Digital Commons Network^™

Estimating The Optimal Cutoff Point For Logistic Regression, Zheng Zhang

Open Access Theses & Dissertations

Binary classification is one of the main themes of supervised learning. This research is concerned about determining the optimal cutoff point for the continuous-scaled outcomes (e.g., predicted probabilities) resulting from a classifier such as logistic regression. We make note of the fact that the cutoff point obtained from various methods is a statistic, which can be unstable with substantial variation. Nevertheless, due partly to complexity involved in estimating the cutpoint, there has been no formal study on the variance or standard error of the estimated cutoff point.

In this Thesis, a bootstrap aggregation method is put forward to estimate the …

A Study Into The Feasibility Of Using Natural Language Processing And Machine Learning For The Identification Of Alcohol Misuse In Trauma Patients, Andrew Phillips

Master's Theses

Alcohol misuse is a leading cause of premature death in the United States, with nearly a third of trauma patients found to have elevated blood alcohol levels upon admission. However, timely intervention has been shown to reduce this. It is thus important to be able to quickly screen patients to identify alcohol misuse. Many medical centers use standardized questionnaires to identify alcohol misuse, but since these instruments are not usually a part of routine care, there are many cases where it is not done.

In this study, large quantities of notes were processed with natural language processing and machine learning …

Comparing Various Machine Learning Statistical Methods Using Variable Differentials To Predict College Basketball, Nicholas Bennett

Williams Honors College, Honors Research Projects

The purpose of this Senior Honors Project is to research, study, and demonstrate newfound knowledge of various machine learning statistical techniques that are not covered in the University of Akron’s statistics major curriculum. This report will be an overview of three machine-learning methods that were used to predict NCAA Basketball results, specifically, the March Madness tournament. The variables used for these methods, models, and tests will include numerous variables kept throughout the season for each team, along with a couple variables that are used by the selection committee when tournament teams are being picked. The end goal is to find …

Advanced Imaging Analysis For Predicting Tumor Response And Improving Contour Delineation Uncertainty, Rebecca N. Mahon

Theses and Dissertations

ADVANCED IMAGING ANALYSIS FOR PREDICTING TUMOR RESPONSE AND IMPROVING CONTOUR DELINEATION UNCERTAINTY

By Rebecca Nichole Mahon, MS

A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at Virginia Commonwealth University.

Virginia Commonwealth University, 2018

Major Director: Dr. Elisabeth Weiss,

Professor,

Department of Radiation Oncology

Radiomics, an advanced form of imaging analysis, is a growing field of interest in medicine. Radiomics seeks to extract quantitative information from images through use of computer vision techniques to assist in improving treatment. Early prediction of treatment response is one way of improving overall patient care. This work …

Characterizing The Information Needs Of Rural Healthcare Practitioners With Language Agnostic Automated Text Analysis, Melissa Resnick

Dissertations and Theses (Open Access)

Objectives – Previous research has characterized urban healthcare providers' information needs, using various qualitative methods. However, little is known about the needs of rural primary care practitioners in Brazil. Communication exchanged during tele-consultations presents a unique data source for the study of these information needs. In this study, I characterize rural healthcare providers' information needs expressed electronically, using automated methods.

Methods – I applied automated methods to categorize messages obtained from the telehealth system from two regions in Brazil. A subset of these messages, annotated with top-level categories in the DeCS terminology (the regional equivalent of MeSH), was used to …

A Machine Learning Management Model For Qoe Enhancement In Next-Generation Wireless Ecosystems, Eva Ibarrola, Mark Davis, Camille Voisin, Ciara Close, Leire Cristobo

Conference papers

Next-generation wireless ecosystems are expected to comprise heterogeneous technologies and diverse deployment scenarios. Ensuring a good quality of service (QoS) will be one of the major challenges of next-generation wireless systems on account of a variety of factors that are beyond the control of network and service providers. In this context, ITU-T is working on updating the various Recommendations related to QoS and users' quality of experience (QoE). Considering the ITU-T QoS framework, we propose a methodology to develop a global QoS management model for next-generation wireless ecosystems taking advantage of big data and machine learning. The results from a …

Automated Estimation Of Winter Driving Conditions, Michael E. Baldwin, Kevin D. Burris, Kimberly L. Elmore

JTRP Technical Reports

There is great potential for improvements in traveler safety and satisfaction as new sources of information are incorporated into advanced analytics and prediction systems. It is critical for transportation agencies to be able to monitor weather conditions in real-time as well as over the long-term for purposes of maintenance, planning, and performance evaluation. Travelers also use this information to plan their routes, make decisions on timing, and improve their awareness of potential hazards. A machine learning model was developed in this project to automatically estimate winter driving conditions in real-time using weather information as input. This system can provide rapid …

Using Artificial Intelligence And Machine Learning To Develop Synthetic Well Logs, Marwan Mohammed Alnuaimi

Graduate Theses, Dissertations, and Problem Reports (ETD)

There has been an increase in the need for energy in the recent past. Oil and gas stand as the source of energy that are widely used. The oil and gas reservoirs are targeted for the purposes of field development. The conventional methods of reservoir characteristics require computing techniques that are unique and complex, some of which are labor and time intensive. Mohaghegh argues that all efforts must be tried and made possible to apply Petroleum Data analytics in production and management of reservoir so as to earn a maximum return (Mohaghegh, Shale Analytics, 2017). Different methodologies have been applied …

Genome-Scale Microrna Target Prediction Through Clustering With Dirichlet Process Mixture Model, Zeynep M. Hakguder, Jiang Shu, Chunxiao Liao, Kaiyue Pan, Juan Cui

School of Computing: Faculty Publications

Background: MicroRNA regulation is fundamentally responsible for fine-tuning the whole gene network in human and has been implicated in most physiological and pathological conditions. Studying regulatory impact of microRNA on various cellular and disease processes has resulted in numerous computational tools that investigate microRNA-mRNA interactions through the prediction of static binding site highly dependent on sequence pairing. However, what hindered the practical use of such target prediction is the interplay between competing and cooperative microRNA binding that complicates the whole regulatory process exceptionally.

Results: We developed a new method for improved microRNA target prediction based on Dirichlet Process …

Fuzziness-Based Active Learning Framework To Enhance Hyperspectral Image Classification Performance For Discriminative And Generative Classifiers, Muhammad Ahmad, Stanislav Protasov, Adil Mehmood Khan, Rasheed Hussain, Asad Masood Khattak, Wajahat Ali Khan

All Works

© 2018 Ahmad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal …

An Evaluation Of Unsupervised Machine Learning Algorithms For Detecting Fraud And Abuse In The U.S. Medicare Insurance Program, Rosa Raquel C Da

Electronic Theses and Dissertations 2010 - 2019

The population of people ages 65 and older has increased since the 1960s and current estimates indicate it will double by 2060. Medicare is a federal health insurance program for people 65 or older in the United States. Medicare claims fraud and abuse is an ongoing issue that wastes a large amount of money every year resulting in higher health care costs and taxes for everyone. In this study, an empirical evaluation of several unsupervised machine learning approaches is performed which indicates reasonable fraud detection results. We employ two unsupervised machine learning algorithms, Isolation Forest and Unsupervised Random Forest, which …

Machine Learning Methods To Understand Textual Data, Sahar Sohangir

Electronic Theses and Dissertations 2010 - 2019

The amount of textual data that produce every minute on the internet is extremely high. Processing of this tremendous volume of mostly unstructured data is not a straightforward function. But the enormous amount of useful information that lay down on them motivate scientists to investigate efficient and effective techniques and algorithms to discover meaningful patterns. Social network applications provide opportunities for people around the world to be in contact and share their valuable knowledge, such as chat, comments, and discussion boards. People usually do not care about spelling and accurate grammatical construction of a sentence in everyday life conversations. Therefore, …

Machine Learning Algorithms With Big Medicare Fraud Data, Richard Andrew Bauder

Electronic Theses and Dissertations 2010 - 2019

Healthcare is an integral component in peoples lives, especially for the rising elderly population, and must be affordable. The United States Medicare program is vital in serving the needs of the elderly. The growing number of people enrolled in the Medicare program, along with the enormous volume of money involved, increases the appeal for, and risk of, fraudulent activities. For many real-world applications, including Medicare fraud, the interesting observations tend to be less frequent than the normative observations. This difference between the normal observations and those observations of interest can create highly imbalanced datasets. The problem of class imbalance, to …

Looping Predictive Method To Improve Accuracy Of A Machine Learning Model, Subramanyam Reddy Pogili

Theses

The topic of this project is an analysis of drug-related tweets. The goal is to build a Machine Learning Model that can distinguish between tweets that indicate drug abuse and other tweets that also contain the name of a drug but do not describe abuse. Drugs can be illegal, such as heroin, or legal drugs with a potential of abuse, such as painkillers. However, building a good Machine Learning Model requires a large amount of training data. For each training tweet, a human expert has determined whether it indicates drug abuse or not. This is difficult work for humans. …

Classifying Cancer Genome Aberrations By Their Mutually Exclusive Effects On Transcription, Jonathan B. Dayton, Stephen R. Piccolo

Faculty Publications

Background

Malignant tumors are typically caused by a conglomeration of genomic aberrations—including point mutations, small insertions, small deletions, and large copy-number variations. In some cases, specific chemotherapies and targeted drug treatments are effective against tumors that harbor certain genomic aberrations. However, predictive aberrations (biomarkers) have not been identified for many tumor types and treatments. One way to address this problem is to examine the downstream, transcriptional effects of genomic aberrations and to identify characteristic patterns. Even though two tumors harbor different genomic aberrations, the transcriptional effects of those aberrations may be similar. These patterns could be used to inform treatment …

Visual Odometry Using Convolutional Neural Networks, Alec Graves, Steffen Lim, Thomas Fagan, Kevin Mcfall Phd.

The Kennesaw Journal of Undergraduate Research

Visual odometry is the process of tracking an agent's motion over time using a visual sensor. The visual odometry problem has only been recently solved using traditional, non-machine learning techniques. Despite the success of neural networks at many related problems such as object recognition, feature detection, and optical flow, visual odometry still has not been solved with a deep learning technique. This paper attempts to implement several Convolutional Neural Networks to solve the visual odometry problem and compare slight variations in data preprocessing. The work presented is a step toward reaching a legitimate neural network solution.

Fifa: Exploring A Focally Induced Fault Attack Strategy In Near-Threshold Computing, Prabal Basu, Chidhambaranathan Rajamanikkam, Aatreyi Bal, Pramesh Pandey, Trevor Carter, Koushik Chakraborty, Sanghamitra Roy

Electrical and Computer Engineering Faculty Publications

In this letter, we explore the emerging security threats of near-threshold computing (NTC). Researchers have shown that the delay sensitivity of a circuit to supply voltage variation tremendously increases, as the circuit's operating conditions shift from traditional super-threshold values to NTC values. As a result, NTC systems become extremely vulnerable to timing fault attacks, jeopardizing trustworthy computing. Inspired by the operation of a polymorphic virus, we propose a novel threat model for NTC, referred to as a focally induced fault attack (FIFA). FIFA employs a machine learning framework to ascertain the circuit vulnerabilities and generates targeted software modules to cause …

Machine Learning To Discover And Optimize Materials, Conrad Waldhar Rosenbrock

Theses and Dissertations

For centuries, scientists have dreamed of creating materials by design. Rather than discovery by accident, bespoke materials could be tailored to fulfill specific technological needs. Quantum theory and computational methods are essentially equal to the task, and computational power is the new bottleneck. Machine learning has the potential to solve that problem by approximating material behavior at multiple length scales. A full end-to-end solution must allow us to approximate the quantum mechanics, microstructure and engineering tasks well enough to be predictive in the real world. In this dissertation, I present algorithms and methodology to address some of these problems at …

A Machine Learning Approach To The Classification Of Phishing Bot Accounts Within Twitter, Christopher James Brake

The Plymouth Student Scientist

Social network bots are becoming an ever-greater threat to online users. Most studies carried out have looked at bots which generate a lot of tweets known as spam, as these are very common. In recent years research into the area of bots within Twitter has been carried out using machine learning to attempt to find patterns in these ac-counts to aide with detection. However, limited research has been carried out that focuses on a sub set of Twitter bots which are involved in phishing campaigns which tweet very little to avoid detection. In this project an application was developed that …

Ethics And Bias In Machine Learning: A Technical Study Of What Makes Us “Good”, Ashley Nicole Shadowen

Student Theses

The topic of machine ethics is growing in recognition and energy, but bias in machine learning algorithms outpaces it to date. Bias is a complicated term with good and bad connotations in the field of algorithmic prediction making. Especially in circumstances with legal and ethical consequences, we must study the results of these machines to ensure fairness. This paper attempts to address ethics at the algorithmic level of autonomous machines. There is no one solution to solving machine bias, it depends on the context of the given system and the most reasonable way to avoid biased decisions while maintaining the …

A Test Driven Approach To Develop Web-Based Machine Learning Applications, Armin Esmaeilzadeh

UNLV Theses, Dissertations, Professional Papers, and Capstones

The purpose of this thesis is to propose the design and architecture of a testable, scalable, and ef-cient web-based application that models and implements machine learning applications in cancer prediction. There are various components that form the architecture of our web-based application including server, database, programming language, web framework, and front-end design. There are also other factors associated with our application such as testability, scalability, performance, and design pattern. Our main focus in this thesis is on the testability of the system while consid- ering the importance of other factors as well.

The data set for our application is a …

A Decision Tree Approach For The Musical Genres Classification, Glaucia M. Bressan, Beatriz C. F. De Azevedo, Elisangela Ap. S. Lizzi

Applied Mathematics & Information Sciences

The interest in the music classification has increased due to its wide applicability and discoveries obtained from researches. However, efficient methods for systemic organization of digital libraries are required, since users need to classify the available music files. When an automatic classification is desired, the extraction of input attributes and an efficient system, able to process them, are needed. In this context, the use of decision trees as a tool to predict musical genres classes allows the monitoring of the ramification, since nodes and branches of the tree can be accessed in this process. Decision tree is a technique very …

Scalable Online Kernel Learning, Jing Lu

Dissertations and Theses Collection (Open Access)

One critical deficiency of traditional online kernel learning methods is their increasing and unbounded number of support vectors (SV’s), making them inefficient and non-scalable for large-scale applications. Recent studies on budget online learning have attempted to overcome this shortcoming by bounding the number of SV’s. Despite being extensively studied, budget algorithms usually suffer from several drawbacks.
First of all, although existing algorithms attempt to bound the number of SV’s at each iteration, most of them fail to bound the number of SV’s for the final averaged classifier, which is commonly used for online-to-batch conversion. To solve this problem, we propose …

Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell

Computer Science Faculty Publications and Presentations

A major goal of computer vision is to enable computers to interpret visual situations—abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations— a situation model—that represent the expected spatial structure of the given situation. These …

Anomaly Detection For A Water Treatment System Using Unsupervised Machine Learning, Jun Inoue, Yoriyuki Yamagata, Yuqi Chen, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

In this paper, we propose and evaluate the application of unsupervised machine learning to anomaly detection for a Cyber-Physical System (CPS). We compare two methods: Deep Neural Networks (DNN) adapted to time series data generated by a CPS, and one-class Support Vector Machines (SVM). These methods are evaluated against data from the Secure Water Treatment (SWaT) testbed, a scaled-down but fully operational raw water purification plant. For both methods, we first train detectors using a log generated by SWaT operating under normal conditions. Then, we evaluate the performance of both methods using a log generated by SWaT operating under 36 …

Neural Network Prediction Of Barbell Kinematics From Joint Kinetics In Weightlifting, Kristof Kipp

ISBS Proceedings Archive

The purpose of this study was to develop and train neural networks (NN) to predict barbell motion and velocity from hip, knee, and ankle joint torques during a weightlifting exercise. Seven weightlifters performed two repetitions of the clean exercise at 85% of maximum while reaction forces and 3-D motion data of the lifter and barbell were acquired. An inverse dynamics procedure was then used to calculate torques at the hip, knee, and ankle joints. The joint torque time-series data were used as inputs to two seperate NN to predict 1) the horizontal and vertical barbell trajectories and 2) the vertical …

Predicting Adverse Outcomes In Chronic Kidney Disease Using Machine Learning Methods: Data From The Modification Of Diet In Renal Disease, Zeid Khitan, Anna P. Shapiro, Preeya T. Shah, Juan R. Sanabria, Prasanna Santhanam, Komal Sodhi, Nader G. Abraham, Joseph I. Shapiro

Marshall Journal of Medicine

Background: Understanding factors which predict progression of renal failure is of great interest to clinicians.

Objectives: We examined machine learning methods to predict the composite outcome of death, dialysis or doubling of serum creatinine using the modification of diet in renal disease (MDRD) data set.

Methods: We specifically evaluated a generalized linear model, a support vector machine, a decision tree, a feed-forward neural network and a random forest evaluated within the context of 10 fold validation using the CARET package available within the open source architecture R program.

Results: We found that using clinical parameters available at entry into the …

Identification Of Reverse Engineering Candidates Utilizing Machine Learning And Aircraft Cannibalization Data, Marc Banghart

International Journal of Aviation, Aeronautics, and Aerospace

As military aircraft continue to remain in service and age, cannibalization of parts is increasing. Proactive identification of parts that are at high risk for cannibalization will inform engineering processes such as reverse engineering, thus allowing potentially reducing lead time to develop new parts. The research objective was to develop a causal structure that can be used for prediction of when cannibalization actions may occur. Bayesian networks allow encoding of causality between various descriptive features given a data set. The method utilized a tabu search algorithm, identified the underlying causal structure and the associated node probabilities. The method is then …

A Comparative Study On Machine Learning Algorithms For Network Defense, Abdinur Ali, Yen-Hung Hu, Chung-Chu (George) Hsieh, Mushtaq Khan

Virginia Journal of Science

Network security specialists use machine learning algorithms to detect computer network attacks and prevent unauthorized access to their networks. Traditionally, signature and anomaly detection techniques have been used for network defense. However, detection techniques must adapt to keep pace with continuously changing security attacks. Therefore, machine learning algorithms always learn from experience and are appropriate tools for this adaptation. In this paper, ten machine learning algorithms were trained with the KDD99 dataset with labels, then they were tested with a different dataset without labels. The researchers investigate the speed and the efficiency of these machine learning algorithms in terms of …

The Folded K-Spectrum Kernel: A Machine Learning Approach To Detecting Transcription Factor Binding Sites With Gapped Nucleotide Dependencies, Abdulkadir Elmas, Xiaodong Wang, Jacqueline M. Dresch

Biology

Understanding the molecular machinery involved in transcriptional regulation is central to improving our knowledge of an organism’s development, disease, and evolution. The building blocks of this complex molecular machinery are an organism’s genomic DNA sequence and transcription factor proteins. Despite the vast amount of sequence data now available for many model organisms, predicting where transcription factors bind, often referred to as ‘motif detection’ is still incredibly challenging. In this study, we develop a novel bioinformatic approach to binding site prediction. We do this by extending pre-existing SVM approaches in an unbiased way to include all possible gapped k-mers, representing different …