Digital Commons Network^™

Recurrent Neural Networks And Algorithms For Reconstruction Of Images From Noisy And/Or Partial Data, Ming-Jung Seow

Electrical & Computer Engineering Theses & Dissertations

In this thesis, modular architectures and neighborhood-distance based learning algorithms for fast and effective convergence with increased storage capacity of Hopfield neural networks are presented. The main objective of this research work is to better understand the function of recurrent neural networks and the influence of modularity within a network, and to design, implement, and test the performance of modular Hopfield neural networks for pattern association. Mathematical analysis and results are provided to show that the speed, storage capacity, and generalization capability of the recurrent networks are improved significantly by incorporating the modular architectures and learning algorithms. A new ratio …

Object-Oriented Architecture For Concurrent Processes In A Port Simulation, Reejo Mathew

Electrical & Computer Engineering Theses & Dissertations

An architectural model to represent the resources and infrastructure within a cargo terminal, as well as to support the concurrent but opposite flow of cargo within the terminal, is presented in this thesis. The model supports the configuration of an individual cargo terminal according to its characteristics, as well as the processing involved in the simultaneous flow of cargo in opposite directions through the terminal. This is useful in the analysis of the flow of military cargo and aids the decision-making process to increase the efficiency and throughput of any military operation. This model has been developed with the aim …

Study Of Transport Properties Of Inas Using Monte Carlo Simulation, Satyanadh Gundimada

Electrical & Computer Engineering Theses & Dissertations

The present research is aimed at ascertaining the usefulness of InAs semiconductor material for single photon avalanche photo detectors operating in the Geiger mode at 2 μm wavelengths. InAs is considered as the material suitable for the purpose because of its less bandgap and lower effective mass of the electrons when compared to other semiconductor materials presently in use. Hence, theoretically transient transport properties of bulk InAs are superior and the velocity overshoot phenomena stronger. InAs is a relatively less explored material when compared to other materials like GaAs. The choice of the material is justified with thorough exploration of …

Support For Statistical Analysis Of The Configurable Port Simulation (Cports), Saurav Mazumdar

Electrical & Computer Engineering Theses & Dissertations

The primary objective of this thesis is to provide support for statistical analysis of CPortS: a transportation logistics simulation, which models the movement of military traffic through seaports and the interaction of the traffic with port infrastructure. By any standards, CPortS is a very large, data intensive simulation. It provides capabilities for analyzing many important issues such as port clearance and throughput. CPortS was classically run in single run mode. Only a single replication of the simulation was performed and conclusions were drawn from the results obtained. Users and analysts of CPortS performed multiple runs only to see the effect …

Approaching High Fidelity Human Tracking And Representation In Interactive Virtual Environments, Taimur K. Khan

Electrical & Computer Engineering Theses & Dissertations

This thesis revolves around an Office of Naval Research (ONR) grant known as Virtual Environments for Training (VET). The primary goal is to determine the effectiveness of an immersive environment for training; the secondary goal is to compare the results of this study to a similar study conducted in an environment that is less immersive.

Effectiveness will be determined by the performance of trainees manning a virtual military checkpoint. A four-wall immersive environment employing cave technology will be compared to a three dimensional desktop version of the scenarios employed in the more immersive environment. In order to make this comparison, …

Yet Another Algorithm For Pitch Tracking (Yaapt), Kavita Kasi

Electrical & Computer Engineering Theses & Dissertations

This thesis presents a pitch detection algorithm that is extremely robust for both high quality and telephone speech. The kernel method for this algorithm is the Normalized Cross Correlation (NCCF) reported by David Talkin [16]. Major innovations include: processing of the original acoustic signal and a nonlinearly processed version of the signal to partially restore very weak F0 components; intelligent peak picking to select multiple F0 candidates and assign merit factors; and, incorporation of highly robust pitch contours obtained from smoothed versions of low frequency portions of spectrograms. Dynamic programming is used to find the ''best" pitch track among all …

A Multilevel Neural Network Architecture For Digital Implementation Of A Face Recognition System Based On Eigenface Approach, Linda Rajan

Electrical & Computer Engineering Theses & Dissertations

The design and development of the digital implementation of a multilevel feed forward neural network architecture for face recognition based on statistical features representing Eigenfaces is presented in this thesis. The architecture is divided into three parts: feature extractor, classifier and identifier, The Eigenface extractor architecture is developed based on an efficient design strategy in which all the M weight values corresponding to the Eigenfaces are generated simultaneously from M images representing the Eigen vectors and the test input image. The multilayer neural network classifier is trained using error backpropagation algorithm. A novel multilevel digital architecture is developed for the …

Traffic Simulation Using Arena, Shanti Yelamanchi

Electrical & Computer Engineering Theses & Dissertations

Many traffic simulation tools exist for developing traffic simulations; these tools can be divided broadly into two categories — macro simulation tools and micro simulation tools. These two categories of simulation tools are directed at modeling the extremes of traffic systems: very large systems and very small systems. There is a class of intermediate-sized transportation networks for which neither category of simulation tools might perform adequately. Additionally these specialized traffic simulation tools have a high learning curve. For developing medium sized traffic simulations in a short period of time, one might choose to use a familiar general-purpose discrete event simulation …

The Effect Of Model Formulation On The Comparative Performance Of Artificial Neural Networks And Regression, Michael F. Cochrane

Engineering Management & Systems Engineering Theses & Dissertations

Multiple linear regression techniques have been traditionally used to construct predictive statistical models, relating one or more independent variables (inputs) to a dependent variable (output). Artificial neural networks can also be constructed and trained to learn these complex relationships, and have been shown to perform at least as well as linear regression on the same data sets. Research on the use of neural network models as alternatives to multivariate linear regression has focused predominantly on the effects of sample size, noise, and input vector size on the comparative performance of these two modeling techniques. However, research has also shown that …

The Development Of An Enterprise Supply Chain Model For Naval Warship Construction, Rex A. Wallen

Computational Modeling & Simulation Engineering Theses & Dissertations

The utilization of computer simulation in the shipbuilding industry is not a new concept and many shipyards in the US and around the world are using simulation tools in a variety of ways with various levels of success. In other industries, computer simulation has proven itself as a powerful tool for reducing non-value added activities and promises to become more prominent in its use as a resource management tool. Its use in the manufacturing of outfitting components in the construction of Naval warships has had limited success due mainly to the inherent nature of ship construction, especially shipyards engaged in …

Embedded Software Programming To Develop A Command Line User Interface For Monitoring And Debugging A Manually Driven Gas Regulator Control System, Syed N. Hyder

Electrical & Computer Engineering Theses & Dissertations

This thesis presents a complete embedded programming model and software codes for a command-line user interface for CONCOA's gas regulator control system. Control Corporation of America (CONCOA) manufactures high-pressure gas regulators, which mechanically control the pressure at their outlets. Since the control system is based on mechanical regulators, adding or stopping gas flow from the system can cause manifold fluctuation that could further cause the pressure to rise or fall with time. The main motivation for developing a command line user interface is to provide a centralized computer control to monitor and debug the gas regulator control system electronically by …

Association Of 3d Visualization With Discrete Event Simulation, Krishna Chaitanya Kunam

Electrical & Computer Engineering Theses & Dissertations

Three-dimensional visualization provides simulation users with imagery that is closely related to their direct human experience. 3D visualization of simulations therefore has several advantages: it assists the developer in verifying and debugging the simulation; it often aids the analyst in gaining a better understanding of system performance; and it is especially important in explaining simulation results to the customer. This work presents a method of associating 3D visualizations to discrete event simulations for process simulations. A software system called 3DGen is developed that automates the process of generating a 3D visualization for a discrete event simulation. The 3DGen system is …

Robust Face Representation And Recognition Under Low Resolution And Difficult Lighting Conditions, Mohammad Moinul Islam

Electrical & Computer Engineering Theses & Dissertations

This dissertation focuses on different aspects of face image analysis for accurate face recognition under low resolution and poor lighting conditions. A novel resolution enhancement technique is proposed for enhancing a low resolution face image into a high resolution image for better visualization and improved feature extraction, especially in a video surveillance environment. This method performs kernel regression and component feature learning in local neighborhood of the face images. It uses directional Fourier phase feature component to adaptively lean the regression kernel based on local covariance to estimate the high resolution image. For each patch in the neighborhood, four directional …

A Formal Object Model For Layered Networks To Support Verification And Simulation, Rasha M. B. E. Morsi

Electrical & Computer Engineering Theses & Dissertations

This work presents an abstract formal model of the interconnection structure of the Open Systems Interconnection Reference Model (OSI-RM) developed using Object-Oriented modeling principles permitting it to serve as a re-usable platform in supporting the development of simulations and formal methods applied to layered network protocols. A simulation of the object model using MODSIM III was developed and Prototype Verification System (PVS) was used to show the applicability of the object model to formal methods by formally specifying and verifying a Global Systems for Mobile communications (GSM) protocol. This application has proved to be successful in two aspects. The first …

Federating Heterogeneous Digital Libraries By Metadata Harvesting, Xiaoming Liu

Computer Science Theses & Dissertations

This dissertation studies the challenges and issues faced in federating heterogeneous digital libraries (DLs) by metadata harvesting. The objective of federation is to provide high-level services (e.g. transparent search across all DLs) on the collective metadata from different digital libraries. There are two main approaches to federate DLs: distributed searching approach and harvesting approach. As the distributed searching approach replies on executing queries to digital libraries in real time, it has problems with scalability. The difficulty of creating a distributed searching service for a large federation is the motivation behind Open Archives Initiatives Protocols for Metadata Harvesting (OAI-PMH). OAI-PMH supports …

Video Indexing And Retrieval Techniques Using Novel Approaches To Video Segmentation, Characterization, And Similarity Matching, Waleed Ezzat Farag

Computer Science Theses & Dissertations

Multimedia applications are rapidly spread at an ever-increasing rate introducing a number of challenging problems at the hands of the research community, The most significant and influential problem, among them, is the effective access to stored data. In spite of the popularity of keyword-based search technique in alphanumeric databases, it is inadequate for use with multimedia data due to their unstructured nature. On the other hand, a number of content-based access techniques have been developed in the context of image indexing and retrieval; meanwhile video retrieval systems start to gain wide attention, This work proposes a number of techniques constituting …

A Policy-Based Resource Brokering Environment For Computational Grids, Ahmed Hamdan Al-Theneyan

Computer Science Theses & Dissertations

With the advances in networking infrastructure in general, and the Internet in particular, we can build grid environments that allow users to utilize a diverse set of distributed and heterogeneous resources. Since the focus of such environments is the efficient usage of the underlying resources, a critical component is the resource brokering environment that mediates the discovery, access and usage of these resources. With the consumer's constraints, provider's rules, distributed heterogeneous resources and the large number of scheduling choices, the resource brokering environment needs to decide where to place the user's jobs and when to start their execution in a …

Performance Modeling And Prediction For The Scalable Solution Of Partial Differential Equations On Unstructured Grids, Dinesh Kumar Kaushik

Computer Science Theses & Dissertations

This dissertation studies the sources of poor performance in scientific computing codes based on partial differential equations (PDEs), which typically perform at a computational rate well below other scientific simulations (e.g., those with dense linear algebra or N-body kernels) on modern architectures with deep memory hierarchies. We identify that the primary factors responsible for this relatively poor performance are: insufficient available memory bandwidth, low ratio of work to data size (good algorithmic efficiency), and nonscaling cost of synchronization and gather/scatter operations (for a fixed problem size scaling). This dissertation also illustrates how to reuse the legacy scientific and engineering software …

Geometric Integrators For Hamiltonian Pdes, Dmitry Karpeev

Computer Science Theses & Dissertations

We consider methods for systematic construction of algorithms for a class of time-dependent PDEs with Hamiltonian structure. These systems possess phase space geometry and constants of the motion that need to be preserved by the integration algorithm to reflect the qualitative features of the system.

We exploit the structure of Hamiltonian systems, in particular their variational formulation based on a Lagrangian, and the dual covariant formulation, to expose the geometric features of the system that have natural analogs when discretized. We emphasize the local space-time approach to the constructions, making them amenable to parallelization and preconditioning using domain decomposition methods, …