Computer Sciences Commons^™

Frequency Based Incremental Attribute Selection For Gre., John D. Kelleher

Conference papers

The DIT system uses an incremental greedy search to generate descriptions, similar to the incremental algorithm described in (Dale and Reiter, 1995). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first). Where two or more attributes have the same frequency of occurrence the first attribute found with that frequency is selected. The type attribute is always included in the description. …

Computer Simulation And Modeling Of Physical And Biological Processes Using Partial Differential Equations, Wensheng Shen

University of Kentucky Doctoral Dissertations

Scientific research in areas of physics, chemistry, and biology traditionally depends purely on experimental and theoretical methods. Recently numerical simulation is emerging as the third way of science discovery beyond the experimental and theoretical approaches. This work describes some general procedures in numerical computation, and presents several applications of numerical modeling in bioheat transfer and biomechanics, jet diffusion flame, and bio-molecular interactions of proteins in blood circulation.

A three-dimensional (3D) multilayer model based on the skin physical structure is developed to investigate the transient thermal response of human skin subject to external heating. The temperature distribution of the skin is …

Users' Perspectives And Attitudes Towards Web Application Security, Leonard Ticualu

Theses : Honours

The Internet has become an integral part of the society in many parts of the world. However, as the Internet becoming more important and useful, the problems with Web security have also increased. More people today have experienced Web security threats such as viruses, spyware, keyloggers, and phishing; and a not insignificant number have encountered financial fraud because of the online activities they conducted. This research investigated the security concerns and level of awareness of users in regards to the use of web applications, by identifying users' concerns of web applications, examining the relationship of users' technical knowledge and users' …

An Evaluation Of Omg Sysml 1.0a Standard Conformance Between Modelling Tools, Andrew James Campbell

Theses : Honours

The SysML is a recent introduction to modelling languages for the systems engineering domain. Modelling tools are offering support for its notation. Studies related to the UML have indicated that modelling tools lack compliance to the UML language. This issue may apply equally to the SysML and the aim of this research is to investigate that language compliance issue. The first phase of this research is concerned with the compliance of current modelling tools to the SysML l.0a Final Adopted Specification (PAS). It consists of a comparative evaluation of candidate tools based on an ideal framework derived from the language …

A Comparison Of Edge Detection Methods For Segmentation Of Skin Lesions In Mobile-Phone-Quality Images, Khanh Linh Hua

Theses : Honours

The world is faced with a rapidly increasing number of skin cancers every year. Melanoma is the most deadly type of skin cancer though it can be treated if it has been detected at an early stage. However, there is a shortage of dermatologists in rural areas. The increasing number of camera phones, together with improved coverage in rural areas gives some potential for tele-dermatology, whereby people with no local access to a dermatologist can send images of suspicious skin lesions to an expert for assessment. Merely relaying images to a human expert solves only part of the problem, there …

Using Machine Learning Techniques To Create Ai Controlled Players For Video Games, Bhuman Soni

Theses : Honours

This study aims to achieve higher replay and entertainment value in a game through human-like AI behaviour in computer controlled characters called bats. In order to achieve that, an artificial intelligence system capable of learning from observation of human player play was developed. The artificial intelligence system makes use of machine learning capabilities to control the state change mechanism of the bot. The implemented system was tested by an audience of gamers and compared against bats controlled by static scripts. The data collected was focused on qualitative aspects of replay and entertainment value of the game and subjected to quantitative …

Sub Space: Enhancing The Spatial Awareness Of Trainee Submariners Using 3d Simulation Environments, Michael Garrett

Theses : Honours

Rapid advancements in computer technology have facilitated the development of practical and economically feasible three dimensional (3D) computer-generated simulation environments that have been utilized for training in a number of different fields. In particular, this development has been heavily influenced by innovations within the gaming industry, where First Person Shooter (FPS) games are often considered to be on the cutting edge of gaming technology in terms of visual fidelity and performance. 3D simulation environments built upon FPS gaming technologies can be used to realistically represent real world places, while also providing a dynamic and responsive experiential based learning environment for …

An Investigation Into The Application Of Data Mining Techniques To Characterize Agricultural Soil Profiles, Rowan J. Maddern

Theses : Honours

The advances in computing and information storage have provided vast amounts of data. The challenge has been to extract knowledge from this raw data; this has led to new methods and techniques such as data mining that can bridge the knowledge gap. The research aims to use these new data mining techniques and apply them to a soil science database to establish if meaningful relationships can be found. A data set extracted from the WA Department of Agriculture and Food (DAFW A) soils database has been used to conduct this research. The database contains measurements of soil profile data from …

In-Between Theory And Practice: Dialogues In Design Research, Arianna Bassoli, Johanna Brewer, Karen Martin

Computer Science: Faculty Publications

Why Wait? and Betwixt are two of the workshops we have recently run on the theme of in-between-ness. The approach of social computing, where researchers work to understand how the socio-cultural aspects of human life relate to the design of new technologies, was the starting point for our investigation. By observing actual instances of in-between-ness in context we explored how design activities can be used as an opportunity to discuss and take positions on a specific theme, and as a space for narrowing the gap in design research between theoretical and practical thinking.

Knowledge-Based Methods For Automatic Extraction Of Domain-Specific Ontologies, Janardhana R. Punuru

LSU Doctoral Dissertations

Semantic web technology aims at developing methodologies for representing large amount of knowledge in web accessible form. The semantics of knowledge should be easy to interpret and understand by computer programs, so that sharing and utilizing knowledge across the Web would be possible. Domain specific ontologies form the basis for knowledge representation in the semantic web. Research on automated development of ontologies from texts has become increasingly important because manual construction of ontologies is labor intensive and costly, and, at the same time, large amount of texts for individual domains is already available in electronic form. However, automatic extraction of …

Content-Based Image Retrieval Using Associative Memories, Arun D. Kulkarni

Computer Science Faculty Publications and Presentations

The rapid growth in the number of large-scale repositories has brought the need for efficient and effective content-based image retrieval (CBIR) systems. The state of the art in the CBIR systems is to search images in database that are “close” to the query image using some similarity measure. The current CBIR systems capture image features that represent properties such as color, texture, and/or shape of the objects in the query image and try to retrieve images from the database with similar features. In this paper, we propose a new architecture for a CBIR system. We try to mimic the human …

Elementary Fuzzy Matrix Theory And Fuzzy Models For Social Scientists, Florentin Smarandache, W.B. Vasantha Kandasamy, K. Ilanthenral

Branch Mathematics and Statistics Faculty and Staff Publications

This book aims to assist social scientists to analyze their problems using fuzzy models. The basic and essential fuzzy matrix theory is given. The book does not promise to give the complete properties of basic fuzzy theory or basic fuzzy matrices. Instead, the authors have only tried to give those essential basically needed to develop the fuzzy model. The authors do not present elaborate mathematical theories to work with fuzzy matrices; instead they have given only the needed properties by way of examples. The authors feel that the book should mainly help social scientists who are interested in finding out …

Factors Influencing Speed Of Cancer Diagnosis In Rural Wa, Moyez Jiwa, Georgia Halkett, Samar Aoun, Hayley Arnet, Marthe Smith, Megan Pilkington, Cheryl Mcmullen

Research outputs pre 2011

Introduction: The speed of diagnosis impacts on prognosis and survival in all types of cancer. In most cases survival and prognosis are significantly worse in rural and remote Australian populations who have less access to diagnostic and therapeutic services than metropolitan communities in this country. Research suggests that in general delays in diagnosis were a factor of misdiagnosis, the confounding effect of existing conditions and delayed or misleading investigation of symptoms. The aim of this study is to further explore the factors that impact on the speed of diagnosis in rural Western Australia with direct reference to General Practitioners (GPs) …

Using Pareto Fronts To Evaluate Polyp Detection Algorithms For Ct Colonography, Adam Huang, Jiang Li, Ronald M. Summers, Nicholas Petrick, Amy K. Hara

Electrical & Computer Engineering Faculty Publications

We evaluate and improve an existing curvature-based region growing algorithm for colonic polyp detection for our CT colonography (CTC) computer-aided detection (CAD) system by using Pareto fronts. The performance of a polyp detection algorithm involves two conflicting objectives, minimizing both false negative (FN) and false positive (FP) detection rates. This problem does not produce a single optimal solution but a set of solutions known as a Pareto front. Any solution in a Pareto front can only outperform other solutions in one of the two competing objectives. Using evolutionary algorithms to find the Pareto fronts for multi-objective optimization problems has been …

A Browser-Side Solution For Detection And Prevention Of Cross-Site Request Forgery Attacks, Mary C. Henthorn

Theses and Dissertations

The security of web-based applications concerns everyone who conducts business online. Cross-site request forgeries (CSRF) subject users, as well as applications, to attack. Cloaked by the standardized request and response interchange between browsers and web-based applications, an attacker can employ the browser as an agent to slip data into the transaction. CSRF exploits ride on session authentication and authorization, stealthily bypassing the security measures intended to form bonds of trust between the user and the application. Until CSRF protection is incorporated in all web-based applications, wary users may look for client-side protection. This thesis offers an original Firefox browser extension …

Near Optimal Output-Feedback Control Of Nonlinear Discrete-Time Systems In Nonstrict Feedback Form With Application To Engines, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier

Electrical and Computer Engineering Faculty Research & Creative Works

A novel reinforcement-learning based output-adaptive neural network (NN) controller, also referred as the adaptive-critic NN controller, is developed to track a desired trajectory for a class of complex nonlinear discrete-time systems in the presence of bounded and unknown disturbances. The controller includes an observer for estimating states and the outputs, critic, and two action NNs for generating virtual, and actual control inputs. The critic approximates certain strategic utility function and the action NNs are used to minimize both the strategic utility function and their outputs. All NN weights adapt online towards minimization of a performance index, utilizing gradient-descent based rule. …

Reinforcement Learning Neural-Network-Based Controller For Nonlinear Discrete-Time Systems With Input Constraints, Pingan He, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

A novel adaptive-critic-based neural network (NN) controller in discrete time is designed to deliver a desired tracking performance for a class of nonlinear systems in the presence of actuator constraints. The constraints of the actuator are treated in the controller design as the saturation nonlinearity. The adaptive critic NN controller architecture based on state feedback includes two NNs: the critic NN is used to approximate the "strategic" utility function, whereas the action NN is employed to minimize both the strategic utility function and the unknown nonlinear dynamic estimation errors. The critic and action NN weight updates are derived by minimizing …

Adaptive Power Control Protocol With Hardware Implementation For Wireless Sensor And Rfid Reader Networks, Kainan Cha, Jagannathan Sarangapani, David Pommerenke

Electrical and Computer Engineering Faculty Research & Creative Works

The development and deployment of radio frequency identification (RFID) systems render a novel distributed sensor network which enhances visibility into manufacturing processes. In RFID systems, the detection range and read rates will suffer from interference among high-power reading devices. This problem grows severely and degrades system performance in dense RFID networks. Consequently, medium access protocols (MAC) protocols are needed for such networks to assess and provide access to the channel so that tags can be read accurately. In this paper, we investigate a suite of feasible power control schemes to ensure overall coverage area of the system while maintaining a …

Forecasting Consumer Adoption Of Technological Innovation: Choosing The Appropriate Diffusion Models For New Products And Services Before Launch, Roger Calantone, Lance Gentry

Business and Information Technology Faculty Research & Creative Works

There are many good articles on various forecasting models. There is consensus that no single diffusion model is best for every situation. Experts in the field have asked for studies to provide empirical-based guidelines for recommending when various models should be used. This research investigates multiple diffusion models and provides recommendations for which diffusion models are appropriate for radical and really new products and services before the launch of the innovation.

A Multiple-Copy Scheme For Multi-Channel Stop-And-Wait Harq, Yucheng Shih

Master's Projects

HARQ (Hybrid Automatic Repeat Request) combines ARQ (Automatic Repeat Request) with FEC (Forward Error Correction) to provide a reliable way to ensure that data are received correctly and in sequence. A multiple-copy HARQ scheme is proposed for WiMAX (Worldwide Interoperability for Microwave Access) to reduce the waiting time of erroneously received data in the receivers’ buffer. In this project, the performances of WiMAX multi-channel stop-and-wait HARQ scheme are compared with that of the proposed multiple-copy HARQ scheme. The multiple-copy HARQ can send the same copy of a data burst on contiguous channels during noisy channel conditions so that the required …

A Hierarchical Trusted Third-Party System For Secure Peer-To-Peer Transactions, Khoi Nguyen

Master's Projects

A peer-to-peer (P2P) network is a distributed network of peer computers loosely connected through the Internet. Transactions in a P2P network are often conducted on a no-security basis. Moreover, peer anonymity is often highly desirable, which makes security even more difficult to achieve. In most cases, a peer executes a transaction solely based on the faith that the other peer plays by the rules. Here we propose a hierarchical Trusted Third-Party (TTP) system that facilitates secure transactions between peers in an existing P2P network. This system is designed to provide mutual authentication by using public key cryptography for peers to …

Case Studies In Proof Checking, Robert Kam

Master's Projects

The aim of computer proof checking is not to find proofs, but to verify them. This is different from automated deduction, which is the use of computers to find proofs that humans have not devised first. Currently, checking a proof by computer is done by taking a known mathematical proof and entering it into the special language recognized by a proof verifier program, and then running the verifier to hopefully obtain no errors. Of course, if the proof checker approves the proof, there are considerations of whether or not the proof checker is correct, and this has been complicated by …

Emotional And Domain Concept Enhancements To Alicebot, Alvin Cho

Master's Projects

Extensive research and development have been done in the area of human simulation and artificial intelligence and their related fields, such as common sense knowledge bases, chatterbots, natural language parsing, semantic analysis, synthetic actors, and cognitive sciences. This paper takes part in that extensive research by focusing on the improvement of human simulation in chatterbots, specifically in Alicebot, a prominent non-emotional pattern-matching chatbot. An emotion and personality model is added to Alicebot so that it can make decisions based on its emotions and personality. Alicebot is also augmented with the ability to determine what it likes or does not like …

Validation And Verification Of Aircraft Control Software For Control Improvement, Thien-Anh Pham

Master's Projects

Validation and Verification are important processes used to ensure software safety and reliability. The Cooper-Harper Aircraft Handling Qualities Rating is one of the techniques developed and used by NASA researchers to verify and validate control systems for aircrafts. Using the Validation and Verification result of controller software to improve controller's performance will be one of the main objectives of this process. Real user feedback will be used to tune PI controller in order for it to perform better. The Cooper-Harper Aircraft Handling Qualities Rating can be used to justify the performance of the improved system.

Mobile Multimedia Streaming Library, Bao Ho

Master's Projects

In recent years, multimedia has become a commonly used tool for presenting contents to the users. The employment of multimedia is no longer limited to only the entertainment industry, but spans in other areas as well. In academics, lectures are recorded to audio and video for storage and distribution to students. Free online multimedia hosting services are popularly cherished, such as “youtube.com” and “yahoo video”, and with the increasing affordability of digital camera, hundreds, or maybe thousands, of home-made videos and music audio are created daily and published online. Low-cost digital recorders such as webcams also help promote the use …

Blog Analysis With Fuzzy Tfidf, Chi-Shu Ho

Master's Projects

These days blogs are becoming increasingly popular because it allows anyone to share their personal diary, opinions, and comments on the World Wide Wed. Many blogs contain valuable information, but it is a difficult task to extract this information from a high number of blog comments. The goal is to analyze a high number of blog comments by clustering all blog comments by their similarity based on keyword relevance into smaller groups. TF-IDF weight has been used in classifying documents by measuring appearance frequency of each keyword in a document, but it is not effective in differentiating semantic similarities between …

Concept Analysis In Web Documents, Rajesh Singh

Master's Projects

A Keyword within a text/web document represents some human thought. The interaction of keywords leads to narrowing of scope of human thought by forming a more precise semantic entity called concepts. Analyzing a set of document not only requires analysis of the keywords within those documents but also their interactions within a document. In this new approach a set of documents can be analyzed where by the interactions of its keywords is also considered in finding the important concepts. These concepts can be used to cluster them into smaller subsets such that documents in each cluster will be semantically similar.

Clustering Blog Information, Mayank Prakash Jaiswal

Master's Projects

Blogs form an important source of information in today’s internet world. There are blogs on different topics such as technical, health, electronic gadgets, shopping, etc. However, most of the blog websites have the blogs arranged in chronological order rather than its contents. Such arrangement of blogs makes it difficult for the user searching information about a particular topic from the blog. To resolve this problem, we propose an approach to cluster the blogs based on its content. We studied several clustering algorithms available. The objective of this report is to understand various steps involved in clustering blog information and working …

Adaptive Neural Network Based Stabilizing Controller Design For Single Machine Infinite Bus Power Systems, Wenxin Liu, Ganesh K. Venayagamoorthy, Donald C. Wunsch, David A. Cartes, Jagannathan Sarangapani, Mariesa Crow

Engineering Management and Systems Engineering Faculty Research & Creative Works

Power system stabilizers are widely used to generate supplementary control signals for the excitation system in order to damp out the low frequency oscillations. In power system control literature, the performances of the proposed controllers were mostly demonstrated using simulation results without any rigorous stability analysis. This paper proposes a stabilizing neural network (NN) controller based on a sixth order single machine infinite bus power system model. The NN is used to approximate the complex nonlinear dynamics of power system. Unlike the other indirect adaptive NN control schemes, there is no offline training process and the NN can be directly …

Classification Of Microarray Data To Predict Toxic Exposure, Tarek A. Seleem

Browse all Theses and Dissertations

This thesis presents a software system for the analysis of microarray data. Microarrays are a relatively new technology that can be used to examine the state of the genome of an organism at some instant in time. The challenge is the amount of natural variation in biological systems limits our ability to identify specific genes that may be sensitive to changes in an organism's physiology or its environment. The analysis software consists of three modules. The first module filters microarray data to reduce the complexity of the problem. The second module selects subsets of genes for evaluation using a genetic …