Computer Sciences Commons^™

Random Forests Based Rule Learning And Feature Elimination, Sheng Liu

Electronic Theses and Dissertations

Much research combines data from multiple sources in an effort to understand the underlying problems. It is important to find and interpret the most important information from these sources. Thus it will be beneficial to have an effective algorithm that can simultaneously extract decision rules and select critical features for good interpretation while preserving the prediction performance. We propose an efficient approach, combining rule extraction and feature elimination, based on 1-norm regularized random forests. This approach simultaneously extracts a small number of rules generated by random forests and selects important features. To evaluate this approach, we have applied it to …

An Evolutionary Approximation To Contrastive Divergence In Convolutional Restricted Boltzmann Machines, Ryan R. Mccoppin

Browse all Theses and Dissertations

Deep learning is an emerging area in machine learning that exploits multi-layered neural networks to extract invariant relationships from large data sets. Deep learning uses layers of non-linear transformations to represent data in abstract and discrete forms. Several different architectures have been developed over the past few years specifically to process images including the Convolutional Restricted Boltzmann Machine. The Boltzmann Machine is trained using contrastive divergence, a depth-first gradient based training algorithm. Gradient based training methods have no guarantee of reaching an optimal solution and tend to search a limited region of the solution space. In this thesis, we present …

Assessment And Prediction Of Cardiovascular Status During Cardiac Arrest Through Machine Learning And Dynamical Time-Series Analysis, Sharad Shandilya

Theses and Dissertations

In this work, new methods of feature extraction, feature selection, stochastic data characterization/modeling, variance reduction and measures for parametric discrimination are proposed. These methods have implications for data mining, machine learning, and information theory. A novel decision-support system is developed in order to guide intervention during cardiac arrest. The models are built upon knowledge extracted with signal-processing, non-linear dynamic and machine-learning methods. The proposed ECG characterization, combined with information extracted from PetCO2 signals, shows viability for decision-support in clinical settings. The approach, which focuses on integration of multiple features through machine learning techniques, suits well to inclusion of multiple physiologic …

An Automatic Framework For Embryonic Localization Using Edges In A Scale Space, Zachary Bessinger

Masters Theses & Specialist Projects

Localization of Drosophila embryos in images is a fundamental step in an automatic computational system for the exploration of gene-gene interaction on Drosophila. Contour extraction of embryonic images is challenging due to many variations in embryonic images. In the thesis work, we develop a localization framework based on the analysis of connected components of edge pixels in a scale space. We propose criteria to select optimal scales for embryonic localization. Furthermore, we propose a scale mapping strategy to compress the range of a scale space in order to improve the efficiency of the localization framework. The effectiveness of the proposed …

Knowledge Extraction In Video Through The Interaction Analysis Of Activities, Omar Ulises Florez

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

A video is a growing stream of unstructured data that significantly increases the amount of information transmitted and stored on the Internet. For example, every minute YouTube users upload 72 GB of information. Some of the best applications for video analysis include the monitoring of activities in defense and security scenarios such as the autonomous planes that collect video and images at reduced risk and the surveillance cameras in public places like traffic lights, airports, and schools.

Some of the challenges in the analysis of video correspond to implement complex operations such as searching of activities, understanding of scenes, and …

A Hierarchical Multi-Output Nearest Neighbor Model For Multi-Output Dependence Learning, Richard Glenn Morris

Theses and Dissertations

Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other. A primary issue that arises in the context of MOD learning is that for any given input pattern there can be multiple correct output patterns. This changes the learning task from function approximation to relation approximation. Previous algorithms do not consider this problem, and thus cannot be readily applied to MOD problems. To perform MOD learning, we introduce the Hierarchical Multi-Output Nearest Neighbor model (HMONN) that employs a basic learning model for each output and a modified nearest …

Spoons: Netflix Outage Detection Using Microtext Classification, Eriq A. Augusitne

Master's Theses

Every week there are over a billion new posts to Twitter services and many of those messages contain feedback to companies about their services. One company that recognizes this unused source of information is Netflix. That is why Netflix initiated the development of a system that lets them respond to the millions of Twitter and Netflix users that are acting as sensors and reporting all types of user visible outages. This system enhances the feedback loop between Netflix and its customers by increasing the amount of customer feedback that Netflix receives and reducing the time it takes for Netflix to …

Learning With An Insufficient Supply Of Data Via Knowledge Transfer And Sharing, Samir Al-Stouhi

Wayne State University Dissertations

As machine learning methods extend to more complex and diverse set of problems, situations arise where the complexity and availability of data presents a situation where the information source is not "adequate" to generate a representative hypothesis. Learning from multiple sources of data is a promising research direction as researchers leverage ever more diverse sources of information. Since data is not readily available, knowledge has to be transferred from other sources and new methods (both supervised and un-supervised) have to be developed to selectively share and transfer knowledge. In this dissertation, we present both supervised and un-supervised techniques to tackle …

Energy Efficient Context-Aware Framework In Mobile Sensing, Ozgur Yurur

USF Tampa Graduate Theses and Dissertations

The ever-increasing technological advances in embedded systems engineering, together with the proliferation of small-size sensor design and deployment, have enabled mobile devices (e.g., smartphones) to recognize daily occurring human based actions, activities and interactions. Therefore, inferring a vast variety of mobile device user based activities from a very diverse context obtained by a series of sensory observations has drawn much interest in the research area of ubiquitous sensing. The existence and awareness of the context provides the capability of being conscious of physical environments or situations around mobile device users, and this allows network services to respond proactively and intelligently …

A Physiological Signal Processing System For Optimal Engagement And Attention Detection., Ashwin Belle

Theses and Dissertations

In today’s high paced, hi-tech and high stress environment, with extended work hours, long to-do lists and neglected personal health, sleep deprivation has become common in modern culture. Coupled with these factors is the inherent repetitious and tedious nature of certain occupations and daily routines, which all add up to an undesirable fluctuation in individuals’ cognitive attention and capacity. Given certain critical professions, a momentary or prolonged lapse in attention level can be catastrophic and sometimes deadly. This research proposes to develop a real-time monitoring system which uses fundamental physiological signals such as the Electrocardiograph (ECG), to analyze and predict …

Contributions To K-Means Clustering And Regression Via Classification Algorithms, Raied Salman

Theses and Dissertations

The dissertation deals with clustering algorithms and transforming regression prob-lems into classification problems. The main contributions of the dissertation are twofold; first, to improve (speed up) the clustering algorithms and second, to develop a strict learn-ing environment for solving regression problems as classification tasks by using support vector machines (SVMs). An extension to the most popular unsupervised clustering meth-od, k-means algorithm, is proposed, dubbed k-means2 (k-means squared) algorithm, appli-cable to ultra large datasets. The main idea is based on using a small portion of the dataset in the first stage of the clustering. Thus, the centers of such a smaller …

Tagline: Information Extraction For Semi-Structured Text Elements In Medical Progress Notes, Dezon K. Finch

USF Tampa Graduate Theses and Dissertations

Text analysis has become an important research activity in the Department of Veterans Affairs (VA). Statistical text mining and natural language processing have been shown to be very effective for extracting useful information from medical documents. However, neither of these techniques is effective at extracting the information stored in semi-structure text elements. A prototype system (TagLine) was developed as a method for extracting information from the semi-structured portions of text using machine learning. Features for the learning machine were suggested by prior work, as well as by examining the text, and selecting those attributes that help distinguish the various classes …

An Ssvep Brain-Computer Interface: A Machine Learning Approach, Fei Teng

Electronic Theses and Dissertations

A Brain-Computer Interface (BCI) provides a bidirectional communication path for a human to control an external device using brain signals. Among neurophysiological features in BCI systems, steady state visually evoked potentials (SSVEP), natural responses to visual stimulation at specific frequencies, has increasingly drawn attentions because of its high temporal resolution and minimal user training, which are two important parameters in evaluating a BCI system. The performance of a BCI can be improved by a properly selected neurophysiological signal, or by the introduction of machine learning techniques. With the help of machine learning methods, a BCI system can adapt to the …

Model Individualization For Real-Time Operator Functional State Assessment, Guangfan Zhang, Roger Xu, Wei Wang, Aaron A. Pepe, Feng Li, Jiang Li, Frederick Mckenzie, Tom Schnell, Nick Anderson, Dean Heitkamp

Electrical & Computer Engineering Faculty Publications

Proper assessment of Operator Functional State (OFS) and appropriate workload modulation offer the potential to improve mission effectiveness and aviation safety in both overload and under-load conditions. Although a wide range of research has been devoted to building OFS assessment models, most of the models are based on group statistics and little or no research has been directed towards model individualization, i.e., tuning the group statistics based model for individual pilots. Moreover, little emphasis has been placed on monitoring whether the pilot is disengaged during low workload conditions. The primary focus of this research is to provide a real-time engagement …

Data-Intensive Computing For Bioinformatics Using Virtualization Technologies And Hpc Infrastructures, Pengfei Xuan

All Theses

The bioinformatics applications often involve many computational components and massive data sets, which are very difficult to be deployed on a single computing machine. In this thesis, we designed a data-intensive computing platform for bioinformatics applications using virtualization technologies and high performance computing (HPC) infrastructures with the concept of multi-tier architecture, which can seamlessly integrate the web user interface (presentation tier), scientific workflow (logic tier) and computing infrastructure (data/computing tier). We demonstrated our platform on two bioinformatics projects. First, we redesigned and deployed the cotton marker database (CMD) (http://www.cottonmarker.org), a centralized web portal in the cotton research community, using the …

Fast Parallel Machine Learning Algorithms For Large Datasets Using Graphic Processing Unit, Qi Li

Theses and Dissertations

This dissertation deals with developing parallel processing algorithms for Graphic Processing Unit (GPU) in order to solve machine learning problems for large datasets. In particular, it contributes to the development of fast GPU based algorithms for calculating distance (i.e. similarity, affinity, closeness) matrix. It also presents the algorithm and implementation of a fast parallel Support Vector Machine (SVM) using GPU. These application tools are developed using Compute Unified Device Architecture (CUDA), which is a popular software framework for General Purpose Computing using GPU (GPGPU). Distance calculation is the core part of all machine learning algorithms because the closer the query …

Fundamental Work Toward An Image Processing-Empowered Dental Intelligent Educational System, Grace Olsen

Theses and Dissertations

Computer-aided education in dental schools is greatly needed in order to reduce the need for human instructors to provide guidance and feedback as students practice dental procedures. A portable computer-aided educational system with advanced digital image processing capabilities would be less expensive than current computer-aided dental educational systems and would also address some of their limitations. This dissertation outlines the development of novel components that would be part of such a system. This research includes the design of a novel image processing technique, the Directed Active Shape Model algorithm, which is used to locate the tooth and drilled preparation from …

Pedagogical Possibilities For The N-Puzzle Problem, Zdravko Markov, Ingrid Russell, Todd W. Neller, Neli Zlatareva

Computer Science Faculty Publications

In this paper we present work on a project funded by the National Science Foundation with a goal of unifying the Artificial Intelligence (AI) course around the theme of machine learning. Our work involves the development and testing of an adaptable framework for the presentation of core AI topics that emphasizes the relationship between AI and computer science. Several hands-on laboratory projects that can be closely integrated into an introductory AI course have been developed. We present an overview of one of the projects and describe the associated curricular materials that have been developed. The project uses machine learning as …

Enhancing Undergraduate Ai Courses Through Machine Learning Projects, Ingrid Russell, Zdravko Markov, Todd W. Neller, Susan Coleman

Computer Science Faculty Publications

It is generally recognized that an undergraduate introductory Artificial Intelligence course is challenging to teach. This is, in part, due to the diverse and seemingly disconnected core topics that are typically covered. The paper presents work funded by the National Science Foundation to address this problem and to enhance the student learning experience in the course. Our work involves the development of an adaptable framework for the presentation of core AI topics through a unifying theme of machine learning. A suite of hands-on semester-long projects are developed, each involving the design and implementation of a learning system that enhances a …

Unifying An Introduction To Artificial Intelligence Course Through Machine Learning Laboratory Experiences, Ingrid Russell, Zdravko Markov, Todd W. Neller, Michael Georgiopoulos, Susan Coleman

Computer Science Faculty Publications

This paper presents work on a collaborative project funded by the National Science Foundation that incorporates machine learning as a unifying theme to teach fundamental concepts typically covered in the introductory Artificial Intelligence courses. The project involves the development of an adaptable framework for the presentation of core AI topics. This is accomplished through the development, implementation, and testing of a suite of adaptable, hands-on laboratory projects that can be closely integrated into the AI course. Through the design and implementation of learning systems that enhance commonly-deployed applications, our model acknowledges that intelligent systems are best taught through their application …

Multizoom Activity Recognition Using Machine Learning, Raymond Smith

Electronic Theses and Dissertations

In this thesis we present a system for detection of events in video. First a multiview approach to automatically detect and track heads and hands in a scene is described. Then, by making use of epipolar, spatial, trajectory, and appearance constraints, objects are labeled consistently across cameras (zooms). Finally, we demonstrate a new machine learning paradigm, TemporalBoost, that can recognize events in video. One aspect of any machine learning algorithm is in the feature set used. The approach taken here is to build a large set of activity features, though TemporalBoost itself is able to work with any feature set …

Pattern Recognition Via Machine Learning With Genetic Decision-Programming, Carl C. Hoff

Browse all Theses and Dissertations

In the intersection of pattern recognition, machine learning, and evolutionary computation is a new search technique by which computers might program themselves. That technique is called genetic decision-programming. A computer can gain the ability to distinguish among the things that it needs to recognize by using genetic decision-programming for pattern discovery and concept learning. Those patterns and concepts can be easily encoded in the spines of a decision program (tree or diagram). A spine consists of two parts: (1) the test-outcome pairs along a path from the program's root to any of its leaves and (2) the conclusion in that …