Digital Commons Network^™

Dbunifier: A Framework For Automated Unification Of Textual Data In Multiple Remote Data Sources, John S. Dembowski

UNF Graduate Theses and Dissertations

Over time, advances in database technology and utilization have resulted in a rapid increase in the number and types of data sources. Simultaneously, numerous methods of unifying these various data sources have emerged. Research has shown that a more comprehensive set of data attribute matches between multiple schemas can be detected by combining a number of the unification methodologies as opposed to using a single method. In this research project, a unification framework, dbUNiFier, has been proposed as an approach to allow for easy integration of both existing and future unification methods and data sources.

Census 2000 Demographic Profile Report Of The Older Adult Population In Cuyahoga, Lake, Geauga, Lorain And Medina Counties, Mark Salling, Sharon Bliss, Mcnamara, Brian

All Maxine Goodman Levin School of Urban Affairs Publications

No abstract provided.

Interactive Multimedia In The Teaching Of The Irish Language In Primary School : Design, Implementation And Development., Máire Lynch

Theses

This thesis focuses on interactive multimedia use specifically in the area of vocabulary acquisition in a second language. It addresses the language learning requirements of third class (nine year olds) language learners, in Primary school. The study is based on existing second language acquisition research, computer - assisted language learning and the design and development of educational multimedia and it delivers an interactive application based on them. The study is firmly rooted in the foundations of the Revised Curriculum for Irish Primary Schools most especially in the language teaching methods it recommends and its emphasis on the use of information …

A Memory-Based Approach To Cantonese Tone Recognition, Deryle W. Lonsdale, Michael Emonts

Faculty Publications

This paper introduces memory-based learning as a viable approach for Cantonese tone recognition. The memorybased learning algorithm employed here outperforms other documented current approaches for this problem, which is based on neural networks. Various numbers of tones and features are modeled to find the best method for feature selection and extraction. To further optimize this approach, experiments are performed to isolate the best feature weighting method, the best class voting weights method, and the best number of k-values to implement. Results and possible future work are discussed.

The Subclassing Anomaly In Compiler Evolution, Atanas Radenski

Mathematics, Physics, and Computer Science Faculty Articles and Research

Subclassing in collections of related classes may require re-implementation of otherwise valid classes just because they utilize outdated parent classes, a phenomenon that is referred to as the subclassing anomaly. The subclassing anomaly is a serious problem since it can void the benefits of code reuse altogether. This paper offers an analysis of the subclassing anomaly in an evolving object-oriented compiler. The paper also outlines a solution for the subclassing anomaly that is based on alternative code reuse mechanism, named class overriding.

A Multi-Platform Application Suite For Enhancing South Asian Language Pedagogy, Tao Bai, Christopher K. Chung, Konstantin Läufer, Daisy Rockwell, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

This interdisciplinary project explores the potential for handheld/wireless (H/W) technology in the context of language education within and beyond the classroom. Specifically, we have designed and implemented a suite of multi-platform (desktop/laptop, handheld, and browser) applications to enhance the teaching of South Asian languages such as Hindi-Urdu. Such languages are very difficult to learn, let alone write, and H/W devices (with their handwriting/drawing capabilities) can play a significant role in overcoming the learning curve. The initial application suite includes a character/word tracer, a word splitter/joiner, a smart flashcard with audio, contextual augmented stories for reading comprehension, and a poetic metronome. …

An Intelligent Early Warning System For Software Quality Improvement And Project Management, Xiaoqing Frank Liu, Gautam Kane, Monu Bambroo

Computer Science Faculty Research & Creative Works

One of the main reasons behind unfruitful software development projects is that it is often too late to correct the problems by the time they are detected. It clearly indicates the need for early warning about the potential risks. In this paper, we discuss an intelligent software early warning system based on fuzzy logic using an integrated set of software metrics. It helps to assess risks associated with being behind schedule, over budget, and poor quality in software development and maintenance from multiple perspectives. It handles incomplete, inaccurate, and imprecise information, and resolve conflicts in an uncertain environment in its …

Machine-Learned Contexts For Linguistic Operations In German Sentence Realization, Eric K. Ringger, Simon Corston-Oliver, Michael Gamon, Robert Moore

Faculty Publications

We show that it is possible to learn the contexts for linguistic operations which map a semantic representation to a surface syntactic tree in sentence realization with high accuracy. We cast the problem of learning the contexts for the linguistic operations as classification tasks, and apply straightforward machine learning techniques, such as decision tree learning. The training data consist of linguistic features extracted from syntactic and semantic representations produced by a linguistic analysis system. The target features are extracted from links to surface syntax trees. Our evidence consists of four examples from the German sentence realization system code-named Amalgam: case …

Improving Speech Recognition Learning Through Lazy Training, Tony R. Martinez, Michael E. Rimer, D. Randall Wilson

Faculty Publications

Multi-layer backpropagation, like most learning algorithms that can create complex decision surfaces, is prone to overfitting. We present a novel approach, called lazy training, for reducing the overfit in multiple-layer networks. Lazy training consistently reduces generalization error of optimized neural networks by more than half on a large OCR dataset and on several real world problems from the UCI machine learning database repository. Here, lazy training is shown to be effective in a multi-layered adaptive learning system, reducing the error of an optimized backpropagation network in a speech recognition system by 50.0% on the TIDIGITS corpus.

A Bdi Agent Software Development Process, Jeffrey M. Einhorn

Theses and Dissertations

As computer software continues to grow increasingly complex with each passing year, researchers continue to try and develop means to simplify software development. In this thesis, we propose a BDI agent software development process as the next evolution in software development. The goal of this research is to develop a process, which can be used to enable the creation of agent-based systems.

This thesis strives to present a practical software development process, which is useful to today's software engineer, by building upon current agent research and proven software engineering practices. Our BDI agent software development process is a systematic process, …

Fuzzy Product -Limit Estimators: Soft Computing In The Presence Of Very Small And Highly Censored Data Sets, Kian Lawrence Pokorny

Doctoral Dissertations

When very few data are available and a high proportion of the data is censored, accurate estimates of reliability are problematic. Standard statistical methods require a more complete data set, and with any fewer data, expert knowledge or heuristic methods are required. In the current research a computational system is developed that obtains a survival curve, point estimate, and confidence interval about the point estimate.

The system uses numerical methods to define fuzzy membership functions about each data point that quantify uncertainty due to censoring. The “fuzzy” data are then used to estimate a survival curve, and the mean survival …

Bubble World - A Novel Visual Information Retrieval Technique, Christopher L. Van Berendonck

Theses and Dissertations

With the tremendous growth of published electronic information sources in the last decade and the unprecedented reliance on this information to succeed in day-to-day operations, comes the expectation of finding the right information at the right time. Sentential interfaces are currently the only viable solution for searching through large infospheres of unstructured information, however, the simplistic nature of their interaction model and lack of cognitive amplification they can provide severely limit the performance of the interface. Visual information retrieval systems are emerging as possible candidate replacements for the more traditional interfaces, but many lack the cognitive framework to support the …

Ontology-Based Semantic Classification Of Unstructured Documents, Ching Kang Cheng, Xiao Shan Pan, Franz J. Kurfess

Computer Science and Software Engineering

As more and more knowledge and information becomes available through computers, a critical capability of systems supporting knowledge management is the classification of documents into categories that are meaningful to the user. In a step beyond the use of keywords, we developed a system that analyzes the sentences contained in unstructured or semi-structured documents, and utilizes an ontology reflecting the domain knowledge for a semantic classification of the documents. An experimental system has been implemented for the analysis of small documents in combination with a limited ontology; an extension to larger sets of documents and extended ontologies, together with an …

Filling Preposition-Based Templates To Capture Information From Medical Abstracts, Gondy Leroy, Hsinchun Chen

CGU Faculty Publications and Research

Due to the recent explosion of information in the biomedical field, it is hard for a single researcher to review the complex network involving genes, proteins, and interactions. We are currently building GeneScene, a toolkit that will assist researchers in reviewing existing literature, and report on the first phase in our development effort: extracting the relevant information from medical abstracts. We are developing a medical parser that extracts information, fills basic prepositional-based templates, and combines the templates to capture the underlying sentence logic. We tested our parser on 50 unseen abstracts and found that it extracted 246 templates with a …

Tr-2002005: Towards A Theory Of Social Software, Rohit Parikh

Computer Science Technical Reports

No abstract provided.

Tr-2002011: Corpus-Based Ambiguity Resolution Of Biomedical Terms Using Knowledge Bases And Machine Learning, Hongfang Liu

Computer Science Technical Reports

No abstract provided.

Tr-2002009: A Formal Semantics For Uml With Real-Time Constructs, Subash Shankar

Computer Science Technical Reports

No abstract provided.

Medtextus: An Ontology-Enhanced Medical Portal, Gondy Leroy, Hsinchun Chen

CGU Faculty Publications and Research

In this paper we describe MedTextus, an online medical search portal with dynamic search and browse tools. To search for information, MedTextus lets users request synonyms and related terms specifically tailored to their query. A mapping algorithm dynamically builds the query context based on the UMLS ontology and then selects thesaurus terms that fit this context. Users can add these terms to their query and meta-search five medical databases. To facilitate browsing, the search results can be reviewed as a list of documents per database, as a set of folders into which all the documents are automatically categorized based on …

An Investigation Into The Concepts And Applicability Of Agent Technologies, Anne White

Theses

The software world is one of great richness and diversity

Even though the concept of software agents date back to the days of AI (Artificial Intelligence) work (1970’s) the word “Agent” is currently in vogue in the computing press and computer science communities.

This thesis presents a review of the ongoing evolution of software agents, places agents in context within today’s software domain, and takes a closer look at the ongoing debate of what really constitutes an '"Agenf\ The numerous dimensions of classification are studied and an opinion of the attributes that an agent should encompass is put forward. Leading …

Peppering Knowledge Sources With Salt: Boosting Conceptual Content For Ontology Generation, Deryle W. Lonsdale, Yihong Ding, David W. Embley, Alan Melby

Faculty Publications

This paper describes work done to explore the common ground between two different ongoing research projects: the standardization of lexical and terminological resources, and the use of conceptual ontologies for information extraction and data integration. Specifically, this paper explores improving the generation of extraction ontologies through use of a comprehensive terminology database that has been represented in a standardized format for easy tool-based implementation. We show how, via the successful integration of these two distinct efforts, it is possible to leverage large-scale terminological and conceptual information having relationship-rich semantic resources in order to reformulate, match, and merge retrieved information of …

Adaptive Information Filtering: Concepts And Algorithms, Daniel R. Tauritz

Computer Science Faculty Research & Creative Works

Adaptive information filtering is concerned with filtering information streams in dynamic (changing) environments. The changes may occur both on the transmission side — the nature of the streams can change — and on the reception side — the interests of the user (or group of users) can change. While information filtering and information retrieval have a lot in common, this dissertation’s primary concern is with the differences. The temporal nature of information filtering necessitates more flexible document representation methods than does information retrieval where all the occurring terms are known in advance. Also, information filtering typically maintains user interest profiles …

Experience-Based Language Acquisition: A Computational Model Of Human Language Acquisition, Brian Edward Pangburn

LSU Doctoral Dissertations

Almost from the very beginning of the digital age, people have sought better ways to communicate with computers. This research investigates how computers might be enabled to understand natural language in a more humanlike way. Based, in part, on cognitive development in infants, we introduce an open computational framework for visual perception and grounded language acquisition called Experience-Based Language Acquisition (EBLA). EBLA can “watch” a series of short videos and acquire a simple language of nouns and verbs corresponding to the objects and object-object relations in those videos. Upon acquiring this protolanguage, EBLA can perform basic scene analysis to generate …

Open Source Software: A History, David Bretthauer

Published Works

In the 30 years from 1970-2000, open source software began as an assumption without a name or a clear alternative. It has evolved into a sophisticated movement which has produced some of the most stable and widely used software packages ever produced. This paper traces the evolution of three operating systems: GNU, BSD, and Linux, as well as the communities which have evolved with these systems and some of the commonly-used software packages developed using the open source model. It also discusses some of the major figures in open source software, and defines both “free software” and “open source software.”

Meeting Medical Terminology Needs: The Ontology-Enhanced Medical Concept Mapper, Gondy Leroy, Hsinchun Chen

CGU Faculty Publications and Research

This paper describes the development and testing of the Medical Concept Mapper, a tool designed to facilitate access to online medical information sources by providing users with appropriate medical search terms for their personal queries. Our system is valuable for patients whose knowledge of medical vocabularies is inadequate to find the desired information, and for medical experts who search for information outside their field of expertise. The Medical Concept Mapper maps synonyms and semantically related concepts to a user's query. The system is unique because it integrates our natural language processing tool, i.e., the Arizona (AZ) Noun Phraser, with human-created …

A Framework For Multilingual Information Processing, Steven Edward Atkin

Theses and Dissertations

Recent and (continuing) rapid increases in computing power now enable more of humankind's written communication to be represented as digital data. The most recent and obvious changes in multilingual information processing have been the introduction of larger character sets encompassing more writing systems. Yet the very richness of larger collections of characters has made the interpretation and processing of text more difficult. The many competing motivations (satisfying the needs of linguists, computer scientists, and typographers) for standardizing character sets threaten the purpose of information processing: accurate and facile manipulation of data. Existing character sets are constructed without a consistent strategy …

Dual Heuristic Programming For Fuzzy Control, George G. Lendaris, Thaddeus T. Shannon, Larry J. Schultz, Steven Hutsell, Alec Rogers

Complex Systems Faculty Publications and Presentations

Overview material for the Special Session (Tuning Fuzzy Controllers Using Adaptive Critic Based Approximate Dynamic Programming) is provided. The Dual Heuristic Programming (DHP) method of Approximate Dynamic Programming is described and used to the design a fuzzy control system. DHP and related techniques have been developed in the neurocontrol context but can be equally productive when used with fuzzy controllers or neuro-fuzzy hybrids. This technique is demonstrated by designing a temperature controller for a simple water bath system. In this example, we take advantage of the TSK model framework to initialize the tunable parameters of our plant model with reasonable …

Wright State University College Of Engineering And Computer Science Bits And Pcs Newsletter, Volume 18, Number 2, October 2001, College Of Engineering And Computer Science, Wright State University

BITs and PCs Newsletter

An eight page newsletter created by the Wright State University College of Engineering and Computer Science that addresses the current affairs of the college.

Online Bayesian Tree-Structured Transformation Of Hmms With Optimal Model Selection For Speaker Adaptation, Shaojun Wang, Yunxin Zhao

Kno.e.sis Publications

This paper presents a new recursive Bayesian learning approach for transformation parameter estimation in speaker adaptation. Our goal is to incrementally transform or adapt a set of hidden Markov model (HMM) parameters for a new speaker and gain large performance improvement from a small amount of adaptation data. By constructing a clustering tree of HMM Gaussian mixture components, the linear regression (LR) or affine transformation parameters for HMM Gaussian mixture components are dynamically searched. An online Bayesian learning technique is proposed for recursive maximum a posteriori (MAP) estimation of LR and affine transformation parameters. This technique has the advantages of …

Visual Iconic Object-Oriented Programming To Advance Computer Science Education And Novice Programming, Nancy Silva Martinez

Theses and Dissertations - UTB/UTPA

Learning how to program a computer is difficult for most people. Computer programming is a cognitively challenging, time consuming, labor intensive, and frustrating endeavor. Years of formal study and training are required to learn a programming language's world of algorithms and data structures. Instructions are coded in advance before the computer demonstrates the desired behavior. Seeing all the programming steps and instruction code is complicated. There exists a tremendous gap between the representations the human brain uses when thinking about a problem and the representations used in programming a computer. Often people are much better at dealing with specific, concrete …

Minimum Mean Square Error Spectral Peak Envelope Estimation For Automatic Vowel Classification, Jaishree Venugopal

Electrical & Computer Engineering Theses & Dissertations

Spectral feature computations continue to be a very difficult problem for accurate machine recognition of speech. In this work, which focuses on vowels, a new spectral peak envelope method for vowel classification is developed, based on a missing frequency components model of speech recognition. According to the missing frequency components model, vowel recognition depends only on the spectral (harmonic) peaks. Smoothing and interpolation of the spectra, performed in the standard cepstral analysis method commonly used in automatic speech recognition, actually loses valuable information and results in reduced recognition accuracy. The new method for feature extraction presented in this thesis is …