaces. Additionally, polyhedra are closed under affine transformations. Given a feed-forward neural network, our method produces an annotated neural network, where each layer is annotated with a set of valid linear inequality predicates. The main challenges for the computation of these assertions is to compute the solution of a non-linear optimization problem and the projection of a polyhedron onto a lower-dimensional subspace.

A forced landing for an Unmanned Aerial Vehicle (UAV) is required if there is an emergency on board that requires the aircraft to land immediately. Piloted aircraft in the same scenario have a human on board that is able to engage in the complex decision making process involved in the choice of a suitable landing location. If UAVs are to ever fly routinely in civilian airspace, then it is argued that the problem of finding a safe landing location for a forced landing is an important unresolved problem that must be addressed. This thesis presents the results of an investigation into the feasibility of using machine vision techniques to locate candidate landing sites for an autonomous UAV forced landing. The approach taken involves the segmentation of the image into areas that are large enough and free of obstacles; classification of the surface types of these areas; incorporating slope information from readily available digital terrain databases; and finally fusing these maps together using a high level set of simple linguistic fuzzy rules to create a final candidate landing site map. All techniques were evaluated on actual flight data collected from a Cessna 172 flying in South East Queensland. It was shown that the use of existing segmentation approaches from the literature did not provide the outputs required for this problem in the airborne images encountered in the gathered dataset. A simple method was then developed and tested that provided suitably sized landing areas that were free of obstacles and large enough to land. The advantage of this novel approach was that these areas could be extracted from the image directly without solving the difficult task of segmenting the entire image into the individual homogenous objects. A number of neural network classification approaches were tested with the surface types of candidate landing site regions extracted from the aerial images. A number of novel techniques were developed through experimentation with the classifiers that greatly improved upon the classification accuracy of the standard approaches considered. These novel techniques included: automatic generation of suitable output subclasses based on generic output classes of the classifier; an optimisation process for generating the best set of input features for the classifier based on an automated analysis of the feature space; the use of a multi-stage classification approach; and the generation of confidence measures based on the outputs of the neural network classifiers. The final classification result of the system performs significantly better than a human test pilot's classification interpretation of the dataset samples. In summary, the algorithms were able to locate candidate landing site areas that were free of obstacles 92.3 ±2.6% (99% confidence in the result) of the time, with free obstacle candidate landing site areas that were large enough to land in missed only 5.3 ±2.2% (99% confidence in the result) of the time. The neural network classification networks developed were able to classify the surface type of the candidate landing site areas to an accuracy of 93.9 ±3.7% (99% confidence in the result) for areas labelled as Very Certain. The overall surface type classification accuracy for the system (includes all candidate landing sites) was 91.95 ±4.2% (99% confidence in the result). These results were considered to be an excellent result as a human test pilot subject was only able to classify the same data set to an accuracy of 77.24 %. The thesis concludes that the techniques developed showed considerable promise and could be used immediately to enhance the safety of UAV operations. Recommendations include the testing of algorithms over a wider range of datasets and improvements to the surface type classification approach that incorporates contextual information in the image to further improve the classification accuracy.