Digital Commons Network^™

Ontology-Based Free-Form Query Processing For The Semantic Web, Mark S. Vickers

Theses and Dissertations

With the onset of the semantic web, the problem of making semantic content effectively searchable for the general public emerges. Demanding an understanding of ontologies or familiarity with a new query language would likely frustrate semantic web users and prevent widespread success. Given this need, this thesis describes AskOntos, which is a system that uses extraction ontologies to convert conjunctive, free-form queries into structured queries for semantically annotated web pages. AskOntos then executes these structured queries and provides answers as tables of extracted values. In experiments conducted AskOntos was able to translate queries with a precision of 88% and a …

Multihierarchical Xquery For Document-Centric Xml, Ionut E. Iacob, Alex Dekhtyar

Computer Science and Software Engineering

Text has a non-hierarchical structure. Not surprisingly, searching for information in the content of a document often yields results that overlap the structure within the document. It is often of a great interest to relate such results to the embedded document structure. In this work we present an extension of the XQuery language over multihierarchical document-centric XML documents. We illustrate the benefits of using multihierarchical XQuery for text-and-structure searches in document-centric XML documents More specifically, multihierarchical XQuery allows representing relationships between textsearch results and document structure even for cases wheresuch search results overlap markup boundaries and even incases when only …

Python First: A Lab-Based Digital Introduction To Computer Science, Atanas Radenski

Mathematics, Physics, and Computer Science Faculty Articles and Research

The emphasis on Java and other commercial languages in CS1 has established the perception of computer science as a dry and technically difficult discipline among undecided students who are still seeking careers. This may not be a big problem during an enrolment boom, but in times of decreased enrolment such negative perception may have a devastating effect on computer science programs and therefore should not be ignored. We have made our CS1 course offerings more attractive to students (1) by introducing an easy to learn yet effective scripting language - Python, (2) by making all course resources available in a …

Exploiting Domain Structure For Named Entity Recognition, Jing Jiang, Chengxiang Zhai

Research Collection School Of Computing and Information Systems

Named Entity Recognition (NER) is a fundamental task in text mining and natural language understanding. Current approaches to NER (mostly based on supervised learning) perform well on domains similar to the training domain, but they tend to adapt poorly to slightly different domains. We present several strategies for exploiting the domain structure in the training data to learn a more robust named entity recognizer that can perform well on a new domain. First, we propose a simple yet effective way to automatically rank features based on their generalizabilities across domains. We then train a classifier with strong emphasis on the …

Structural Auditing Methodologies For Controlled Terminologies, Hua Min

Dissertations

Several auditing methodologies for large controlled terminologies are developed. These are applied to the Unified Medical Language System XXXX and the National Cancer Institute Thesaurus (NCIT). Structural auditing methodologies are based on the structural aspects such as IS-A hierarchy relationships groups of concepts assigned to semantic types and groups of relationships defined for concepts. Structurally uniform groups of concepts tend to be semantically uniform. Structural auditing methodologies focus on concepts with unlikely or rare configuration. These concepts have a high likelihood for errors.

One of the methodologies is based on comparing hierarchical relationships between the META and SN, two major …

Artificial Societies, Virtual Worlds, And Their Meaningful Integration, Andrew Krausnick

Computer Science Honors Theses

Artificial societies and virtual worlds are two areas of interest to modern social scientists that are distinctly separate in modern academic study, and are yet undeniably related. Artificial societies are multi-agent systems comprised of autonomous social agents, programmed with their own set of rules and behavior. While virtual worlds are occupied in large part by human controlled agents participating in a collective virtual experience and space. Within both types of virtual environments there can be found a scarcity of resources and intricate cross-entity interaction. This often results in the development and evolution of complex economic and cultural structures. In addition, …

Semantic Analytics Visualization, Leonidas Deligiannidis, Amit P. Sheth, Boanerges Aleman-Meza

Kno.e.sis Publications

In this paper we present a new tool for semantic analytics through 3D visualization called “Semantic Analytics Visualization” (SAV). It has the capability for visualizing ontologies and meta-data including annotated web-documents, images, and digital media such as audio and video clips in a synthetic three-dimensional semi-immersive environment. More importantly, SAV supports visual semantic analytics, whereby an analyst can interactively investigate complex relationships between heterogeneous information. The tool is built using Virtual Reality technology which makes SAV a highly interactive system. The backend of SAV consists of a Semantic Analytics system that supports query processing and semantic association discovery. Using a …

Mutual Knowledge And Its Impact On Virtual Team Performance, Alanah Davis, Deepak Khazanchi

Information Systems and Quantitative Analysis Faculty Proceedings & Presentations

This paper describes the notion of mutual knowledge and its potential impact on virtual team performance. Based on a review of the literature, including proponents and opponents for the concept of mutual knowledge in group interaction, we suggest that there is a gap in our understanding of what is known about mutual knowledge as it impacts team dynamics and ultimately virtual team performance. We conclude the paper by discussing the importance of mutual knowledge for virtual team performance and the research issues that need to be addressed in this domain.

A Fuzzy Approach For Detecting Anomalous Behaviour In E-Mail Traffic, Mark Jynhuey Lim, Michael Negnevitsky, Jacky Hartnett

Australian Digital Forensics Conference

This paper investigates the use of fuzzy inference for detection of abnormal changes in email traffic communication behaviour. Several communication behaviour measures and metrics are defined for extracting information on the traffic communication behaviour of email users. The information from these behaviour measures is then combined using a hierarchy of fuzzy inference systems, to provide an abnormality rating for overall changes in communication behaviour of suspect email accounts. The use of fuzzy inference is then demonstrated with a case study investigating the email traffic behaviour of a person’s email accounts from the Enron email corpus.

Dial 2004 Working Group Report On Acquisition Quality Control, William A. Barrett, Henry Baird, Frank Le Bourgeois, Xiaofan Lin, George Nagy, Steve Simske, Elisa H. Barney Smith

Faculty Publications

This report summarizes the discussions of the Working Group on Acquisition Quality at the International Workshop on Document Image Analysis for Libraries, Palo Alto, CA, 23-24 January 2004. Acquisition of the image is one of the most time intensive components of forming a digital library, and the quality of the acquisition will affect all later stages of the digital library project. The current state of the art in acquisition is analyzed. Problems and suggested improvements for image acquisition and storage formats and the special problems associated with acquisition from microfilm follows. A list of general suggestions was developed which was …

Whole Word Phonetic Displays For Speech Articulation Training, Fansheng Meng

Electrical & Computer Engineering Theses & Dissertations

The main objective of this dissertation is to investigate and develop speech recognition technologies for speech training for people with hearing impairments. During the course of this work, a computer aided speech training system for articulation speech training was also designed and implemented. The speech training system places emphasis on displays to improve children's pronunciation of isolated Consonant-Vowel-Consonant (CVC) words, with displays at both the phonetic level and whole word level. This dissertation presents two hybrid methods for combining Hidden Markov Models (HMMs) and Neural Networks (NNs) for speech recognition. The first method uses NN outputs as posterior probability estimators …

A Component Based Formal Ontology Model, A Method For Evaluating Such A Model, And The Results Of An Application Of That Method, Charles Tumitsa

Computational Modeling & Simulation Engineering Theses & Dissertations

For systems to truly communicate effectively, more than just data interchange is necessary. The systems must achieve conceptual interoperability, which implies communicating with understanding.

The LCIM (Levels of Conceptual Interoperability Model) describes a number of levels of interoperability, each of which shows systems with an increased amount of conceptual understanding of the other systems they are communicating with. The lowest levels of this model, technical and syntactic interoperability, are achieved (and there are many existing examples) via data exchange in a number of different ways. Research has shown, however, that to attain higher levels of conceptual understanding, that there must …

Mobius: An Omnidirectional Robotic Platform And Software Architecture For Network Teleoperation, Samuel Aaron Miller

Electrical & Computer Engineering Theses & Dissertations

The following thesis presents the results of a project to develop and test an omnidirectional robotic system (hardware and software) at NASA Langley Research Center's Robotics and Intelligent Machines Lab. The impetus for the project was the unique capabilities of omnidirectional systems. Some of the many potential benefits these systems have include improved material-handling capabilities in constrained environments (such as might be found in extraterrestrial manned habitats), efficient camera-based vehicle teleoperation, and simplified route planning for autonomous robot operations.

The project's focus was to design, build, and test a system that used Mecanum wheels to achieve omnidirectional motion. In addition …

Surface Realization Using A Featurized Syntactic Statistical Language Model, Thomas L. Packer

Theses and Dissertations

An important challenge in natural language surface realization is the generation of grammatical sentences from incomplete sentence plans. Realization can be broken into a two-stage process consisting of an over-generating rule-based module followed by a ranker that outputs the most probable candidate sentence based on a statistical language model. Thus far, an n-gram language model has been evaluated in this context. More sophisticated syntactic knowledge is expected to improve such a ranker. In this thesis, a new language model based on featurized functional dependency syntax was developed and evaluated. Generation accuracies and cross-entropy for the new language model did not …

Using Augmented Virtuality To Improve Human-Robot Interactions, Curtis W. Nielsen

Theses and Dissertations

Mobile robots can be used in situations and environments that are distant from an operator. In order for an operator to control a robot effectively he or she requires an understanding of the environment and situation around the robot. Since the robot is at a remote distant from the operator and cannot be directly observed, the information necessary for an operator to develop an understanding or awareness of the robot's situation comes from the user interface. The usefulness of the interface depends on the manner in which the information from the remote environment is presented. Conventional interfaces for interacting with …

Text Mining With Exploitation Of User's Background Knowledge : Discovering Novel Association Rules From Text, Xin Chen

Dissertations

The goal of text mining is to find interesting and non-trivial patterns or knowledge from unstructured documents. Both objective and subjective measures have been proposed in the literature to evaluate the interestingness of discovered patterns. However, objective measures alone are insufficient because such measures do not consider knowledge and interests of the users. Subjective measures require explicit input of user expectations which is difficult or even impossible to obtain in text mining environments.

This study proposes a user-oriented text-mining framework and applies it to the problem of discovering novel association rules from documents. The developed system, uMining, consists of two …

Bioinformatics Framework For Genotyping Microarray Data Analysis, Kai Zhang

Dissertations

Functional genomics is a flourishing science enabled by recent technological breakthroughs in high-throughput instrumentation and microarray data analysis. Genotyping microarrays establish the genotypes of DNA sequences containing single nucleotide polymorphisms (SNPs), and can help biologists probe the functions of different genes and/or construct complex gene interaction networks. The enormous amount of data from these experiments makes it infeasible to perform manual processing to obtain accurate and reliable results in daily routines. Advanced algorithms as well as an integrated software toolkit are needed to help perform reliable and fast data analysis.

The author developed a Matlab_TM based software package, called …

Using Content And Process Scaffolds For Collaborative Discourse In Asynchronous Learning Networks, Irene Wong-Bushby

Dissertations

Discourse, a form of collaborative learning, is one of the most widely used methods of teaching and learning in the online environment. Particularly, in large courses, discourse needs to be 'structured' to be effective. Historically, technology-mediated learning (TML) research has been inconclusive with often conflicting results. To address this issue, TML research needs greater breadth and depth in pedagogical grounding. The purpose of this research is to build and test an original, technology-mediated, discourse-centered model called the Asynchronous Learning Network Cognitive Discourse Model (ALNCDM) grounded in pedagogy. Cognitive discourse is defined as discourse on conceptual subject matter. The model is …

Ontological Implications Of The Levels Of Conceptual Interoperability Model, Andreas Tolk, Charles D. Turnitsa, Saikou Y. Diallo

Computational Modeling & Simulation Engineering Faculty Publications

The Levels of Conceptual Interoperability Model (LCIM) was developed to cope with the different layers of interoperation of modeling & simulation applications. It introduced technical, syntactic, semantic, pragmatic, dynamic, and conceptual layers of interoperation and showed how they are related to the ideas of integratability, interoperability, and composability. This paper will be presented in the invited session "Ontology Driven Interoperability for Agile Applications using Information Systems: Requirements and Applications for Agent Mediated Decision Support" at WMSCI 2006.

Health Information Text Characteristics, Gondy Leroy, Evren Eryilmaz '11, Benjamin T. Laroya

CGU Faculty Publications and Research

Millions of people search online for medical text, but these texts are often too complicated to understand. Readability evaluations are mostly based on surface metrics such as character or words counts and sentence syntax, but content is ignored. We compared four types of documents, easy and difficult WebMD documents, patient blogs, and patient educational material, for surface and content-based metrics. The documents differed significantly in reading grade levels and vocabulary used. WebMD pages with high readability also used terminology that was more consumer-friendly. Moreover, difficult documents are harder to understand due to their grammar and word choice and because they …

The Effect Of The Exposure To Domestic Violence On Psychological Well-Being Among American Muslim Women, Soulafa Shakhshir Massoud, Vanessa Francis Romo

Theses Digitization Project

A quantitative study that examines American Muslim women's level of exposure to domestic violence, resources available to them, and the effect of domestic violence on their psychological well-being. Data was collected from 128 Muslim women from the Islamic Center of Riverside in Southern California. The key finding of the study was a significant positive relationship between depression and the use of verbal aggression. In addition, a positive relationship was found to exist between anxiety, depression and the use of violence.

Introducing Semantics In Web Personalization: The Role Of Ontologies, Magdalini Eirinaki, Dimitrios Mavroeidis, George Tsatsaronis, Michalis Vazirgiannis

Faculty Publications

Web personalization is the process of customizing a web site to the needs of each specific user or set of users. Personalization of a web site may be performed by the provision of recommendations to the users, high-lighting/adding links, creation of index pages, etc. The web personalization systems are mainly based on the exploitation of the navigational patterns of the web site’s visitors. When a personalization system relies solely on usage-based results, however, valuable information conceptually related to what is finally recommended may be missed. The exploitation of the web pages’ semantics can considerably improve the results of web usage …

Taxaminer: Improving Taxonomy Label Quality Using Latent Semantic Indexing, Cartic Ramakrishnan, Christopher Thomas, Vipul Kashyap, Amit P. Sheth

Kno.e.sis Publications

The development of taxonomies/ontologies is a human intensive process requiring prohibitively large resource commitments in terms of time and cost. In our previous work we have identified an experimentation framework for semi-automatic taxonomy/hierarchy generation from unstructured text. In the preliminary results presented, the taxonomy/hierarchy quality was lower than we had anticipated. In this paper, we present two variations of our experimentation framework, viz. Latent semantic Indexing (LSI) for document indexing and the use of term vectors to prune labels assigned to nodes in the final taxonomy/hierarchy. Using our previous results of taxonomy/hierarchy quality as the baseline we present results that …

Semi-Supervised Conditional Random Fields For Improved Sequence Segmentation And Labeling, Feng Jiao, Shaojun Wang, Chi-Hoon Lee, Russell Greiner, Dale Schuurmans

Kno.e.sis Publications

We present a new semi-supervised training procedure for conditional random fields (CRFs) that can be used to train sequence segmentors and labelers from a combination of labeled and unlabeled training data. Our approach is based on extending the minimum entropy regularization framework to the structured prediction case, yielding a training objective that combines unlabeled conditional entropy with labeled conditional likelihood. Although the training objective is no longer concave, it can still be used to improve an initial model (e.g. obtained from supervised training) by iterative ascent. We apply our new training algorithm to the problem of identifying gene and protein …

Modeling Autonomous Agents In Military Simulations, Varol Kaptan

Electronic Theses and Dissertations

Simulation is an important tool for prediction and assessment of the behavior of complex systems and situations. The importance of simulation has increased tremendously during the last few decades, mainly because the rapid pace of development in the field of electronics has turned the computer from a costly and obscure piece of equipment to a cheap ubiquitous tool which is now an integral part of our daily lives. While such technological improvements make it easier to analyze well-understood deterministic systems, increase in speed and storage capacity alone are not enough when simulating situations where human beings and their behavior are …

Predicting Domain Specific Entities With Limited Background Knowledge, Christopher Thomas, Amit P. Sheth

Kno.e.sis Publications

This paper proposes a framework for automatic recognition of domain-specific entities from text, given limited background knowledge, e.g. in form of an ontology. The algorithm exploits several lightweight natural language processing techniques, such as tokenization and stemming, as well as statistical techniques, such as singular value decomposition (SVD) to suggest domain relatedness of unknown entities.

Position Tracking And Motion Prediction Using Fuzzy Logic, Patrick Rodjito

Honors Theses

Unlike with traditional, computationally expensive algorithms, with Fuzzy Logic (FL) one does not have to own a fast computer or very precise measuring instruments to get good results. At lower costs, FL provides a simple way to arrive at a definite conclusion based upon vague, ambiguous, imprecise, noisy, or missing input information. This is a facet of AI that appears to resemble human intuition in an important way: the ability to make quick and urgent judgment calls, on the spot, without the need to be absolutely certain of the input. The benefit brought by a low-cost solution like FL to …

A Fast Predictive Vision System For A Mobile Robot, Paul P. Benjamin, Tom Achtemichuk, Damian Lyons

CSIS Technical Reports

ADAPT’s vision system predicts what the robot expects to see and compares those predictions with actual visual data. Predictions come from a dynamic 3D world model built with Ogre3D; discrepancies become perceptual goals. The architecture implements Robot Schemas in Soar and aims to use Soar learning to improve the speed and accuracy of visual comprehension.

Model Generation For Generalized Quantifiers Via Answer Set Programming, Yuliya Lierler, Günther Görz

Computer Science Faculty Proceedings & Presentations

For the semantic evaluation of natural language sentences, in particular those containing generalized quantifiers, we subscribe to the generate and test methodology to produce models of such sentences. These models are considered as means by which the sentences can be interpreted within a natural language processing system. The goal of this paper is to demonstrate that answer set programming is a simple, efficient and particularly well suited model generation technique for this purpose, leading to a straightforward implementation.

Standards Directory: An Engineering And Technology Standards Digital Library And Information Retrieval System For The Walt Disney Company, Shawn Harrs

CCAC Theses and Dissertations

Walt Disney Company (Company) engineers and architects utilize engineering and technology standards in the design, development, and maintenance of its physical infrastructure worldwide. There was a need to improve the methods by which Company standards are organized and retrieved. While the leading commercial information brokers for engineering and technology standards provide standards search engines and online standards catalogs, these search services are poor in supporting standards seekers who have only a general understanding of their information needs because their searches only utilize a standard's document number, title, and keywords as metadata for searching.

In order to provide a tool for …