Computer Engineering Commons^™

3-D Scene Reconstruction From Line Correspondences Between Multiple Views, Michael Linger

Browse all Theses and Dissertations

Three-dimensional scene reconstruction from 2-D images has many applications, such as surveillance, mission planning, autonomous navigation systems, cartography, and target recognition. Of specific interest to this research is the reconstruction of urban scenes containing man-made structures, such as roads and buildings, to support the burgeoning surveillance industry. Using 3-D maps to augment existing mission planning cartography products (DTED/SRTM, CADRG, CIB), mission and event planners will be able to compute strategic line-of-sight coverage for threat avoidance or threat prosecution. Forensic video analysts can use these models to recreate crime scenes, while law enforcement can build flight plans to minimize occlusions from …

A Large Scale Distributed Syntactic, Semantic And Lexical Language Model For Machine Translation, Ming Tan

Browse all Theses and Dissertations

The n-gram model is the most widely used language model (LM) in statistical machine translation system, due to its simplicity and scalability. However, it only encodes the local lexical relation between adjacent words and clearly ignores the rich syntactic and semantic structures of the natural languages. Attempting to increase the order of an n-gram to describe longer range dependencies in natural language immediately runs into the curse of dimensionality. Although previous researches tried to increase the order of n-gram on a large corpus, they did not see obvious improvement beyond 6-gram. Meanwhile, other LMs, such as syntactic language models and …

A Semantics-Based Approach To Machine Perception, Cory Andrew Henson

Browse all Theses and Dissertations

Machine perception can be formalized using semantic web technologies in order to derive abstractions from sensor data using background knowledge on the Web, and efficiently executed on resource-constrained devices. Advances in sensing technology hold the promise to revolutionize our ability to observe and understand the world around us. Yet the gap between observation and understanding is vast. As sensors are becoming more advanced and cost-effective, the result is an avalanche of data of high volume, velocity, and of varied type, leading to the problem of too much data and not enough knowledge (i.e., insights leading to actions). Current estimates predict …

A Methodology For Extracting Human Bodies From Still Images, Athanasios Tsitsoulis

Browse all Theses and Dissertations

Monitoring and surveillance of humans is one of the most prominent applications of today and it is expected to be part of many future aspects of our life, for safety reasons, assisted living and many others. Many efforts have been made towards automatic and robust solutions, but the general problem is very challenging and remains still open. In this PhD dissertation we examine the problem from many perspectives. First, we study the performance of a hardware architecture designed for large-scale surveillance systems. Then, we focus on the general problem of human activity recognition, present an extensive survey of methodologies that …

Anomalies In Sensor Network Deployments: Analysis, Modeling, And Detection, Giovani Rimon Abuaitah

Browse all Theses and Dissertations

A sensor network serves as a vital source for collecting raw sensory data. Sensor data are later processed, analyzed, visualized, and reasoned over with the help of several decision making tools. A decision making process can be disastrously misled by a small portion of anomalous sensor readings. Therefore, there has been a vast demand for mechanisms that identify and then eliminate such anomalies in order to ensure the quality, integrity, and/or trustworthiness of the raw sensory data before they can even be interpreted.

Prior to identifying anomalies, it is essential to understand the various anomalous behaviors prevalent in a sensor …

Visualizing Confusion Matrices For Multidimensional Signal Detection Correlational Methods And Semantic Cluster Based Visualization In Virtual Environments, Yue Zhou

Browse all Theses and Dissertations

General Recognition Theory (GRT) is a multidimensional signal detection theory framework for capturing sources of perceptual and decisional dependence. The primary type of data for GRT models is an identification-confusion matrix derived in a complete factorial identification task. This confusion matrix plots the responses of study participant for a given signal. The responses may reveal that participants were unable to recognize the signal properly. Such violations of any type of independence in the GRT framework result in response patterns that reflect some form of correlation in the GRT space. While an individual confusion matrix is rather small and relatively easy …

Cooperative Interactive Distributed Guidance On Mobile Devices, Gregory Burnett

Browse all Theses and Dissertations

Mobiles device are quickly becoming an indispensable part of our society. Equipped with numerous communication capabilities, they are increasingly being examined as potential tools for civilian and military usage to aide in distributed remote collaboration for dynamic decision making and physical task completion. With an ever growing mobile workforce, the need for remote assistance in aiding field workers who are confronted with situations outside their expertise certainly increases. Enhanced capabilities in using mobile devices could significantly improve numerous components of a task's completion (i.e. accuracy, timing, etc.). This dissertation considers the design of mobile implementation of technology and communication capabilities …

Streamsurface Smoke Effect For Visualizing Dragon Fly Cfd Data In Modern Opengl With An Emphasis On High Performance, Jordan Sipes

Browse all Theses and Dissertations

Visualizing 3D, time dependent velocity vector fields is a difficult topic. Streamlines can be used to visualize 3D vector fields. A smoke effect where the streamline is faded out as time progresses can provide a better visualization of a time dependent flow. This work uses modern OpenGL to create a smoke trail effect with streamsurfaces in the dragon fly data set. Many aspects affecting performance are tested to determine the best options or approach.

Natural Language Document And Event Association Using Stochastic Petri Net Modeling, Michael Thomas Mills

Browse all Theses and Dissertations

The purpose of this research is to design and implement a new methodology that captures the natural language understanding of events from English natural language text and model it using Stochastic Petri Nets. To establish a baseline of recent natural language processing (NLP) and understanding (NLU) research, two surveys are presented. One is a general survey in NLP and NLU methodologies for processing multi-documents. It summarizes and presents methodologies in terms of their features, capabilities, and maturity. The second survey focuses on graph-based methods for NL text processing and understanding and analyzes them in terms of their functional descriptions, capabilities …

Adaptive Semantic Annotation Of Entity And Concept Mentions In Text, Pablo N. Mendes

Browse all Theses and Dissertations

The recent years have seen an increase in interest for knowledge repositories that are useful across applications, in contrast to the creation of ad hoc or application-specific databases.

These knowledge repositories figure as a central provider of unambiguous identifiers and semantic relationships between entities. As such, these shared entity descriptions serve as a common vocabulary to exchange and organize information in different formats and for different purposes. Therefore, there has been remarkable interest in systems that are able to automatically tag textual documents with identifiers from shared knowledge repositories so that the content in those documents is described in a …

Solar-Powered Wireless Sensor Nodes With Dynamic Power Management For Indoor Use, Ethan Charles Humphrey

Browse all Theses and Dissertations

Indoor environment monitoring, such as medical monitoring and home automation, is achieved through wireless sensor networks that collect data through wireless sensor nodes. These nodes are typically powered by exhaustible power sources that could be difficult or impossible to maintain regularly. A solution to the need for frequent maintenance is to collect the solar power in the environment. This project shows how collecting the solar energy in the environment can extend the lifetime of a sensor node and limit the maintenance required. Along with charging the battery with a solar panel, a dynamic power management scheme can also be implemented. …

Low Cost Open Source Modal Virtual Environment Interfaces Using Full Body Motion Tracking And Hand Gesture Recognition, Matthew J. Marangoni

Browse all Theses and Dissertations

Virtual environments provide insightful and meaningful ways to explore data sets through immersive experiences. One of the ways immersion is achieved is through natural interaction methods instead of only a keyboard and mouse. Intuitive tracking systems for natural interfaces suitable for such environments are often expensive. Recently however, devices such as gesture tracking gloves and skeletal tracking systems have emerged in the consumer market. This project integrates gestural interfaces into an open source virtual reality toolkit using consumer grade input devices and generates a set of tools to enable multimodal gestural interface creation. The AnthroTronix AcceleGlove is used to augment …

Mining Diversified Decision Trees Across Multiple Datasets To Capture Similarities And Alignable Differences, Qian Han

Browse all Theses and Dissertations

This dissertation studies the problem of mining shared and alignable difference knowledge structures across multiple datasets/applications. Shared and alignable difference knowledge structures are important for identifying analogies between application domains and for forming new hypothesis in challenging research applications, and for assessing the degree and types of knowledge-level similarities and differences between application domains for use in learning transfer. Generally speaking, shared knowledge structures characterize underlying datasets and highlight conceptual-level structural similarities among the datasets. This dissertation studies the mining of shared decision trees, which are a special type of shared knowledge structures. We first consider building one shared decision …

Human Action Recognition By Principal Component Analysis Of Motion Curves, Daniel Stephen Chivers

Browse all Theses and Dissertations

Human action recognition is used to automatically detect and recognize actions per- formed by humans in a video. Applications include visual surveillance, human-computer interaction, and robot intelligence, to name a few. An example of a surveillance application is a system that monitors a large public area, such as an airport, for suspicious activity. In human-machine interaction, computers may be controlled by simple human actions. For example, the motion of an arm may instruct the computer to rotate a 3-D model that is being displayed. Human action recognition is also an important capability of intelligent robots that interact with humans.

General …

Behavioral Signature-Based Framework For Identifying Unsatisfiable Variable Mappings Between Digital Designs, Vaibhav Uday Tendulkar

Browse all Theses and Dissertations

Throughout its design process (from specification to implementation) a digital circuit goes through a variety of structural changes. These changes are introduced primarily due to the use of automated tools in the design process. Checking whether the Boolean functions representing the two designs are equivalent is thus necessary to verify if a design implementation adheres to its specification. Combinational Equivalence Checking (CEC) - a process of determining whether two combinational design functions are equiv-alent, has been one of the most researched Boolean matching problems. The well-known CEC techniques that have been proposed adopt some kind of a formal approach such …

Linked Open Data Alignment & Querying, Prateek Jain

Browse all Theses and Dissertations

The recent emergence of the "Linked Data" approach for publishing data represents a major step forward in realizing the original vision of a web that can "understand and satisfy the requests of people and machines to use the web content" i.e. the Semantic Web. This new approach has resulted in the Linked Open Data (LOD) Cloud, which includes more than 295 large datasets contributed by experts belonging to diverse communities such as geography, entertainment, and life sciences. However, the current interlinks between datasets in the LOD Cloud, as we will illustrate,are too shallow to realize much of the benefits promised. …

Cloudvista: A Framework For Interactive Visual Cluster Exploration Of Big Data In The Cloud, Zhen Li

Browse all Theses and Dissertations

With the development and deployment of ubiquitous information sensing, mobile devices,wireless sensor networks, RFID readers, simulation, and computer generated software logs, big data have become precious resources for scientific study, business intelligence, and national security. As one of the most intuitive and effective analysis methods,visual cluster analysis remains as a significant challenge for big datasets. First, existing visualization models need to be updated to process big data in parallel. Second, processing big data inevitably bring large latency, which conflicts the requirement of interactivity. In this thesis, we develop the CloudVista framework to address the common problems with data reduction methods …

Knowledge Acquisition In A System, Christopher J. Thomas

Browse all Theses and Dissertations

I present a method for growing the amount of knowledge available on the Web using a hermeneutic method that involves background knowledge, Information Extraction techniques and validation through discourse and use of the extracted information.

I present the metaphor of the "Circle of Knowledge on the Web". In this context, knowledge acquisition on the web is seen as analogous to the way scientific disciplines gradually increase the knowledge available in their field.

Here, formal models of interest domains are created automatically or manually and then validated by implicit and explicit validation methods before the statements in the created models can …

Abstraction Driven Application And Data Portability In Cloud Computing, Ajith Harshana Ranabahu

Browse all Theses and Dissertations

Cloud computing has changed the way organizations create, manage, and evolve their applications. While many organizations are eager to use the cloud, tempted by substantial cost savings and convenience, the implications of using clouds are still not well understood. One of the major concerns in cloud adoption is the vendor lock-in of applications, caused by the heterogeneity of the numerous cloud service offerings. Vendor locked applications are difficult, if not impossible to port from one cloud system to another, forcing cloud service consumers to use undesired or suboptimal solutions. This dissertation investigates a complete and comprehensive solution to address the …

Winding Resistance And Winding Power Loss Of High-Frequency Power Inductors, Rafal P. Wojda

Browse all Theses and Dissertations

The scope of this research is concentrated on analytical winding size optimization (thickness or diameter) of high-frequency power inductors wound with foil, solid-round wire, multi-strand wire, and litz-wire conductors.

The first part of this research concerns analytical optimization of the winding size (thickness or diameter) for the inductors conducting a sinusoidal current. Estimation of winding resistance in individual inductor layers made of foil, taking into account the skin and proximity effects is performed. Approximated equations for the winding power loss in each layer are given and the optimal values of foil thickness for each layer are derived.

A low- and …

Optimization Of Spectrum Allocation In Cognitive Radio And Dynamic Spectrum Access Networks, Tao Zhang

Browse all Theses and Dissertations

Spectrum has become a treasured commodity. However, many licensed frequency bands exclusively assigned to the primary license holders (also called primary users) remain relatively unused or under-utilized for most of the time. Allowing other users (also called secondary users) without a license to operate in these bands with no interference becomes a promising way to satisfy the fast growing needs for frequency spectrum resources. A cognitive radio adapts to the environment it operates in by sensing the spectrum and quickly decides on appropriate frequency bands and transmission parameters to use in order to achieve certain performance goals. One of the …

Measuring Uncertainty Of Protein Secondary Structure, Alan Eugene Herner

Browse all Theses and Dissertations

This dissertation develops and demonstrates a method to measure the uncertainty of secondary structure of protein sequences using Shannon's information theory. This method is applied to a newly developed large dataset of chameleon sequences and to several protein hinges culled from the Hinge Atlas. The uncertainty of the central residue in each tripeptide is computed for each amino acid in a sequence using Cuff and Barton's CB513 as the reference set. It is shown that while secondary structure uncertainty is relatively high in chameleon regions [avg = 1.27 bits] it is relatively low in the regions 1-7 residues nearest a …

A User Centered Design And Prototype Of A Mobile Reading Device For The Visually Impaired, Robert B. Keefer

Browse all Theses and Dissertations

While mobile reading devices have been on the market and investigated by researchers in recent years, there is still work required to make these devices highly accessible to the visually impaired. A usability test with one such device revealed gaps in the current state of the art devices. These gaps focus mostly on the user interaction and his or her ability to quickly consume written reading material. In this dissertation a voice user interface (VUI) is presented that improves the ability of a blind user of a mobile reading device to interact with written material. The image processing techniques required …

A Triangulation-Based Approach To Nonrigid Image Registration, Timothy R. Linden

Browse all Theses and Dissertations

A triangulation-based approach to nonrigid image registration is presented. This method builds upon control point projective registration methods. Control points for this method are located using the Harris point detector. An analysis is presented for this detector to show its properties. Projective registration is used as the basis for this non-rigid registration method. Details of the projective registration method used are presented. Nonrigid registration is used to spatially align images of a 3-D scene taken from different views. Projective registration approximates the scene geometry as a plane. This nonrigid approach subdivides the images into small corresponding triangles, to improve the …

Weapon Engagement Zone Maximum Launch Range Approximation Using A Multilayer Perceptron, Brian Michael Birkmire

Browse all Theses and Dissertations

This thesis investigates the use of an artificial neural network (ANN), in particular a Multi-Layer Perceptron (MLP), to perform function approximation on truth data representing a weapon engagement zone's (WEZ) maximum launch range. The WEZ of an air-to-air missile represents the boundaries and zones of effectiveness for a one-vs-one air-to-air combat engagement [13]. The intent is for the network to fuse table lookup and interpolation functionality into a physically compact and computationally efficient package, while improving approximation accuracy over conventional methods. Data was collected from simulated firings of a notional air-to-air missile model and used to train a two layer …

Design And Development Of A Fall Detection Device With Infrared Receiving Capabilities, Ammari Ramzi

Browse all Theses and Dissertations

Fall related injuries are the leading cause of death and hospitalization among the elderly. Falls among older people become a major problem facing hospitals and nursing homes. In this study we put an effort to design a wireless device capable of detecting falls with the hope that this study will provide a path towards better healthcare monitoring and better independent living for the elderly.

In this project I showed how the fall detection device can be interfaced with different systems to achieve functionality without adding extra cost. For seniors who prefer to stay at their homes and live independently, the …

Large Scale Distributed Semantic N-Gram Language Model, Yuandong Jiang

Browse all Theses and Dissertations

Language model is a crucial component in statistical machine translation system. The basic language model is N-gram which predicts the next word based on previous N-1 words. It has been used in the state-of-the-art commercial machine translation systems over years. However, the N-gram model ignores the rich syntactic and semantic structure in natural languages. We propose a composite semantic N-gram language model which combines probabilistic latent semantic analysis model with N-gram as a generative model. We have implemented the proposed composite language model in a super-computer with thousand processors that is trained by 1.3 billion tokens corpus. Comparing with simple …

3-D Model Characterization And Identification From Intrinsic Landmarks, John L. Camp

Browse all Theses and Dissertations

A method to automatically characterize and identify 3-D range scans based on intrinsic landmarks is presented. Intrinsic landmarks represent locally unique, intrinsic properties of a scanned surface, regardless of scale or rotation. The number, location, and characteristics of landmarks are used to characterize the scanned models. This method contains a selection process to identify stable, intrinsic landmarks for range scans as well as the identification of those scans. The selection process requires no user interaction or surface assumptions. It uses the principal curvatures at the range points to select the landmarks. First, a large number of landmarks are generated by …

A Domain Specific Language Based Approach For Developing Complex Cloud Computing Applications, Ashwin Kumar Manjunatha

Browse all Theses and Dissertations

Computing has changed. Lately, a slew of cheap, ubiquitous, connected mobile devices as well as seemingly unlimited, utility style, pay as you go computing resources has become available at the disposal of the common man. The latter commonly called Cloud Computing (or just Cloud) is democratizing computing by making large computing power accessible to people and corporations around the world easily and economically.

However, taking full advantage of this computing landscape, especially for the data intensive domains, has been hampered by many factors, the primary one being the complexity in developing applications for the variety of available platforms.

This thesis …

Understanding User-Generated Content On Social Media, Bala Meenakshi Nagarajan

Browse all Theses and Dissertations

Over the last few years, there has been a growing public and enterprise fascination with 'social media' and its role in modern society. At the heart of this fascination is the ability for users to participate, collaborate, consume, create and share content via a variety of platforms such as blogs, micro-blogs, email, instant messaging services, social network services, collaborative wikis, social bookmarking sites, and multimedia sharing sites.

This dissertation is devoted to understanding informal user-generated textual content on social media platforms and using the results of the analysis to build Social Intelligence Applications.

The body of research presented in this …