Computer Sciences Commons^™

Composite Feature-Based Face Detection Using Skin Color Modeling And Svm Classification, Swathi Rajashekar

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

This report proposes a face detection algorithm based on skin color modeling and support vector machine (SVM) classification. Said classification is based on various face features used to detect specific faces in an input color image. A YCbCr color space is used to filter the skin color pixels from the input color image. Template matching is used on the result with various window sizes of the template created from an ORL face database. The candidates obtained above, are then classified by SVM classifiers using the histogram of oriented gradients, eigen features, edge ratio, and edge statistics features.

Peer-To-Peer Simulation Of Massive Virtual Environments, James Dean Mathias

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Massively multiplayer games make up a large and growing segment of the computer game industry. One of the best known examples of these games is World of Warcraft, developed and published by Activision Blizzard. World of Warcraft boasts a subscriber base of over eleven million active subscribers, earning an estimated $1 billion dollars in 2010.

Some of the core issues for companies that publish these games are the cost of the computers, Internet bandwidth usage, and supporting technical staff. These costs easily reach hundreds of thousands of dollars each month, and in the case of World of Warcraft, millions of …

A Localized Geometric-Distortion Resilient Digital Watermarking Scheme Using Two Kinds Of Complementary Feature Points, Jiyuan Wang

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

More and more digital images are being distributed over the Internet to an evergrowing number of people for sharing, studying, or other purposes. However, most of those digital products are exposed without any protection, and such information can be easily transferred, copied, and tampered without authorization simply by using readily available digital multimedia editing software. Digital watermarking techniques have been developed as a tool to discriminate whether the original content of digital media is tampered or not. A digital watermark is embedded on digital images as an invisible message and is used to demonstrate the proof by the owner.

In …

A Novel And Effective Short Track Speed Skating Tracking System, Yuxuan Wang

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Short track speed skating lends itself to intense competitions with a strong visual impact. Thus, the sport has become increasingly popular. In fact, in 1992, short track speed skating became an official Winter Olympic sport with four events, and four more events were added in 2002. Because of the sport’s growing popularity, there is a high demand from both coaches and TV broadcasters for a means of automatically gathering competition data such as trajectories, velocities, and 2D reconstruction animation. We call this vision-based sports video analysis.

In competitive short track speed skating, multiple skaters skate together on an ice track …

Java Api-Aware Code Generation Engine: A Prototype, Chandra Sekhar Vijyapurpu

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Software reuse enhances a programmer's productivity and reduces programming errors. Improving software reuse through libraries and frameworks is a vast problem area. This thesis offers an approach to solve two sub-problems within the problem area - to identify the right library components, and to offer code snippets that use the components correctly. The Java API-Aware Code Generation Engine, or JAGE for short, is a prototype system that demonstrates the feasibility of generating semantically valid code snippets consisting of method calls to classes in the J2SDK library.

Developers often search for sample code snippets that describe how to use the …

Challenging Disciplinary Boundaries In The First Year: A New Introductory Integrated Science Course For Stem Majors, Lisa Gentile, Lester Caudill, Mirela Fetea, April L. Hill, Kathy Hoke, Barry Lawson, Ovidiu Z. Lipan, Michael Kerckhove, Carol A. Parish, Krista J. Stenger, Doug Szajda

Biology Faculty Publications

To help undergraduates make connections among disciplines so they are able to approach, evaluate, and contribute to the solutions of important global problems, our campus has been focused on interdisciplinary research and education opportunities across the science, technology, engineering, and mathematics (STEM) disciplines. This paper describes the mobilization, planning, and implementation of a first-year interdisciplinary course for STEM majors that integrates key concepts found in traditional first-semester biology, chemistry, computer science, mathematics, and physics courses. This team-taught course, Integrated Quantitative Science (IQS), is half of a first-year student’s schedule in both semesters and is composed of a double lecture and …

Impressionist Rendering Of An Animated Painting, Michela Rose

All Theses

The following thesis documents the development of a non-traditional rendering technique, that of classic impressionist painting, and its use to create an animated three-dimensional painting. Impressionist style painting has an organic feel to it, with brush strokes that remain visible in the dried paint and a light, lively color palette that seeks to capture the light in an image. Reproducing this style in a computer-generated image is no small task. For this project a CG paint method was developed, utilizing Maya Paint Effects and particles. This method was implemented with a script, saving time by automating the process as much …

The Adaptation Of 3d Video Game Production Techniques To The 2d Game Play Mechanics Of The Beat-Em-Up Genre, Donald Roeder

All Theses

In this paper, we address some of the technological issues and shortcomings that led to the recession in popularity of the Beat 'em up video game genre. In particular, we adapt current technological advances and apply them to 3D video game development to mirror the mechanics of the 2D Beat 'em up genre. We describe our assembly-line approach to 3D asset production that permits quick development of multiple and varied characters and environments. Our approach to 3D camera placement provides the same viewpoint used in the 2D game approach. We have developed various scripts to streamline the animation process. In …

Bringing Action-Adventure Gameplay To The Ipad Using The Unreal Development Kit, Jonathan Lequire

All Theses

Mobile game development is a fast growing industry that
is primarily focused on casual games with short play sessions.
In this paper, we describe an approach to the development of a
game with a focus on lengthy, more traditional gameplay. We describe
some techniques to exploit the UDK for this purpose, even
though the UDK has been used, traditionally, for the
development of shooter games. We have implemented
these techniques, and we describe our port of the game to the
the Apple iPad. The result of our work is a playable game that runs on
the iPad 2, and features …

Data Driven Approach To Multi-Agent Low Level Behavior Generation In Medical Simulations, Manan Gupta

All Theses

A multi-agent scenario generation framework is designed, implemented and evaluated in the context of a preventive medicine education virtual reality system with data collected from a sensor network at the University of Iowa Hospital. An agent in the framework is a virtual human that represents a healthcare worker. The agent is able to make certain decisions based on the information it gathers from its surroundings in the virtual environment. Distributed sensor networks are becoming very commonplace in public areas for public safety and surveillance purposes. The data collected from these sensors can be visualized in a multi-agent simulation. The various …

Onecloud: A Study Of Dynamic Networking In An Openflow Cloud, Gregory Stabler

All Theses

Cloud computing is a popular paradigm for accessing computing resources. It provides elastic, on-demand and pay-per-use models that help reduce costs and maintain a flexible infrastructure. Infrastructure as a Service (IaaS) clouds are becoming increasingly popular because users do not have to purchase the hardware for a private cloud, which significantly reduces costs. However, IaaS presents networking challenges to cloud providers because cloud users want the ability to customize the cloud to match their business needs. This requires providers to offer dynamic networking capabilities, such as dynamic IP addressing. Providers must expose a method by which users can reconfigure the …

Student Usage Patterns And Perceptions For Differentiated Lab Exercises In An Undergraduate Programming Course, Heng Ngee Mok

Research Collection School Of Computing and Information Systems

Differentiated instruction in the form of tiered take-home lab exercises was implemented for students of an undergraduate-level programming course. This paper attempts to uncover the perceptions and usage patterns of students toward these new lab exercises using a comprehensive survey. Findings reveal that these tiered exercises are generally very well received and preferred over their traditional "one size fits all" counter-parts. Although the study does not show that tiered exercises have improved proÞciency or scores, it does seem to indicate higher student engagement and motivation levels. Based on the survey results, a list of recommendations is put forth for the …

Empirical Studies On Collaboration In Software Development: A Systematic Literature Review, Christoph Treude, Margaret-Anne Storey, Jens Weber

Research Collection School Of Computing and Information Systems

Collaboration in software development is a complex is- sue that has been examined by various researchers over the last decade. This paper presents a systematic literature re- view of pertinent literature on empirical studies on collabo- rative software development. We found that a lot of progress has been achieved in the field of global or distributed de- velopment. While there are still many challenges, today's projects seem to have overcome at least some of those. Also, first steps have been made in understanding the collabora- tive aspects of requirements engineering and design. Re- search on tools for collaboration is advanced, …

Expressive Cp-Abe With Partially Hidden Access Structures, Junzuo Lai, Robert H. Deng, Yingjiu Li

Research Collection School Of Computing and Information Systems

At Eurocrypt 2005, Sahai and Waters [7] introduced the concept of attribute-based encryption (ABE). ABE enables public key based one-to-many encryption and is envisioned as a promising cryptographic primitive for realizing scalable and fine-grained access control systems. There are two kinds of ABE schemes [1], key-policy ABE (KP-ABE) and ciphertext-policy ABE (CP-ABE) schemes. This paper, our concern is on the latter.

Spalendar: Visualizing A Group's Calendar Events Over A Geographic Space On A Public Display, Chen Xiang, Sebastian Boring, Sheelagh Carpendale, Anthony Tang, Saul Greenberg

Research Collection School Of Computing and Information Systems

Portable paper calendars (i.e., day planners and organizers) have greatly influenced the design of group electronic calendars. Both use time units (hours/days/weeks/etc.) to organize visuals, with useful information (e.g., event types, locations, attendees) usually presented as - perhaps abbreviated or even hidden - text fields within those time units. The problem is that, for a group, this visual sorting of individual events into time buckets conveys only limited information about the social network of people. For example, people’s whereabouts cannot be read ‘at a glance’ but require examining the text. Our goal is to explore an alternate visualization that can …

Pamr: Passive-Aggressive Mean Reversion Strategy For Portfolio Selection, Bin Li, Peilin Zhao, Steven C. H. Hoi, Vivekanand Gopalkrishnan

Research Collection School Of Computing and Information Systems

This project proposes a novel online portfolio selection strategy named ``Passive Aggressive Mean Reversion" (PAMR). Unlike traditional trend following approaches, the proposed approach relies upon the mean reversion relation of financial markets. Equipped with online passive aggressive learning technique from machine learning, the proposed portfolio selection strategy can effectively exploit the mean reversion property of markets. By analyzing PAMR's update scheme, we find that it nicely trades off between portfolio return and volatility risk and reflects the mean reversion trading principle. We also present several variants of PAMR algorithm, including a mixture algorithm which mixes PAMR and other strategies. We …

Organizing User Search Histories, Heasoo Hwang, Hady W. Lauw, Lise Getoor, Alexandros Ntoulas

Research Collection School Of Computing and Information Systems

Users are increasingly pursuing complex task-oriented goals on the web, such as making travel arrangements, managing finances, or planning purchases. To this end, they usually break down the tasks into a few codependent steps and issue multiple queries around these steps repeatedly over long periods of time. To better support users in their long-term information quests on the web, search engines keep track of their queries and clicks while searching online. In this paper, we study the problem of organizing a user's historical queries into groups in a dynamic and automated fashion. Automatically identifying query groups is helpful for a …

Vignette: Interactive Texture Design And Manipulation With Freeform Gestures For Pen-And-Ink Illustration, Rubaiat Habib Kazi, Takeo Igarashi, Shengdong Zhao, Richard C. Davis

Research Collection School Of Computing and Information Systems

Vignette is an interactive system that facilitates texture creation in pen-and-ink illustrations. Unlike existing systems, Vignette preserves illustrators' workflow and style: users draw a fraction of a texture and use gestures to automatically fill regions with the texture. We currently support both 1D and 2D synthesis with stitching. Our system also has interactive refinement and editing capabilities to provide a higher level texture control, which helps artists achieve their desired vision. A user study with professional artists shows that Vignette makes the process of illustration more enjoyable and that first time users can create rich textures from scratch within minutes.

Method And Apparatus For Rapid Identification Of Column Heterogeneity, Bing Tian Dai, Nikolaos Koudas, Beng Chin Ooi, Divesh Srivastava, Suresh Venkatasubranmanian

Research Collection School Of Computing and Information Systems

A method and apparatus for rapid identification of column heterogeneity in databases are disclosed. For example, the method receives data associated with a column in a database. The method computes a cluster entropy for the data as a measure of data heterogeneity and then determines whether said data is heterogeneous in accordance with the cluster entropy.

Three-Dimensional Scene Reconstruction Using Multiple Microsoft Kinects, Matt Miller

Graduate Theses and Dissertations

The Microsoft Kinect represents a leap forward in the form of cheap, consumer friendly, depth sensing cameras. Through the use of the depth information as well as the accompanying RGB camera image, it becomes possible to represent the scene, what the camera sees, as a three-dimensional geometric model. In this thesis, we explore how to obtain useful data from the Kinect, and how to use it for the creation of a three-dimensional geometric model of the scene. We develop and test multiple ways of improving the depth information received from the Kinect, in order to create smoother three-dimensional models. We …

Extending The Hybridthread Smp Model For Distributed Memory Systems, Eugene Anthony Cartwright Iii

Graduate Theses and Dissertations

Memory Hierarchy is of growing importance in system design today. As Moore's Law allows system designers to include more processors within their designs, data locality becomes a priority. Traditional multiprocessor systems on chip (MPSoC) experience difficulty scaling as the quantity of processors increases. This challenge is common behavior of memory accesses in a shared memory environment and causes a decrease in memory bandwidth as processor numbers increase. In order to provide the necessary levels of scalability, the computer architecture community has sought to decentralize memory accesses by distributing memory throughout the system. Distributed memory offers greater bandwidth due to decoupled …

A Computational Pipeline For Mci Detection From Heterogeneous Brain Images, Lin Li

All Dissertations

The aging population has increased the importance of identifying and understanding mild cognitive impairment (MCI), particularly given that 6 - 15 % of MCI cases convert to Alzheimer's disease (AD) each year. The early identification of MCI has the potential for timely therapeutic interventions that would limit the advancement of
MCI to AD. However, it is difficult to identify MCI-related pathology based on visual inspection because these changes in brain morphology are subtle and spatially distributed. Therefore, reliable and automated methods to identify subtle changes in morphological
characteristics of MCI would aid in the identification and understanding of MCI. Meanwhile, …

Hybrid Query Expansion On Ontology Graph In Biomedical Information Retrieval, Liang Dong

All Dissertations

Nowadays, biomedical researchers publish thousands of papers and journals every day. Searching through biomedical literature to keep up with the state of the art is a task of increasing difficulty for many individual researchers. The continuously increasing amount of biomedical text data has resulted in high demands for an efficient and effective biomedical information retrieval (BIR) system. Though many existing information retrieval techniques can be directly applied in BIR, BIR distinguishes itself in the extensive use of biomedical terms and abbreviations which present high ambiguity.
First of all, we studied a fundamental yet simpler problem of word semantic similarity. We …

A Radio Link Quality Model And Simulation Framework For Improving The Design Of Embedded Wireless Systems, Sally Wahba

All Dissertations

Despite the increasing application of embedded wireless systems, developers face numerous challenges during the design phase of the application life cycle. One of the critical challenges is ensuring performance reliability with respect to radio link quality. Specifically, embedded links experience exaggerated link quality variation, which results in undesirable wireless performance characteristics. Unfortunately, the resulting post-deployment behaviors often necessitate network redeployment.
Another challenge is recovering from faults that commonly occur in embedded wireless systems, including node failure and state corruption. Self-stabilizing algorithms can provide recovery in the presence of such faults. These algorithms guarantee the eventual satisfaction of a given state …

Simplifying Domain Modeling And Memory Management In User-Mode Filesystems With The Nofs Framework, Joseph P. Kaylor, Konstantin Läufer, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

Transparent access to remote data sets and data arising from web services is a non-trivial challenge to application developers. This early stage work addresses this challenge with NOFS, an object-oriented framework for creating filesystems to support domain specific functionality. While an early stage work, we present a solution to solve the access problem. Our solution greatly simplifies the task of filesystems development by providing the glue code needed between a domain model and the filesystem contract. We demonstrate support for domain models that are larger than physical memory and demonstrate how the concerns of caching can be removed from user-mode …

Seafloor Characterization For Trawlability Using The Simrad Me70 Multibeam Echosounder In The Gulf Of Alaska, Jodi L. Pirtle, Thomas C. Weber, Chris Rooper, Christopher D. Wilson, Brian R. Calder

Center for Coastal and Ocean Mapping

No abstract provided.

Planning In Incomplete Domains, Jared William Robertson

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Automated planning in computer science consists of finding a sequence of actions leading from an initial state to a goal state. People who have expert knowledge of the specific problem domain work with experts in automated planning to define the domain states and actions. This knowledge engineering required to create complete and correct domain descriptions for planning problems is often very costly and difficult. Our goal with incomplete planning is to allow people to program domains without the need for planning experts.

Throughout the process of instruction of intelligent systems, teachers can often leave out whole procedures and aspects of …

Spatial Queries In Wireless Broadcast Environments [Keynote Speech], Kyriakos Mouratidis

Research Collection School Of Computing and Information Systems

Wireless data broadcasting is a promising technique for information dissemination that exploits the computational capabilities of mobile devices, in order to enhance the scalability of the system. Under this environment, the data are continuously broadcast by the server, interleaved with some indexing information for query processing. Clients may tune in the broadcast channel and process their queries locally without contacting the server. In this paper we focus on spatial queries in particular. First, we review existing methods on this topic. Next, taking shortest path computation as an example, we showcase technical challenges arising in this processing model and describe techniques …

Coercion Resistance In Authentication Responsibility Shifting, Payas Gupta, Xuhua Ding, Debin Gao

Research Collection School Of Computing and Information Systems

Responsibility shifting, a popular solution used in the event of failure of primary authentication where a human helper is involved in regaining access, is vulnerable to coercion attacks. In this work, we report our user study which investigates the helper’s emotional status when being coerced to assist in an attack. Results show that the coercion causes involuntary skin conductance fluctuation on the helper, which indicates that he/she is nervous and stressed. This response can be used to strengthen the security of the authentication system by providing coercion resistance.

Quest Hierarchy For Hyperspectral Face Recognition, David M. Ryer, Trevor J. Bihl, Kenneth W. Bauer Jr., Steven K. Rogers

Faculty Publications

A qualia exploitation of sensor technology (QUEST) motivated architecture using algorithm fusion and adaptive feedback loops for face recognition for hyperspectral imagery (HSI) is presented. QUEST seeks to develop a general purpose computational intelligence system that captures the beneficial engineering aspects of qualia-based solutions. Qualia-based approaches are constructed from subjective representations and have the ability to detect, distinguish, and characterize entities in the environment Adaptive feedback loops are implemented that enhance performance by reducing candidate subjects in the gallery and by injecting additional probe images during the matching process. The architecture presented provides a framework for exploring more advanced integration …