Content Based Image Retrieval For Bio-Medical Images, 2010 Missouri University of Science and Technology
Content Based Image Retrieval For Bio-Medical Images, Vikas Nahar
"Content Based Image Retrieval System (CBIR) is used to retrieve images similar to the query image. These systems have a wide range of applications in various fields. Medical subject headings, key words, and bibliographic references can be augmented with the images present within the articles to help clinicians to potentially improve the relevance of articles found in the querying process. In this research, image feature analysis and classification techniques are explored to differentiate images found in biomedical articles which have been categorized based on modality and utility. Examples of features examined in this research include: features based on different histograms ...
Contribution-Based Priority Assessment In A Web-Based Intelligent Argumentation Network For Collaborative Software Development, 2010 Missouri University of Science and Technology
Contribution-Based Priority Assessment In A Web-Based Intelligent Argumentation Network For Collaborative Software Development, Maithili Satyavolu
"Decision making is an important aspect of the collaborative software development process which usually involves complex process of conflict resolution. Stakeholders approach decision making process from multiple perspectives and their priorities play a vital role in it. The priority assessment methods used in the argumentation process so far are usually static. Priorities remain constant throughout the decision making process. In order to make the collaborative system more closely replicate real-world scenarios, this work incorporates dynamic priority assessment into a web-based collaborative system which is based on intelligent computational argumentation. It evaluates priorities dynamically for each cycle of decision process based ...
Representation And Validation Of Domain And Range Restrictions In A Relational Database Driven Ontology Maintenance System, 2010 Missouri University of Science and Technology
Representation And Validation Of Domain And Range Restrictions In A Relational Database Driven Ontology Maintenance System, Patrick Garrett. Edgett
"An ontology can be used to represent and organize the objects, properties, events, processes, and relations that embody an area of reality . These knowledge bases may be created manually (by individuals or groups), and/or automatically using software tools, such as those developed for information retrieval and data mining. Recently, the National Science Foundation funded a large collaborative development project for the semi-automated construction of an ontology of amphibian anatomy (AmphibAnat ). To satisfy the extensive community curation requirements of that project, a generic, Web-based, multi-user, relational database ontology management system (RDBOM ) was constructed, based upon a novel ...
Cloud Security Requirements Analysis And Security Policy Development Using A High-Order Object-Oriented Modeling Technique, 2010 Missouri University of Science and Technology
Cloud Security Requirements Analysis And Security Policy Development Using A High-Order Object-Oriented Modeling Technique, Kenneth Kofi Fletcher
"Security continues to be a major challenge for cloud computing, and it is one that must be addressed if cloud computing is to be fully accepted. Most technological means of securing non-cloud computing systems can be either applied directly or modified to secure a cloud; however, no integrated model-based methodology is yet available to analyze cloud security requirements and develop policy to deal with both internal and external security challenges. This work proposes just such a methodology and demonstrates its application with specific cases. Cloud assets are represented by high order object models, and misuse cases together with malactivity swimlane ...
Event Detection From Click-Through Data Via Query Clustering, 2010 Missouri University of Science and Technology
Event Detection From Click-Through Data Via Query Clustering, Prabhu Kumar Angajala
"The web is an index of real-world events and lot of knowledge can be mined from the web resources and their derivatives. Event detection is one recent research topic triggered from the domain of web data mining with the increasing popularity of search engines. In the visitor-centric approach, the click-through data generated by the web search engines is the start up resource with the intuition: often such data is event-driven. In this thesis, a retrospective algorithm is proposed to detect such real-world events from the click-through data. This approach differs from the existing work as it: (i) considers the click-through ...
Population Control In Evolutionary Algorithms, 2010 Missouri University of Science and Technology
Population Control In Evolutionary Algorithms, Jason Edward Cook
"Traditional evolutionary algorithms (EAs) are powerful robust problem solvers that have several fixed parameters which require prior specification. Having to determine good values for any of these parameters can be problematic, as the performance of EAs is generally very sensitive to these parameters, requiring expert knowledge to set optimally without extensive use of trial and error. Parameter control is a promising approach to achieving this automation and has the added potential of increasing EA performance based on both theoretical and empirical evidence that the optimal values of EA strategy parameters change during the course of executing an evolutionary run. While ...
Multi Axis Slicing For Rapid Prototyping, 2010 Missouri University of Science and Technology
Multi Axis Slicing For Rapid Prototyping, Divya Kanakanala
"With multi-axis capability, direct laser deposition process can produce a metal part without the usage of support structures. In order to fully utilize such a capability, a slicing method for multi-axis metal deposition process is discussed. Using the geometry information of adjacent layers, the slicing direction and layer thickness can be changed as needed. A hierarchy structure is designed to manage the topological information which is used to determine the slicing sequence. The parallel slicing process is studied to build hollow type structure. With such a character, the hole like feature can be deposited directly to save the required machining ...
A Pilot Study In An Application Of Text Mining To Learning System Evaluation, 2010 Missouri University of Science and Technology
A Pilot Study In An Application Of Text Mining To Learning System Evaluation, Nitsawan Katerattanakul
"Text mining concerns discovering and extracting knowledge from unstructured data. It transforms textual data into a usable, intelligible format that facilitates classifying documents, finding explicit relationships or associations between documents, and clustering documents into categories. Given a collection of survey comments evaluating the civil engineering learning system, text mining technique is applied to discover and extract knowledge from the comments. This research focuses on the study of a systematic way to apply a software tool, SAS Enterprise Miner, to the survey data. The purpose is to categorize the comments into different groups in an attempt to identify "major" concerns from ...
An Artificial Life Approach To Evolutionary Computation: From Mobile Cellular Algorithms To Artificial Ecosystems, 2010 Missouri University of Science and Technology
An Artificial Life Approach To Evolutionary Computation: From Mobile Cellular Algorithms To Artificial Ecosystems, Shivakar Vulli
"This thesis presents a new class of evolutionary algorithms called mobile cellular evolutionary algorithms (mcEAs). These algorithms are characterized by individuals moving around on a spatial population structure. As a primary objective, this thesis aims to show that by controlling the population density and mobility in mcEAs, it is possible to achieve much better control over the rate of convergence than what is already possible in existing cellular EAs. Using the observations and results from this investigation into selection pressure in mcEAs, a general architecture for developing agent-based evolutionary algorithms called Artificial Ecosystems (AES) is presented. A simple agent-based EA ...
Minimize End-To-End Delay Through Cross-Layer Optimization In Multi-Hop Wireless Sensor Networks, 2010 Missouri University of Science and Technology
Minimize End-To-End Delay Through Cross-Layer Optimization In Multi-Hop Wireless Sensor Networks, Yibo Xu
"End-to-end delay plays a very important role in wireless sensor networks. It refers to the total time taken for a single packet to be transmitted across a network from source to destination. There are many factors could affect the end-to-end delay, among them the routing path and the interference level along the path are the two basic elements that could have significant influence on the result of the end-to-end delay. This thesis presents a transmission scheduling scheme that minimizes the end-to-end delay when the node topology is given. The transmission scheduling scheme is designed based on integer linear programming and ...
Structure And Content Semantic Similarity Detection Of Extensible Markup Language Documents Using Keys, 2010 Missouri University of Science and Technology
Structure And Content Semantic Similarity Detection Of Extensible Markup Language Documents Using Keys, Waraporn Viyanon
"XML (eXtensible Mark-up Language) has become the fundamental standard for efficient data management and exchange. Due to the widespread use of XML for describing and exchanging data on the web, XML-based comparison is central issues in database management and information retrieval. In fact, although many heterogeneous XML sources have similar content, they may be described using different tag names and structures. This work proposes a series of algorithms for detection of structural and content changes among XML data. The first is an algorithm called XDoI (XML Data Integration Based on Content and Structure Similarity Using Keys) that clusters XML documents ...
Deadlock Detection And Dihomotopic Reduction Via Progress Shell Decomposition, 2010 Missouri University of Science and Technology
Deadlock Detection And Dihomotopic Reduction Via Progress Shell Decomposition, David Andrew Cape
"Deadlock detection for concurrent programs has traditionally been accomplished by symbolic methods or by search of a state transition system. This work examines an approach that uses geometric semantics involving the topological notion of dihomotopy to partition the state space into components, followed by an exhaustive search of the reduced state space. Prior work partitioned the state-space inductively; however, this work shows that a technique motivated by recursion further reduces the size of the state transition system. The reduced state space results in asymptotic improvements in overall runtime for verification. Thus, with efficient partitioning, more efficient deadlock detection and eventually ...
Computational Methods For The Discovery And Analysis Of Genes And Other Functional Dna Sequences, 2010 Missouri University of Science and Technology
Computational Methods For The Discovery And Analysis Of Genes And Other Functional Dna Sequences, Cyriac Kandoth
"The need for automating genome analysis is a result of the tremendous amount of genomic data. As of today, a high-throughput DNA sequencing machine can run millions of sequencing reactions in parallel, and it is becoming faster and cheaper to sequence the entire genome of an organism. Public databases containing genomic data are growing exponentially, and hence the rise in demand for intuitive automated methods of DNA analysis and subsequent gene identification. However, the complexity of gene organization makes automation a challenging task, and smart algorithm design and parallelization are necessary to perform accurate analyses in reasonable amounts of time ...
A Comparison Of Computer-Based Training And Traditional Classroom Training For The Sad Corporation Job Placement Team, Janice Brown Adams
Purpose: The purpose of this research study was to compare the effectiveness of computer-based training with traditional classroom training; both instructional delivery methods utilized the traditional classroom curriculum as a means of delivery for an on-the-job company-sponsored program. The JAW-SAD Human Resource Center (HRC) is a training facility for the SAD Corporation, a major international manufacturing company. The HRC is responsible for conducting continuous training and certification of SAD employees. Historically, training has been provided through conference workshops with a traditional classroom training format. The motivation and importance for this study was influenced by an administrative requirement to determine the ...
Cbtv: Visualising Case Bases For Similarity Measure Design And Selection, 2010 Technological University Dublin
Cbtv: Visualising Case Bases For Similarity Measure Design And Selection, Brian Mac Namee, Sarah Jane Delany
In CBR the design and selection of similarity measures is paramount. Selection can benefit from the use of exploratory visualisation- based techniques in parallel with techniques such as cross-validation ac- curacy comparison. In this paper we present the Case Base Topology Viewer (CBTV) which allows the application of different similarity mea- sures to a case base to be visualised so that system designers can explore the case base and the associated decision boundary space. We show, using a range of datasets and similarity measure types, how the idiosyncrasies of particular similarity measures can be illustrated and compared in CBTV allowing ...
Inside The Selection Box: Visualising Active Learning Selection Strategies, 2010 Technological University Dublin
Inside The Selection Box: Visualising Active Learning Selection Strategies, Brian Mac Namee, Rong Hu, Sarah Jane Delany
Visualisations can be used to provide developers with insights into the inner workings of interactive machine learning techniques. In active learning, an inherently interactive machine learning technique, the design of selection strategies is the key research question and this paper demonstrates how spring model based visualisations can be used to provide insight into the precise operation of various selection strategies. Using sample datasets, this paper provides detailed examples of the differences between a range of selection strategies.
Tunepal: The Traditional Musician's Toolbox, 2010 Technological University Dublin
Tunepal: The Traditional Musician's Toolbox, Bryan Duggan
In this paper we present Tunepal, a search engine and music retrieval tool for traditional musicians that runs on an iPhone/iPod Touch (2nd generation)/iPad. Tunepal connects musicians the scores and metadata of 13,290 traditional Irish, Welsh, Scottish and Breton dance tunes. These tunes are drawn from community sources, such as the website thesession.org and “standard” references including O’Neills Dance Music of Ireland and Brendan Breathneach’s Ceol Rince Na hÉireann series. Tunes can be retrieved by typing in a title or by playing a twelve second extract from the tune on a traditional instrument. Tunepal ...
Svm Based Active Learning With Exploration, 2010 Technological University Dublin
Svm Based Active Learning With Exploration, Patrick Lindstrom, Rong Hu, Sarah Jane Delany, Brian Mac Namee
No abstract provided.
Exploring The Frontier Of Uncertainty Space, 2010 Technological University Dublin
Exploring The Frontier Of Uncertainty Space, Rong Hu, Patrick Lindstrom, Sarah Jane Delany, Brian Mac Namee
We aim to investigate methods balancing exploitation with exploration in active learning to improve the performance of uncertainty sampling. Two exploration guided sampling methods are compared to uncertainty sampling on various real-life datasets from the 2010 Active Learning Challenge. Our initial experiments seems to indicate that combining exploration with uncertainty sampling improves performance on certain datasets but not all.
An Empirically-Based Model For Perspective Selection In Route-Finding Dialogues, 2010 Technological University Dublin
An Empirically-Based Model For Perspective Selection In Route-Finding Dialogues, Robert Ross, Kavita E. Thomas
In this work we aim to computationally model the extent to which certain empirical factors affect spatial perspective selection as used in route-finding dialogues. In such dialogues, both interlocutors need to adopt a spatial perspective in which to describe movement direction. In map-based tasks such as the one we are concerned with, two perspective choices are typically available, i.e., route perspective, where projective terms are defined with respect to the perspective of the route follower themselves, e.g., ``go to your right'', or survey perspective, where projective terms are defined with respect to a global or allocentric perspective, e ...