Computer Engineering Commons^™

Learning Image‐Text Associations, Tao Jiang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Web information fusion can be defined as the problem of collating and tracking information related to specific topics on the World Wide Web. Whereas most existing work on Web information fusion has focused on text-based multidocument summarization, this paper concerns the topic of image and text association, a cornerstone of cross-media Web information fusion. Specifically, we present two learning methods for discovering the underlying associations between images and texts based on small training data sets. The first method based on vague transformation measures the information similarity between the visual features and the textual features through a set of predefined domain-specific …

Programmer Friendly Refactoring Tools, Emerson Murphy-Hill

Dissertations and Theses

Tools that perform semi-automated refactoring are currently under-utilized by programmers. If more programmers adopted refactoring tools, software projects could make enormous productivity gains. However, as more advanced refactoring tools are designed, a great chasm widens between how the tools must be used and how programmers want to use them. This dissertation begins to bridge this chasm by exposing usability guidelines to direct the design of the next generation of programmer-friendly refactoring tools, so that refactoring tools fit the way programmers behave, not vice-versa.

Locating And Tracking Objects By Efficient Comparison Of Real And Predicted Synthetic Video Imagery, Damian M. Lyons, D. Paul Benjamin

Faculty Publications

A mobile robot moving in an environment in which there are other moving objects and active agents, some of which may represent threats and some of which may represent collaborators, needs to be able to reason about the potential future behaviors of those objects and agents. In this paper we present an approach to tracking targets with complex behavior, leveraging a 3D simulation engine to generate predicted imagery and comparing that against real imagery. We introduce an approach to compare real and simulated imagery and present results using this approach to locate and track objects with complex behaviors. In this …

Reusable, Interactive, Multilingual Online Avatars, Charlie Cullen, Carl Goodman, Paula Mcgloin, Anna Deegan

Conference papers

This paper details a system for delivering reusable, interactive multilingual avatars in online children’s games. The development of these avatars is based on the concept of an intelligent media object that can be repurposed across different productions. The system is both language and character independent, allowing content to be reused in a variety of contexts and locales. In the current implementation, the user is provided with an interactive animated robot character that can be dressed with a range of body parts chosen by the user in real-time. The robot character reacts to each selection of a new part in a …

A Hierarchical Method Based On Active Shape Models And Directed Hough Transform For Segmentation Of Noisy Biomedical Images; Application In Segmentation Of Pelvic X-Ray Images, Rebecca Smith, Kayvan Najarian, Kevin R. Ward

Computer Science Publications

Background

Traumatic pelvic injuries are often associated with severe, life-threatening hemorrhage, and immediate medical treatment is therefore vital. However, patient prognosis depends heavily on the type, location and severity of the bone fracture, and the complexity of the pelvic structure presents diagnostic challenges. Automated fracture detection from initial patient X-ray images can assist physicians in rapid diagnosis and treatment, and a first and crucial step of such a method is to segment key bone structures within the pelvis; these structures can then be analyzed for specific fracture characteristics. Active Shape Model has been applied for this task in other bone …

Unified Wavelet And Gaussian Filtering For Segmentation Of Ct Images; Application In Segmentation Of Bone In Pelvic Ct Images, Simina Vasilache, Kevin R. Ward, Charles Cockrell, Jonathan Ha, Kayvan Najarian

Computer Science Publications

Background

The analysis of pelvic CT scans is a crucial step for detecting and assessing the severity of Traumatic Pelvic Injuries. Automating the processing of pelvic CT scans could impact decision accuracy, decrease the time for decision making, and reduce health care cost. This paper discusses a method to automate the segmentation of bone from pelvic CT images. Accurate segmentation of bone is very important for developing an automated assisted-decision support system for Traumatic Pelvic Injury diagnosis and treatment.

Methods

The automated method for pelvic CT bone segmentation is a hierarchical approach that combines filtering and histogram equalization, for image …

A Comparative Analysis Of Multi-Level Computer-Assisted Decision Making Systems For Traumatic Injuries, Soo-Yeon Ji, Rebecca Smith, Toan Huynh, Kayvan Najarian

Computer Science Publications

Background

This paper focuses on the creation of a predictive computer-assisted decision making system for traumatic injury using machine learning algorithms. Trauma experts must make several difficult decisions based on a large number of patient attributes, usually in a short period of time. The aim is to compare the existing machine learning methods available for medical informatics, and develop reliable, rule-based computer-assisted decision-making systems that provide recommendations for the course of treatment for new patients, based on previously seen cases in trauma databases. Datasets of traumatic brain injury (TBI) patients are used to train and test the decision making algorithm. …

Brain Mapping And Detection Of Functional Patterns In Fmri Using Wavelet Transform; Application In Detection Of Dyslexia, Soo-Yeon Ji, Kevin R. Ward, Kayvan Najarian

Computer Science Publications

Background

Functional Magnetic Resonance Imaging (fMRI) has been proven to be useful for studying brain functions. However, due to the existence of noise and distortion, mapping between the fMRI signal and the actual neural activity is difficult. Because of the difficulty, differential pattern analysis of fMRI brain images for healthy and diseased cases is regarded as an important research topic. From fMRI scans, increased blood ows can be identified as activated brain regions. Also, based on the multi-sliced images of the volume data, fMRI provides the functional information for detecting and analyzing different parts of the brain.

Methods

In this …

Automated Ventricular Systems Segmentation In Brain Ct Images By Combining Low-Level Segmentation And High-Level Template Matching, Wenan Chen, Rebecca Smith, Soo-Yeon Ji, Kevin R. Ward, Kayvan Najarian

Computer Science Publications

Background

Accurate analysis of CT brain scans is vital for diagnosis and treatment of Traumatic Brain Injuries (TBI). Automatic processing of these CT brain scans could speed up the decision making process, lower the cost of healthcare, and reduce the chance of human error. In this paper, we focus on automatic processing of CT brain images to segment and identify the ventricular systems. The segmentation of ventricles provides quantitative measures on the changes of ventricles in the brain that form vital diagnosis information.

Methods

First all CT slices are aligned by detecting the ideal midlines in all images. The initial …

Whole-Genome Resequencing Of Escherichia Coli K-12 Mg1655 Undergoing Short-Term Laboratory Evolution In Lactate Minimal Media Reveals Flexible Selection Of Adaptive Mutations, Tom M. Conrad, Andrew R. Royce, M. Kenyon Applebee, Christian L. Barrett, Bin Xie, Yuan Gao, Bernhard Ø. Palsson

Computer Science Publications

Background

Short-term laboratory evolution of bacteria followed by genomic sequencing provides insight into the mechanism of adaptive evolution, such as the number of mutations needed for adaptation, genotype-phenotype relationships, and the reproducibility of adaptive outcomes.

Results

In the present study, we describe the genome sequencing of 11 endpoints of Escherichia coli that underwent 60-day laboratory adaptive evolution under growth rate selection pressure in lactate minimal media. Two to eight mutations were identified per endpoint. Generally, each endpoint acquired mutations to different genes. The most notable exception was an 82 base-pair deletion in the rph-pyrE operon that appeared in …

C2 Domain Ontology Within Our Lifetime, Leslie Winters, Andreas Tolk

Computational Modeling & Simulation Engineering Faculty Publications

Agile Command and Control (C2) requires agile information sharing with an increasingly wide variety of military and non-military partners. While current net-centric approaches may improve information sharing within a particular niche of C2, they do not support information sharing across the larger C2 domain. Although not a silver bullet, the development and application of a C2 domain ontology to improve C2 data and service integration appears to be increasingly realistic. In fact, there are several examples of successful ontology applications in domains such as medicine, biology, and engineering, and the new discipline of Applied Ontology is emerging. C2 data, architecture, …

Conceptual Requirements For Command And Control Languages, Andreas Tolk, Curtis L. Blais, Saikou Y. Diallo, Charles Turnitsa

Computational Modeling & Simulation Engineering Faculty Publications

The current Coalition Battle Management Language initiative (C-BML) will define a language to unambiguously exchange command and control information between systems. This paper introduces a categorization that may be used to guide the process of developing C-BML effectively by enumerating the conceptual requirements the authors have identified in model-based data engineering and process engineering based studies in various domains.

First, it is important to distinguish if application of the language will support the planning, execution, or observation phase of command and control. While C-BML already distinguishes between tasking and reporting, planning is a category with different requirements.

Second, the language …

Harmonizing Bml Approaches: Grammars And Data Models For A Bml Standard, Dietmar Kunde, Thomas Orichel, Andreas Tolk, Ulrich Schade, Michael R. Hieb

Computational Modeling & Simulation Engineering Faculty Publications

Battle Management Language (BML) is being developed as an open standard that unambiguously formalizes and specifies Command and Control information, including orders and reports built upon precise representations of tasks. BML is a language specification, based on doctrine and consistent with Coalition standards. The goal of BML is to enable and improve the interoperability in the C2 area, especially by enabling also the military communication with simulation systems and future robotic forces.

Although the need for BML is well documented, a SISO standard has still not been achieved. At present, there are two recommended approaches focusing on different aspects. In …

An Extended Interoperability Framework For Joint Composability, Andreas Tolk, Charles D. Turnitsa

Computational Modeling & Simulation Engineering Faculty Publications

Interoperation of systems is defined by the aspects of integratability, interoperability, and composability. It is therefore needed, to address all levels of interoperation - from conceptual models via implemented systems to the supported infrastructure - accordingly in an interoperation framework.

Several candidates are available and provide valuable part solution. This paper evaluates the Base Object Models (BOMs), Discrete Event Simulation Specifications (DEVS), Unified Language Model (UML) artifacts as used within the Test and Training Enabling Architecture (TENA), the Object-Process Methodology (OPM), and Conceptual Graphs (CG) regarding their contribution.

Using the Levels of Conceptual Interoperability Model (LCIM), an extended interoperability framework …

Exploring Primitives Of Meaning In Support Of Interoperability, Charles D. Turnitsa, Andreas Tolk, Robert Kewley

Computational Modeling & Simulation Engineering Faculty Publications

Semantic mismatch between systems is due, in part, to the grouping together of terms who have defined meaning in different levels of granularity, and which are composed together into different groupings by distinct systems. It has been proposed that making use of elemental concepts (referred to here as primitives of meaning) can assist in interoperability, but seeking to define all terms at a level of granularity equal to or greater than that of all involved systems.

By decomposing a system’s groups of composed terms into primitives of meaning, the building blocks that can be reassembled into the compositions required by …

Applying Model-Based Data Engineering To Evaluate The Alignment Of Information Modeled Within Jc3iedm, Msdl, And Matrex-Fom, Anil Ustun, Andreas Tolk, Saikou Diallo

Computational Modeling & Simulation Engineering Faculty Publications

The need for a common representation of entities and their relations to support the easier composition and federation of independently developed solutions in support of the user has been identified and addressed in several papers presented during recent simulation interoperability workshop. One of the underlying assumptions is that standards derived from the same conceptual domain can easily be converted into each others, as they deal with the same concepts. In a project conducted for the U.S. Army’s Program Executive Office (PEO) Soldier, three of such solutions for military operations (with focus on the land forces) were utilized to capture the …

Utilizing Strategic Project Management Processes And The Nato Code Of Best Practice To Improve Management Of Experimentation Events, Andreas Tolk, Rafael E. Landaeta, Robert H. Kewley, Thomas T. Litwin

Computational Modeling & Simulation Engineering Faculty Publications

Systems engineering and project management are two core engineering management processes supported by core quantitative disciplines within engineering management problems. Traditional approaches to systems engineering focus on a single system being engineered and managed (i.e., project managed), while challenges addressing composition of systems of systems and the reuse of systems for new solutions require a strategic management approach that promote a process flow in which the outputs of one project (e.g., deliverables, knowledge, work documents) are captured for the benefit of other projects within and outside the project-based organization. Two other core processes of engineering management are therefore critical to …

Asymmetric Heteroskedasticity Models: A New Justification, Songsak Sriboonchitta, Vladik Kreinovich

Departmental Technical Reports (CS)

Most existing econometric models such as ARCH(q) and GARCH(p,q) take into account heteroskedasticity (non-stationarity) of time series. However, the original ARCH(q) and GARCH(p,q) models do not take into account the asymmetry of the market's response to positive and to negative changes. Several heuristic modifications of ARCH(q) and GARCH(p,q) models have been proposed that take this asymmetry into account. These modifications turned out to be very adequate and efficient in describing the econometric time series. In this paper, we propose a justification of these heuristic modifications -- and thus, an explanation of their empirical efficiency.

Quantum Computing As A Particular Case Of Computing With Tensors, Martine Ceberio, Vladik Kreinovich

Departmental Technical Reports (CS)

One of the main potential applications of uncertainty in computations is quantum computing. In this paper, we show that the success of quantum computing can be explained by the fact that quantum states are, in effect, tensors.

Query Recommendations For Interactive Database Exploration, Gloria Chatzopoulou, Magdalini Eirinaki, Neoklis Polyzotis

Faculty Publications

Relational database systems are becoming increasingly popular in the scientific community to support the interactive exploration of large volumes of data. In this scenario, users employ a query interface (typically, a web-based client) to issue a series of SQL queries that aim to analyze the data and mine it for interesting information. First-time users, however, may not have the necessary knowledge to know where to start their exploration. Other times, users may simply overlook queries that retrieve important information. To assist users in this context, we draw inspiration from Web recommender systems and propose the use of personalized query recommendations. …

One Stop Information Site, Poongkuzhali Dhanasekaran

Theses Digitization Project

The purpose of this project is to construct a website to provide users with interactive, daily information such as weather, traffic alerts, news, restaurant, etc. in one easy accessible site. Contains source code.

Fuzzy Optimal Swarm Of Autonomous Aircrafts For Target Determination And Convergence Control System, Zach D. Richards

Electronic Theses and Dissertations

The thesis project proposes analytical and theoretical algorithms for a networked swarm of autonomous vehicles, such as those used in planet exploration, and to be used in target location determination and convergence, an algorithm of this type could be used in an Autonomous Stratospheric Aircraft (ASA), thus having the possibility of being used for the exploration of a planet as well as many other applications. Upon locating an unknown location of a specified target, the algorithm would then swarm and eventually converge upon the location. There are two similar, but fundamentally different algorithms proposed in this project. These algorithms are …

Biomedical Informatics Research Network (Birn) Data Repository, Laurence Jonathan Bouts Bohannan

Theses Digitization Project

The primary goal of this project was to streamline the submission process for researchers to categorize, approve, curate, and publish these data sets. By supporting the sharing and exchange of these data types in fulfillment of the National Institute of Health guidelines the BIRN Data Repository will have the ability to grow as the need develops for these researchers to easily share information.

Efficient Proton Computed Tomography Image Reconstruction Using General Purpose Graphics Processing Units, Scott Alan Mcallister

Theses Digitization Project

This thesis will investigate the use of general purpose graphics processing units (GPGPUs)for execution of parallel algorithms as well as exploiting the structure of the data being processed.

Archetype Alignment: A Two-Level Driven Semantic Matching Approach To Interoperability In The Clinical Domain, Damon Berry, Jesus Bisbal

Conference Papers

Semantic interoperability between electronic health record systems and other information systems in the health domain implies agreement about the structure and the meaning of the information that is communicated. There are still a number of similar but different EHR system approaches. Some of the newer approaches adopt the two-layer model approach where a generic reference model is constrained by archetypes into valid clinical concepts which can be exchanged. The meaning of the concepts that are represented by an archetype can be conveyed by embedding codes from a commonly recognised terminology at appropriate points in the archetype. However, as the number …

Heterogeneous Drive Mechanisms For Novel Locomotion In Rough Terrain, Roy Godzdanker

Electronic Theses and Dissertations

The smaller the robot the easier it is for it to access voids in a collapsed structure, however small size brings a host of other problems related to constrained resources. One of the primary constraints on small robots is limited motive power to surmount obstacles and navigate rough terrain. This thesis examines the addition of bulk motive force actuators to existing locomotion platforms and the impact of these heterogeneous actuators on conventional steering methods. The steering methods examined are those associated with skid steered vehicles and differential drive vehicles. In developing the Crabinator, a robot composed of a limbed crawler …

Scalable And Efficient Outlier Detection In Large Distributed Data Sets With Mixed-Type Attributes, Anna Koufakou

Electronic Theses and Dissertations

An important problem that appears often when analyzing data involves identifying irregular or abnormal data points called outliers. This problem broadly arises under two scenarios: when outliers are to be removed from the data before analysis, and when useful information or knowledge can be extracted by the outliers themselves. Outlier Detection in the context of the second scenario is a research field that has attracted significant attention in a broad range of useful applications. For example, in credit card transaction data, outliers might indicate potential fraud; in network traffic data, outliers might represent potential intrusion attempts. The basis of deciding …

Ground-Plane Quasicloaking For Free Space, Efthymios Kallos, Christos Argyropoulos, Yang Hao

Department of Electrical and Computer Engineering: Faculty Publications

Ground-plane cloak designs are presented, which minimize scattering of electromagnetic radiation from metallic objects in the visible spectrum. It is showed that simplified ground-plane cloaks made from only a few blocks of all-dielectric isotropic materials, either embedded in a background medium or in free space, can provide considerable cloaking performance while maintaining their broadband nature. A design which operates isolated in free space that cloaks radiation originating from a specified direction is also analyzed. These schemes should be much easier to be demonstrated experimentally compared to full designs.

Samplemaskinginellipsometerand The Like Systems Including Detection Of Substrate Backside Reflections, Martin M. Liphardt, James D. Welch, Corey L. Bungay, John A. Woollam

Department of Electrical and Computer Engineering: Faculty Publications

A system and method of preventing substrate backside reflected components in a beam of electromagnetic radiation caused to reflect from the surface of a sample in an ellipsometer or polarimeter system, involving placing a mask adjacent to the surface of the sample which allows electromagnetic radiation to access the sample over only a limited area, wherein to access the sample over only a limited area, wherein the mask can include detector elements for collecting electromagnetic radiation reflected from the sample backside.

A Possible Way To Avoid Heat Death, Nitaya Buntao, Narunchara Katemee, Vladik Kreinovich

Departmental Technical Reports (CS)

A disturbing consequence of the traditional thermodynamics is the possibility of heat death, when the Universe arrives at the state with the largest possible value of the entropy and all the processes will stop. In this paper, we show that one possible way to avoid this consequence is to consider situations in which the entropy never attains its maximum -- and thus, the heat death state is not possible. We show that such situations can have physical sense -- e.g., they naturally appear in boostrap models.