Digital Commons Network^™

Big Data: Learning, Analytics, And Applications, Nasir Safdari, Hussein Alrubaye, Wajdi Aljedaani, Bladimir Baez Baez, Andrew Distasi, Mohamed Wiem Mkaouer

Presentations and other scholarship

With the rise of autonomous systems, the automation of faults detection and localization becomes critical to their reliability. An automated strategy that can provide a ranked list of faulty modules or files with respect to how likely they contain the root cause of the problem would help in the automation bug localization. Learning from the history if previously located bugs in general, and extracting the dependencies between these bugs in particular, helps in building models to accurately localize any potentially detected bugs. In this study, we propose a novel fault localization solution based on a learning-to-rank strategy, using the history …

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher

Student Research Symposium

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …

Diagnostic Imaging Of Structural Concrete Using Ground Penetrating Radar And Ultrasonic Array, Sina Mehdinia, Thomas Schumacher, Eric Wan, Xubo Song

Student Research Symposium

Structural concrete is the most widely used construction material in the world. Many structures critical to a society such as bridges, hospitals, and airports are built with concrete. While this material is well understood from a mechanical design point of view, still no accurate quantitative tools exist to assess it for damage and deterioration. This is of particular concern for an urban area like Portland with a mega-thrust earthquake waiting to occur. Non-destructive evaluation tools that can quickly and accurately give a full picture of the integrity of structural concrete elements will be key to help plan effective and safe …

An Unsupervised Machine-Learning Framework For Behavioral Classification From Animal-Borne Accelerometers, Jane Elizabeth Dentinger

Theses and Dissertations

Studies of animal spatial distributions typically use prior knowledge of animal habitat requirements and behavioral ecology to deduce the most likely explanations of observed habitat use. Animal-borne accelerometers can be used to distinguish behaviors which allows us to incorporate in situ behavior into our understanding of spatial distributions. Past research has focused on using supervised machine-learning, which requires a priori specification of behavior to identify signals whereas unsupervised approaches allow the model to identify as many signal types as permitted by the data. The following framework couples direct observation to behavioral clusters identified from unsupervised machine learning on a large …

Machine Learning Predictions Of No-Show Appointments In A Primary Care Setting, Joseph Denney, Samuel Coyne, Sohail Rafiqi

SMU Data Science Review

No-show appointments are a significant financial and operational burden for the entire healthcare system. In primary care, the rate of no-show appointments ranges from 19% [1] to 42% [2]. The data set contains just over 988,000 unique encounters spanning 7 years’ worth of appointment, clinical, demographic, and financial data from a large rural Federally Qualified Health Center. Prediction of the probability of a patient missing a scheduled appointment in a primary health care center can be a significant advantage to operational and financial success for a primary care practice. Using the predictive data generated, in combination with targeted interventions, can …

Identifying Fake News Using Emotion Analysis, Brady Gilleran

Computer Science and Computer Engineering Undergraduate Honors Theses

This paper presents research applying Emotional Analysis to “Fake News” and “Real News” articles to investigate whether or not there is a difference in the emotion used in these two types of news articles. The paper reports on a dataset for Fake and Real News that we created, and the natural language processing techniques employed to process the collected text. We use a lexicon that includes predefined words for eight emotions (anger, anticipation, disgust, fear, surprise, sadness, joy, trust) to measure the emotional impact in each of these eight dimensions. The results of the emotion analysis are used as features …

The P-Art Framework For Placement Of Virtual Network Services In A Multi-Cloud Environment, Lav Gupta, Raj Jain, Aiman Erbad, Deval Bhamare

Computer Science Faculty Works

Carriers’ network services are distributed, dynamic, and investment intensive. Deploying them as virtual network services (VNS) brings the promise of low-cost agile deployments, which reduce time to market new services. If these virtual services are hosted dynamically over multiple clouds, greater flexibility in optimizing performance and cost can be achieved. On the flip side, when orchestrated over multiple clouds, the stringent performance norms for carrier services become difficult to meet, necessitating novel and innovative placement strategies. In selecting the appropriate combination of clouds for placement, it is important to look ahead and visualize the environment that will exist at the …

Deep Reinforcement Learning-Based Portfolio Management, Nitin Kanwar

Computer Science and Engineering Theses - Archive

Machine Learning is at the forefront of every field today. The subfields of Machine Learning called Reinforcement Learning and Deep Learning, when combined have given rise to advanced algorithms which have been successful at reaching or surpassing the human-level performance at playing Atari games to defeating multiple times champion at Go. These successes of Machine Learning have attracted the interest of the financial community and have raised the question if these techniques could also be applied in detecting patterns in the financial markets. Until recently, mathematical formulations of dynamical systems in the context of Signal Processing and Control Theory have …

Clustering Of Multiple Instance Data., Andrew D. Karem

Electronic Theses and Dissertations

An emergent area of research in machine learning that aims to develop tools to analyze data where objects have multiple representations is Multiple Instance Learning (MIL). In MIL, each object is represented by a bag that includes a collection of feature vectors called instances. A bag is positive if it contains at least one positive instance, and negative if no instances are positive. One of the main objectives in MIL is to identify a region in the instance feature space with high correlation to instances from positive bags and low correlation to instances from negative bags -- this region is …

Studying And Handling Iterated Algorithmic Biases In Human And Machine Learning Interaction., Wenlong Sun

Electronic Theses and Dissertations

Algorithmic bias consists of biased predictions born from ingesting unchecked information, such as biased samples and biased labels. Furthermore, the interaction between people and algorithms can exacerbate bias such that neither the human nor the algorithms receive unbiased data. Thus, algorithmic bias can be introduced not only before and after the machine learning process but sometimes also in the middle of the learning process. With a handful of exceptions, only a few categories of bias have been studied in Machine Learning, and there are few, if any, studies of the impact of bias on both human behavior and algorithm performance. …

Learning Representations Using Reinforcement Learning, Sourabh Bose

Computer Science and Engineering Dissertations - Archive

The framework of reinforcement learning is a powerful suite of algorithms that can learn generalized solutions to complex decision making problems. However, the applications of reinforcement learning algorithms to traditional machine learning problems such as clustering, classification and representation learning, have rarely been explored. With the advent of large amounts of data, robust models are required which can extract meaningful representations from the data that can potentially be applied to new unseen tasks. The presented work investigates the applications of reinforcement learning algorithms in the perspective of transfer learning by applying algorithms in the framework of reinforcement learning to address …

Seeing Eye To Eye: A Machine Learning Approach To Automated Saccade Analysis, Maigh Attre

Honors Scholar Theses

Abnormal ocular motility is a common manifestation of many underlying pathologies particularly those that are neurological. Dynamics of saccades, when the eye rapidly changes its point of fixation, have been characterized for many neurological disorders including concussions, traumatic brain injuries (TBI), and Parkinson’s disease. However, widespread saccade analysis for diagnostic and research purposes requires the recognition of certain eye movement parameters. Key information such as velocity and duration must be determined from data based on a wide set of patients’ characteristics that may range in eye shapes and iris, hair and skin pigmentation [36]. Previous work on saccade analysis has …

Modeling And Counteracting Exposure Bias In Recommender Systems., Sami Khenissi

Electronic Theses and Dissertations

Recommender systems are becoming widely used in everyday life. They use machine learning algorithms which learn to predict our preferences and thus influence our choices among a staggering array of options online, such as movies, books, products, and even news articles. Thus what we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated predictions made by learning machines. Similarly, the predictive accuracy of these learning machines heavily depends on the feedback data, such as ratings and clicks, that we provide them. This mutual influence can lead to closed-loop interactions that may cause unknown …

Machine Learning And Empirical Asset Pricing, Yingnan Yi

Doctor of Business Administration Dissertations

In this paper, I conduct a comprehensive study of using machine learning tools to forecast the U.S. stock returns. I use three sets of predictors: the past history summarized by 120 lagged returns, the technical indicators measured by 120 moving average trading signals, and the 79 firm fundamentals, which helps to understand the weak-form market efficiency, algorithm trading and fundamental analysis. I find each set independently has strong predictive power, and buying the top 20% stocks with the greatest predicted returns and shorting bottom 20% with the lowest earns economically significant profits, and the profitability is robust to a number …

Boosting The Hodrick-Prescott Filter, Peter C.B. Phillips, Zhentao Shi

Cowles Foundation Discussion Papers

The Hodrick-Prescott (HP) filter is one of the most widely used econometric methods in applied macroeconomic research. The technique is nonparametric and seeks to decompose a time series into a trend and a cyclical component unaided by economic theory or prior trend specification. Like all nonparametric methods, the HP filter depends critically on a tuning parameter that controls the degree of smoothing. Yet in contrast to modern nonparametric methods and applied work with these procedures, empirical practice with the HP filter almost universally relies on standard settings for the tuning parameter that have been suggested largely by experimentation with macroeconomic …

Machine Learning Classification Of Primary Tissue Origin Of Cancer From Dna Methylation Markers, Sravani Gannavarapu Surya Naga

UNLV Theses, Dissertations, Professional Papers, and Capstones

Cancer is one of the leading causes of death globally and was responsible for approximately 9.6 million deaths in 2018. One of the main reason for deaths from cancer is late-stage presentation and inaccessible diagnosis and treatment. Cancer often spreads from the part of the body where it started (primary site) to a different part of the body (metastatic site). Identifying the primary site of cancer plays a key role as it directs the appropriate treatment. Cancer which spreads needs the same treatment as its origin. Having this knowledge can help doctors to decide the type of treatment.

All cancers …

Efficient Distribution Regression, Nicholas Wilkins

Theses

In this thesis we devise a method for performing distribution regression utilizing an extension of mixture density networks. This method will be benchmarked against other state-of-the-art methods (utilizing negative log loss) and distribution-agnostic models of similar complexity. We demonstrate that our proposed method performs at least as well as the state-of-the-art methods in distribution regression. Additionally, we show that adding distribution predictive capabilities does not significantly decrease performance in models. We illustrate how one can utilize this methodology to regress to confidence interval predictions. Finally, we demonstrate a variety of novel and interesting applications of our framework.

Transferring Generalized Knowledge From Physics-Based Simulation To Clinical Domain, Mohammed Abdullatif Alawad

Theses

A primary factor for the success of machine learning is the quality of labeled training data. However, in many fields, labeled data can be costly, difficult, or even impossible to acquire. In comparison, computer simulation data can now be generated at a much higher abundance with a much lower cost.

These simulation data could potentially solve the problem of data deficiency in many machine learning tasks. Nevertheless, due to model assumptions, simplifications and possible errors, there is always a discrepancy between simulated and real data. This discrepancy needs to be addressed when transferring the knowledge from simulation to real data. …

Detection And Classification Of Vibrating Objects In Sar Images, Francisco German Perez Venegas

Electrical and Computer Engineering ETDs

The vibratory response of buildings and machines contains key information that can be exploited to infer their operating conditions and to diagnose failures. Furthermore, since vibration signatures observed from the exterior surfaces of structures are intrinsically linked to the type of machinery operating inside of them, the ability to monitor vibrations remotely can enable the detection and identification of the machinery.

This dissertation focuses on developing novel techniques for the detection and M-ary classification of vibrating objects in SAR images. The work performed in this dissertation is conducted around three central claims. First, the non-linear transformation that the micro-Doppler return …

Improved Evolutionary Support Vector Machine Classifier For Coronary Artery Heart Disease Prediction Among Diabetic Patients, Narasimhan B, Malathi A Dr

Library Philosophy and Practice (e-journal)

Soft computing paves way many applications including medical informatics. Decision support system has gained a major attention that will aid medical practitioners to diagnose diseases. Diabetes mellitus is hereditary disease that might result in major heart disease. This research work aims to propose a soft computing mechanism named Improved Evolutionary Support Vector Machine classifier for CAHD risk prediction among diabetes patients. The attribute selection mechanism is attempted to build with the classifier in order to reduce the misclassification error rate of the conventional support vector machine classifier. Radial basis kernel function is employed in IESVM. IESVM classifier is evaluated through …

Intelligent Machine Learning: Tailor-Making Macromolecules, Yousef Mohammadi, Mohammad Reza Saeb, Alexander Penlidis, Esmaiel Jabbari, Florian J. Stadler, Philippe Zinck, Krzysztof Matyjaszewski

Faculty Publications

Nowadays, polymer reaction engineers seek robust and effective tools to synthesize complex macromolecules with well-defined and desirable microstructural and architectural characteristics. Over the past few decades, several promising approaches, such as controlled living (co)polymerization systems and chain-shuttling reactions have been proposed and widely applied to synthesize rather complex macromolecules with controlled monomer sequences. Despite the unique potential of the newly developed techniques, tailor-making the microstructure of macromolecules by suggesting the most appropriate polymerization recipe still remains a very challenging task. In the current work, two versatile and powerful tools capable of effectively addressing the aforementioned questions have been proposed and …

Highly Accurate Fragment Library For Protein Fold Recognition, Wessam Elhefnawy

Computer Science Theses & Dissertations

Proteins play a crucial role in living organisms as they perform many vital tasks in every living cell. Knowledge of protein folding has a deep impact on understanding the heterogeneity and molecular functions of proteins. Such information leads to crucial advances in drug design and disease understanding. Fold recognition is a key step in the protein structure discovery process, especially when traditional computational methods fail to yield convincing structural homologies. In this work, we present a new protein fold recognition approach using machine learning and data mining methodologies.

First, we identify a protein structural fragment library (Frag-K) composed of a …

The Validity Of Microblogs As A Source For Idiopathic Pulmonary Fibrosis Patient-Reported Outcomes, Kim Tran

Theses and Dissertations

Idiopathic pulmonary fibrosis (IPF) is an interstitial lung disease which affects an estimated five million patients worldwide. Characterized by progressive respiratory failure and a median patient survival time of three to five years, this disease affects 150,000 patients in the United States (US) and results in 40,000 deaths annually. While the US mortality rate for IPF is similar to breast cancer, idiopathic pulmonary fibrosis remains characterized as a rare disease. Lack of awareness and information for lesser known diseases such as IPF can affect factors ranging from proper diagnosis to the advancement of the drug development pipeline. One platform which …

Confidence Inference In Defensive Cyber Operator Decision Making, Graig S. Ganitano

Theses and Dissertations

Cyber defense analysts face the challenge of validating machine generated alerts regarding network-based security threats. Operations tempo and systematic manpower issues have increased the importance of these individual analyst decisions, since they typically are not reviewed or changed. Analysts may not always be confident in their decisions. If confidence can be accurately assessed, then analyst decisions made under low confidence can be independently reviewed and analysts can be offered decision assistance or additional training. This work investigates the utility of using neurophysiological and behavioral correlates of decision confidence to train machine learning models to infer confidence in analyst decisions. Electroencephalography …

Characterization Of Tropical Cyclone Intensity Using Microwave Imagery, Amanda M. Nelson

Theses and Dissertations

In the absence of wind speed data from aircraft reconnaissance of tropical cyclones (TCs), analysts rely on remote sensing tools to estimate TC intensity. For over 40 years, the Dvorak technique has been applied to estimate intensity using visible and infrared (IR) satellite imagery, but its accuracy is sometimes limited when the radiative effects of high clouds obscure the TC convective structure below. Microwave imagery highlights areas of precipitation and deep convection revealing different patterns than visible and IR imagery. This study explores application of machine learning algorithms to identify patterns in microwave imagery to infer storm intensity, particularly focusing …

A Performance Comparison Of Machine Learning Algorithms For Arced Labyrinth Spillways, Fernando Salazar, Brian M. Crookston

Publications

Labyrinth weirs provide an economic option for flow control structures in a variety of applications, including as spillways at dams. The cycles of labyrinth weirs are typically placed in a linear configuration. However, numerous projects place labyrinth cycles along an arc to take advantage of reservoir conditions and dam alignment, and to reduce construction costs such as narrowing the spillway chute. Practitioners must optimize more than 10 geometric variables when developing a head–discharge relationship. This is typically done using the following tools: empirical relationships, numerical modeling, and physical modeling. This study applied a new tool, machine learning, to the analysis …

Computational Regiospecific Analysis Of Brain Lipidomic Profiles, Austin Ahlstrom

Undergraduate Honors Theses

Mass spectrometry provides an extensive data set that can prove unwieldy for practical analytical purposes. Applying programming and machine learning methods to automate region analysis in DESI mass spectrometry of mouse brain tissue can help direct and refine such an otherwise unusable data set. The results carry promise of faster, more reliable analysis of this type, and yield interesting insights into molecular characteristics of regions of interest within these brain samples. These results have significant implications in continued investigation of molecular processes in the brain, along with other aspects of mass spectrometry, collective analysis of biological molecules (i.e. omics), and …

Essays On Cloud Computing Analytics, Vivek Kumar Singh

USF Tampa Graduate Theses and Dissertations

This dissertation research focuses on two key aspects of cloud computing research – pricing and security using data-driven techniques such as deep learning and econometrics. The first dissertation essay (Chapter 1) examines the adoption of spot market in cloud computing and builds IT investment estimation models for organizations adopting cloud spot market. The second dissertation essay (Chapter 2 and 3) studies proactive threat detection and prediction in cloud computing. The final dissertation essay (Chapter 4) develops a secured cloud files system which protects organizations using cloud computing in accidental data leaks.

Interim Performance Report, Lg‐71‐16‐0152‐16, Extending Intelligent Computational Image Analysis For Archival Discovery, March 2019, Elizabeth Lorang, Leen-Kiat Soh, John O'Brien

CDRH Grant Reports

The primary goal of "Extending Intelligent Computational Image Analysis for Archival Discovery" is to investigate the use of image analysis as a methodology for content identification, description, and information retrieval in digital libraries and other digitized collections. Building on work started under a National Endowment for the Humanities' Office of Digital Humanities Start-up Grant, our IMLS project seeks to 1) analyze and verify our previously developed image analysis approach and extend it so that it is newspaper agnostic, type agnostic, and language agnostic; 2) scale and revise the intelligent image analysis approach and determine the ideal balance between precision and …

Noise-Tolerant Modular Neural Network System For Classifying Ecg Signal, Alberto Ochoa, Luis J. Mena, Vanessa G. Felix, Apolinar Gonzalez, Walter Mena, Gladys E. Maestre

School of Medicine Publications

Millions of electrocardiograms (ECG) are interpreted every year, requiring specialized training for accurate interpretation. Because automated and accurate classification ECG signals will improve early diagnosis of heart condition, several neural network (NN) approaches have been proposed for classifying ECG signals. Current strategies for a critical step, the preprocessing for noise removal, are still unsatisfactory. We propose a modular NN approach based on artificial noise injection, to improve the generalization capability of the resulting model. The NN classifier initially performed a fairly accurate recognition of four types of cardiac anomalies in simulated ECG signals with minor, moderate, severe, and extreme noise, …