Digital Commons Network^™

Object Tracking And Activity Recognition In Video Acquired Using Mobile Cameras, Alper Yilmaz

Electronic Theses and Dissertations

Due to increasing demand on deployable surveillance systems in recent years, object tracking and activity recognition are receiving considerable attention in the research community. This thesis contributes to both the tracking and the activity recognition components of a surveillance system. In particular, for the tracking component, we propose two different approaches for tracking objects in video acquired by mobile cameras, each of which uses a different object shape representation. The first approach tracks the centroids of the objects in Forward Looking Infrared Imagery (FLIR) and is suitable for tracking objects that appear small in airborne video. The second approach tracks …

Interactivity And User-Heterogeneity In On Demand Broadcast Video, Mounir Tantaoui El Araki

Electronic Theses and Dissertations

Video-On-Demand (VOD) has appeared as an important technology for many multimedia applications such as news on demand, digital libraries, home entertainment, and distance learning. In its simplest form, delivery of a video stream requires a dedicated channel for each video session. This scheme is very expensive and non-scalable. To preserve server bandwidth, many users can share a channel using multicast. Two types of multicast have been considered. In a non-periodic multicast setting, users make video requests to the server; and it serves them according to some scheduling policy. In a periodic broadcast environment, the server does not wait for service …

Automatic Annotation Of Database Images For Query-By-Concept, Nualsawat Hiransakolwong

Electronic Theses and Dissertations

As digital images become ubiquitous in many applications, the need for efficient and effective retrieval techniques is more demanding than ever. Query by Example (QBE) and Query by Concept (QBC) are among the most popular query models. The former model accepts example images as queries and searches for similar ones based on low-level features such as colors and textures. The latter model allows queries to be expressed in the form of high-level semantics or concept words, such as "boat" or "car," and finds images that match the specified concepts. Recent research has focused on the connections between these two models …

Toward Building A Social Robot With An Emotion-Based Internal Control, Andreas Marpaung

Electronic Theses and Dissertations

In this thesis, we aim at modeling some aspects of the functional role of emotions on an autonomous embodied agent. We begin by describing our robotic prototype, Cherry--a robot with the task of being a tour guide and an office assistant for the Computer Science Department at the University of Central Florida. Cherry did not have a formal emotion representation of internal states, but did have the ability to express emotions through her multimodal interface. The thesis presents the results of a survey we performed via our social informatics approach where we found that: (1) the idea of having emotions …

Image Based View Synthesis, Jiangjian Xiao

Electronic Theses and Dissertations

This dissertation deals with the image-based approach to synthesize a virtual scene using sparse images or a video sequence without the use of 3D models. In our scenario, a real dynamic or static scene is captured by a set of un-calibrated images from different viewpoints. After automatically recovering the geometric transformations between these images, a series of photo-realistic virtual views can be rendered and a virtual environment covered by these several static cameras can be synthesized. This image-based approach has applications in object recognition, object transfer, video synthesis and video compression. In this dissertation, I have contributed to several sub-problems …

Designing And Implementing A User-Focused Web-Based Database System, Rachel Noiseux

Honors Theses

The goal of this project was to combine two different fields within computer science to produce a system that would be beneficial to a wide variety of people. The first area, user-centered design, studies how users interact with an interface and the motivation behind the decisions they make when interacting with the interface. The second area, databases, explores different techniques for storing and retrieving large amounts of data.

An Implicit Surface Modeling Technique Based On A Modular Neural Network Architecture, Manuel Carcenac

Turkish Journal of Electrical Engineering and Computer Sciences

Independently from artificial intelligence applications, an artificial neural network can be viewed as a powerful tool for function reconstruction. Previous papers used this property to model an implicit surface out of some control points by reconstructing its underlying scalar field. Such an approach requests the neural network to memorize the control points, which has turned problematic for complex surfaces. In our paper, we show that this problem can be efficiently tackled by adapting the architecture of the neural network to the features compounding the surface: by learning first these features independently and then blending them gradually together, our modular architecture …

Real-Time Classification Algorithm For Recognition Of Machine Operating Modes By Use Of Self-Organizing Maps, Gancho Vachkov, Yuhiko Kiyota, Koji Komatsu, Satoshi Fujii

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper a new algorithm for classification and real-time recognition of different a-priorily assumed operating modes for construction machines is proposed. This algorithm utilizes the effectiveness of the Self-Organizing Maps (SOM) for creating the so called Separation Models, that are able to distinguish each operating mode separately. After training, these models are used in a real-time procedure, which calculates at each sampling time the minimal Euclidean distances from the current data point to a certain node of each SOM. Then the separation model (represented by a respective SOM) that has the least minimal distance to this data point defines …

Algebraic Semantics For Coalgebraic Logics, Clemens Kupke, Alexander Kurz, Dirk Pattinson

Engineering Faculty Articles and Research

With coalgebras usually being defined in terms of an endofunctor T on sets, this paper shows that modal logics for T-coalgebras can be naturally described as functors L on boolean algebras. Building on this idea, we study soundness, completeness and expressiveness of coalgebraic logics from the perspective of duality theory. That is, given a logic L for coalgebras of an endofunctor T, we construct an endofunctor L such that L-algebras provide a sound and complete (algebraic) semantics of the logic. We show that if L is dual to T, then soundness and completeness of the algebraic semantics immediately yield the …

Preface, Thomas Hildebrandt, Alexander Kurz

Engineering Faculty Articles and Research

No abstract provided.

Metadata And Buckets In The Smart Object, Dumb Archive (Soda) Model, Michael L. Nelson, Kurt Maly, Delwin R. Croom Jr., Steven W. Robbins

Computer Science Faculty Publications

We present the Smart Object, Dumb Archive (SODA) model for digital libraries (DLs), and discuss the role of metadata in SODA. The premise of the SODA model is to "push down" many of the functionalities generally associated with archives into the data objects themselves. Thus the data objects become "smarter", and the archives "dumber". In the SODA model, archives become primarily set managers, and the objects themselves negotiate and handle presentation, enforce terms and conditions, and perform data content management. Buckets are our implementation of smart objects, and da is our reference implementation for dumb archives. We also present our …

Xml In Computational Science, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

In this first article in a series about XML in computational science, I present some background and lightweight examples of XML usage, describe some XML component frameworksalong with their purpose and applicability to computational science, and discuss some technical obstacles to overcome for the language to be taken seriously in computational science.

Integrating Experiments And Simulators Into A Distributed E-Learning Environment, Frank Koehler

Theses

New information and communication technologies have emerged in the last few years which have made an impact on learning at all levels. At universities, the spectrum of learning support ranges from enriching traditional lectures and courses with multi- media elements to complete web-based interactive learning environments. A special aspect based on the new media technologies is learning within model worlds by use of simulations or real-life experiments. There are normally no links between these applications and the learning content, so it is impossible to tap the full potential of these applications. Research activities in the area of e-learning underline the …

A Novel Approach To Information Security Risk Analysis, Bilge Karabacak, Ibrahim Sogukpinar

All Faculty and Staff Scholarship

A number of risk analysis methods became obsolete because of the profound changes in information technologies. Revolutionary changes in information technologies have converted many risk analysis methods into inconsistent, long lasting and expensive instruments. Therefore, risk analysis methods should be adaptively modified or redesigned according to the changes in information technologies, so that they meet the information security requirements of the organizations. By taking these requirements into consideration, a survey based approach is proposed for analyzing the risks of information technologies. This new method is named as Risk Analysis Method for Information Security (RAMIS). A case study is conducted to …

Parametric Classification In Domains Of Characters, Numerals, Punctuation, Typefaces And Image Qualities, Osama Ahmed Khan

Theses and Dissertations - UTB/UTPA

This thesis contributes to the Optical Font Recognition problem (OFR), by developing a classifier system to differentiate ten typefaces using a single English character ‘e’. First, features which need to be used in the classifier system are carefully selected after a thorough typographical study of global font features and previous related experiments. These features have been modeled by multivariate normal laws in order to use parameter estimation in learning. Then, the classifier system is built up on six independent schemes, each performing typeface classification using a different method. The results have shown a remarkable performance in the field of font …

An Analysis Of Case-Base Editing In A Spam Filtering Systems, Sarah Jane Delany, Padraig Cunningham

Conference papers

Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work well. Case-Based Reasoning (CBR) is a lazy approach to machine learning where induction is delayed to run time. This means that the case base can be updated continuously and new training data is immediately available to the induction process. In this paper we present a detailed description of such a system called ECUE and evaluate design decisions concerning the case representation. We compare its performance with an alternative system that uses …

Openmvc: A Non-Proprietary Component-Based Framework For Web Applications, Ronan Barrett, Sarah Jane Delany

Conference papers

No abstract provided.

Digital Mountain: From Granite Archive To Global Access, William A. Barrett, Luke A. D. Hutchison, Douglas J. Kennard, Heath E. Nielson, Dallan Quass

Faculty Publications

Large-scale, multi-terabyte digital libraries are becoming feasible due to decreasing costs of storage, CPU, and bandwidth. However, costs associated with preparing content for input into the library remain high due to the amount of human labor required. This paper describes the Digital Microfilm Pipeline – a sequence of image processing operations used to populate a large-scale digital library from a “mountain” of microfilm and reduce the human labor involved. Essential parts of the pipeline include algorithms for document zoning and labeling, consensus-based template creation, reversal of geometric transformations and Just-In-Time Browsing, an interactive technique for progressive access of image content …

Fast Registration Of Tabular Document Images Using The Fourier-Mellin Transform, William A. Barrett, Luke A. D. Hutchison

Faculty Publications

A new technique is presented for quickly identifying global affine transformations applied to tabular document images, and to correct for those transformations. This technique, based on the Fourier-Mellin transform, is used to register (align) a set of tabular documents to each other. Each component of the affine transform is handled separately, which dramatically reduces the total parameter space of the problem. This method is robust, and deals with all components of the affine transform in a uniform way. The Fourier-Mellin transform is also extended to handle shear, which can approximate a small amount of perspective distortion, and to not need …

[Introduction To] Schaum's Outline Of Programming With Java, John R. Hubbard

Bookshelf

Tough Test Questions? Missed Lectures? Not Enough Time?

Fortunately for you, there's Schaum's Outlines. More than 40 million students have trusted Schaum's to help them succeed in the classroom and on exams. Schaum's is the key to faster learning and higher grades in every subject. Each Outline presents all the essential course information in an easy-to-follow, topic-by-topic format. You also get hundreds of examples, solved problems, and practice exercises to test your skills.

This Schaum's Outline gives you

• Practice problems with full explanations that reinforce knowledge
• Coverage of the most up-to-date developments in your course field
• In-depth review of practices …

Bidirectional Lao* Algorithm (A Faster Approach To Solve Goal-Directed Mdps), Venkata Deepti Kiran Bhuma

University of Kentucky Master's Theses

Uncertainty is a feature of many AI applications. While there are polynomial-time algorithms for planning in stochastic systems, planning is still slow, in part because most algorithms plan for all eventualities. Algorithms such as LAO* are able to find good or optimal policies more quickly when the starting state of the system is known.

In this thesis we present an extension to LAO*, called BLAO*. BLAO* is an extension of the LAO* algorithm to a bidirectional search. We show that BLAO* finds optimal or ^_E-optimal solutions for goal-directed MDPs without necessarily evaluating the entire state space. BLAO* …

Optimal Design Of Engineering Systems Using Mpi-Enabled Genetic Algorithm, S. D. Rajan, D. T. Nguyen, M. D. Deshpande, L. Harrell

Civil & Environmental Engineering Faculty Publications

The focus of this paper is on the development and implementation of a genetic algorithm (GA)-based software system using message passing interface (MPI) protocol and library. A customized form of simple GA used in previous research [1-4] is parallelized. This MPI-enabled version is used to find the solution to finite element based design optimization problems. Results show that an almost linear speedup is obtained on homogenous hardware cluster and, with proper reworking of the software, on heterogeneous hardware cluster.

Virtual Personal Assistants In A Pervasive Computing World, John F. Bradley, Brian R. Duffy, Gregory O'Hare, Alan Martin, Bianca Schoen-Phelan

Conference papers

Computing paradigms are constantly evolving-from mainframe to desktop, and on to ubiquitous computing. With a wide variety of devices, each with varying constraints, it would be quite difficult to develop services that would operate in a uniform manner across all platforms. With this in mind we offer an agent based solution. Agent attributes of autonomy, adaptability and mobility make them highly suitable for use in pervasive computing environments. Agent Chameleons illustrates a framework for Virtual Personal Assistants (VPA) for the information age. This paper briefly outlines some of the technologies and concepts that underpin the functionality of a VPA.

Java-Based Digital Library Portal For Geography Education, Zehua Liu, Hai Yuan, Ee Peng Lim, Ming Yin, Dion Hoe-Lian Goh, Yin-Leng Theng, Wee-Keong Ng

Research Collection School Of Computing and Information Systems

G-Portal is a Java-based digital library system for managing the metadata of geography related resources on the Web. In addition to providing a flexible repository subsystem to accommodate metadata of different formats using XML and XML Schemas, G-Portal organizes metadata into projects and layers, and supports an integrated and synchronized classification and map-based interfaces over the stored metadata. G-Portal also includes a classification subsystem that creates category structures and classifies metadata resources into categories based on user-specified classification schemas. Furthermore, G-Portal users can annotate resources and make their annotations available to others. In this paper, we describe the design and …

Viscors: A Visual-Content Recommender For The Mobile Web, Chan Young Kim, Jae Kyu Lee, Yoon Ho Cho, Deok Hwan Kim

Research Collection School Of Computing and Information Systems

Current search methods for mobile-Web content can be frustrating to use. To shorten searches for cell phone wallpaper images, VISCORS combines collaborative filtering with content-based image retrieval. An increasing selection of content is becoming available in the mobile-Web environment, where users navigate the Web using wireless devices such as cell phones and PDAs. The fast growth and excellent prospects of the mobile-Web content market have attracted many content providers.

Supply Chains Integration: Architecture And Enabling Technologies, Keng Siau, Yuhong Tian

Research Collection School Of Computing and Information Systems

An effective and efficient supply chain is vital to the competitiveness and the survival of an organization. With the emergence of the e-business era, supply chain systems need to be able to extend beyond the traditional boundaries. This paper proposes integrated supply chain architecture (SCA) that combines the benefits of Enterprise Resource Planning (ERP) and the various supply chain applications. Some necessary criteria for an integrated supply chain include completeness, security, flexibility, scalability, and interoperability. The enabling technologies for such a supply chain system include XML, DCOM, CORBA, SOAP, Net, and Semantic Web. Wireless and mobile technologies could further extend …

Logistics Outsourcing And 3pl Challenges, Michelle L. F. Cheong

Research Collection School Of Computing and Information Systems

Logistics has been an important part of every economy and every business entity. The worldwide trend in globalization has led to many companies outsourcing their logistics function to Third-Party Logistics (3PL) companies, so as to focus on their core competencies. This paper attempts to broadly identify and categorize the challenges faced by 3PL companies and discover potential gaps for future research. Some of the challenges will be related with the experience and information collected from interviews with two 3PL companies.

Integrating Perception, Language And Problem Solving In A Cognitive Agent For A Mobile Robot., Deryle W. Lonsdale, D. Paul Benjamin, Damian M. Lyons

Faculty Publications

We are implementing a unified cognitive architecture for a mobile robot. Our goal is to endow a robot agent with the full range of cognitive abilities, including perception, use of natural language, learning and the ability to solve complex problems. The perspective of this work is that an architecture based on a unified theory of robot cognition has the best chance of attaining human-level performance.

This agent architecture is an integration of three theories: a theory of cognition embodied in the Soar system, the RS formal model of sensorimotor activity and an algebraic theory of decomposition and reformulation.

These three …

An Agent-Based Approach To Adaptive Navigational Support Within 3d-Environments, Bianca Schoen-Phelan, Gregory O'Hare, Brian Duffy, Alan Martin

Conference papers

his paper investigates mechanisms and approaches to assisting user navigation and exploration within 3-dimensional worlds. Specifically it advocates the deployment of an agentbased approach to dynamic system assistance and intervention. A performance equation is presented in a basic and an extended version, which is used to activate system interventions and to evaluate user performances online and offline. The measure is derived via a light-weight computationally inexpensive masking approach. We describe some navigation experiments and the results of navigational intervention via the damping of the sensitivity of the navigational keys. Interestingly the navigational assistance does not yield improvements in the subjects’ …

Discrete-Time Neural Network Output Feedback Control Of Nonlinear Systems In Non-Strict Feedback Form, P. He, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

An adaptive neural network (NN) -Based output feedback controller is proposed to deliver a desired tracking performance for a class of discrete-time nonlinear systems, which is represented in non-strict feedback form. the NN backstepping approach is utilized to design the adaptive output feedback controller consisting of 1) a NN observer to estimate the system states with the input-output data, and 2) two NNs to generate the virtual and actual control inputs, respectively. the non-causal problem in the discrete time backstepping design is avoided by using the universal NN approximator. the persistence excitation (PE) condition is relaxed both in the NN …