Digital Commons Network^™

Divide-And-Conquer Distributed Learning: Privacy-Preserving Offloading Of Neural Network Computations, Lewis C.L. Brown

Graduate Theses and Dissertations

Machine learning has become a highly utilized technology to perform decision making on high dimensional data. As dataset sizes have become increasingly large so too have the neural networks to learn the complex patterns hidden within. This expansion has continued to the degree that it may be infeasible to train a model from a singular device due to computational or memory limitations of underlying hardware. Purpose built computing clusters for training large models are commonplace while access to networks of heterogeneous devices is still typically more accessible. In addition, with the rise of 5G networks, computation at the edge becoming …

Machine Learning-Based Event Generator, Yasir Alanazi

Computer Science Theses & Dissertations

Monte Carlo-based event generators have been the primary source for simulating particle collision experiments for the study of interesting physics scenarios. Monte Carlo generators rely on theoretical assumptions, which limit their ability to capture the full range of possible correlations between particle’s momenta. In addition, the simulations of the complete pipeline often take minutes to generate a single event even with the help of supercomputers.

In recent years, much attention has been devoted to the development of machine learning event generators. They demonstrate attractive advantages, including fast simulations, data compression, and being agnostic of theoretical assumptions. However, most of the …

Advancing Statistical Learning And Decision Modeling Using Irregularly-Sampled Multivariate Data For Managing Respiratory Diseases, Maryam Alimohammadi

Graduate Theses and Dissertations

Complex healthcare systems require efficient and effective data-driven decision making in various aspects. As patient data becomes more available, advanced statistical learning and machine learning techniques are applied to improve data-driven decision making. However, patient health data, including clinical trial data, medical records, and electronic health records, are associated with several challenges. Patient health data includes medical information of a patient that may includedemographics, information relating to their health or illness, medications and treatments, etc. They are a combination of static and time series variables, with many censoring and missingness in the data, and are irregularly sampled in most cases. …

Predicting The Stability Of Open Stopes Using Machine Learning, Alicja Szmigiel, Derek B. Apel

Journal of Sustainable Mining

The Mathews stability graph method was presented for the first time in 1980. This method was developed to assess the stability of open stopes in different underground conditions, and it has an impact on evaluating the safety of underground excavations. With the development of technology and growing experience in applying computer sciences in various research disciplines, mining engineering could significantly benefit by using Machine Learning. Applying those ML algorithms to predict the stability of open stopes in underground excavations is a new approach that could replace the original graph method and should be investigated. In this research, a Potvin database …

A Review Of Risk Concepts And Models For Predicting The Risk Of Primary Stroke, Elizabeth Hunter, John D. Kelleher

Articles

Predicting an individual's risk of primary stroke is an important tool that can help to lower the burden of stroke for both the individual and society. There are a number of risk models and risk scores in existence but no review or classification designed to help the reader better understand how models differ and the reasoning behind these differences. In this paper we review the existing literature on primary stroke risk prediction models. From our literature review we identify key similarities and differences in the existing models. We find that models can differ in a number of ways, including the …

Predicting Users’ Personality On Social Media: A Comparative Study Of Different Machine Learning Techniques, Ali Saadi Al-Fallooji, Ahmed Al-Azawei

Karbala International Journal of Modern Science

The use of social media sites (SMSs) becomes ubiquitous worldwide as the number of users is noticeably increasing. This has led to exploiting such sites by market, business, and educational companies to deliver content that meets users’ personal needs. However, this requires identifying users’ personalities to respond to their individual preferences. This research aims at (1) analyzing users' posts on SMSs to predict their personality based on the Meyers-Briggs Type Indicator (MBTI) model, (2) comparing the performance accuracy of different preprocessing and data mining techniques, and (3) improving the prediction accuracy of users' personality types. The used dataset includes 8668 …

An Empirical Study Of Artifacts And Security Risks In The Pre-Trained Model Supply Chain, Wenxin Jiang, Nicholas Synovic, Rohan Sethi, Aryan Indarapu, Matt Hyattt, Taylor R. Schorlemmer, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Deep neural networks achieve state-of-the-art performance on many tasks, but require increasingly complex architectures and costly training procedures. Engineers can reduce costs by reusing a pre-trained model (PTM) and fine-tuning it for their own tasks. To facilitate software reuse, engineers collaborate around model hubs, collections of PTMs and datasets organized by problem domain. Although model hubs are now comparable in popularity and size to other software ecosystems, the associated PTM supply chain has not yet been examined from a software engineering perspective.

We present an empirical study of artifacts and security features in 8 model hubs. We indicate the potential …

Machine Learning With Gradient-Based Optimization Of Nuclear Waste Vitrification With Uncertainties And Constraints, Lagrande Gunnell, Kyle Manwaring, Xiaonan Lu, Jacob Reynolds, John Vienna, John Hedengren

Faculty Publications

Gekko is an optimization suite in Python that solves optimization problems involving mixed-integer, nonlinear, and differential equations. The purpose of this study is to integrate common Machine Learning (ML) algorithms such as Gaussian Process Regression (GPR), support vector regression (SVR), and artificial neural network (ANN) models into Gekko to solve data based optimization problems. Uncertainty quantification (UQ) is used alongside ML for better decision making. These methods include ensemble methods, model-specific methods, conformal predictions, and the delta method. An optimization problem involving nuclear waste vitrification is presented to demonstrate the benefit of ML in this field. ML models are compared …

Open-Source Clinical Machine Learning Models: Critical Appraisal Of Feasibility, Advantages, And Challenges, Keerthi B. Harish, W. Nicholson Price Ii, Yindalon Aphinyanaphongs

Articles

Machine learning applications promise to augment clinical capabilities and at least 64 models have already been approved by the US Food and Drug Administration. These tools are developed, shared, and used in an environment in which regulations and market forces remain immature. An important consideration when evaluating this environment is the introduction of open-source solutions in which innovations are freely shared; such solutions have long been a facet of digital culture. We discuss the feasibility and implications of open-source machine learning in a health care infrastructure built upon proprietary information. The decreased cost of development as compared to drugs and …

Investigating Students' Interpretations Of Ecological Food Webs, Christopher Neil Grissett

USF Tampa Graduate Theses and Dissertations

To better prepare undergraduate students for current and future biological challenges, scientists, educators and researchers in the Vision and Change report recommended five core conceptual areas essential for the improvement of biological literacy, one of which is biological systems. Systems are an identified core concept that may help promote biological literacy. One example of a system that students have difficulty understanding is an ecological food web, which consists of parts or components interacting with one another to perform a given phenomenon. The intricacies of this system tend to confuse students and can produce naïve conceptions that could hinder future learning …

Design Of Secure Communication Schemes To Provide Authentication And Integrity Among The Iot Devices, Vidya Rao Dr.

Technical Collection

The fast growth in Internet-of-Things (IoT) based applications, has increased the number of end-devices communicating over the Internet. The end devices are made with fewer resources and are low battery-powered. These resource-constrained devices are exposed to various security and privacy concerns over publicly available Internet communication. Thus, it becomes essential to provide lightweight security solutions to safeguard data and user privacy. Elliptic Curve Cryptography (ECC) can be used to generate the digital signature and also encrypt the data. The method can be evaluated on a real-time testbed deployed using Raspberry Pi3 devices and every message transmitted is subjected to ECC. …

Application Of Machine Learning And Cyber Security In Smart Grid, Soham Dutta Dr.

Technical Collection

Unplanned islanding of microgrids is a major hindrance in providing continuous power supply to the critical loads. The detection of these islanding instants needs to be very fast so that the distributed generators (DG) are able to take control actions in minimum time. Due to high quality data at a rapid rate, micro phasor measurement unit (μ-PMU) are becoming widely popular in distribution system and micro grids. These μ-PMUs can be leveraged for island detection. However, the working of μ-PMU is hugely dependent on communication network for data transmission which is prone to cyber-attacks. In view of the above facts, …

Anti-Phishing Tools: State Of The Art And Detection Efficiencies, M. F. Alghenaim, N. A. Abu Bakar, F. Abdul Rahim

Applied Mathematics & Information Sciences

A phishing attack is a process of obtaining a customers private data, whether by using phishing emails or fake websites. With every new development on the Internet, the attackers means of phishing attacks develop, requiring more powerful phishing tools to counter these attacks. The Internet has become an essential part of the personal and social life of the public and governments, institutions, and companies all over the world. This means that Internet users need tools to protect against phishing attack types and web risks, which may cause personal, institutional, financial, and informational damage. Hence, this study reviews anti-phishing attack tools …

Anti-Phishing Tools: State Of The Art And Detection Efficiencies, M. F. Alghenaim, N. A. Abu Bakar, F. Abdul Rahim

Applied Mathematics & Information Sciences

A phishing attack is a process of obtaining a customers private data, whether by using phishing emails or fake websites. With every new development on the Internet, the attackers means of phishing attacks develop, requiring more powerful phishing tools to counter these attacks. The Internet has become an essential part of the personal and social life of the public and governments, institutions, and companies all over the world. This means that Internet users need tools to protect against phishing attack types and web risks, which may cause personal, institutional, financial, and informational damage. Hence, this study reviews anti-phishing attack tools …

Designing With And For Youth: A Participatory Design Research Approach For Critical Machine Learning Education, Golnaz Arastoopour Irgens, Ibrahim Adisa, Cinamon Bailey, Hazel Vega Quesada

Publications

As big data algorithm usage becomes more ubiquitous, it will become critical for all young people, particularly those from historically marginalized populations, to have a deep understanding of data science that empowers them to enact change in their local communities and globally. In this study, we explore the concept of critical machine learning: integrating machine learning knowledge content with social, ethical, and political effects of algorithms. We modified an intergenerational participatory design approach known as cooperative inquiry to co-design a critical machine learning educational program with and for youth ages 9 - 13 in two after-school centers in the southern …

Using Artificial Intelligence In The Law Review Submissions Process, Brenda M. Simon

Faculty Scholarship

The use of artificial intelligence to help editors examine law review submissions may provide a way to improve an overburdened system. This Article is the first to explore the promise and pitfalls of using artificial intelligence in the law review submissions process. Technology-assisted review of submissions offers many possible benefits. It can simplify preemption checks, prevent plagiarism, detect failure to comply with formatting requirements, and identify missing citations. These efficiencies may allow editors to address serious flaws in the current selection process, including the use of heuristics that may result in discriminatory outcomes and dependence on lower-ranked journals to conduct …

A Bibliometric Analysis Of Machine Learning Econometrics In Asset Pricing, Hector O. Zapata, Supratik Mukhopadhyay

Faculty Publications

Machine learning (ML) is a novel method that has applications in asset pricing and that fits well within the problem of measurement in economics. Unlike econometrics, ML models are not designed for parameter estimation and inference, but similar to econometrics, they address, and may be better suited for, problems of prediction. While some ML methods have been applied in econometrics for decades, their success in prediction has been limited, and examples of this abound in the asset pricing literature. In recent years, the ML literature has advanced new, more efficient, computation methods for regularization, modeling nonlinearity, and improved out-of-sample prediction. …

Investigating Bloom's Cognitive Skills In Foundation And Advanced Programming Courses From Students' Discussions, Joel Jer Wei Lim, Gottipati Swapna, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

Programming courses provide students with the skills to develop complex business applications. Teaching and learning programming is challenging, and collaborative learning is proposed to help with this challenge. Online discussion forums promote networking with other learners such that they can build knowledge collaboratively. It aids students open their horizons of thought processes to acquire cognitive skills. Cognitive analysis of discussion is critical to understand students' learning process. In this paper, we propose Bloom's taxonomy based cognitive model for programming discussion forums. We present machine learning (ML) based solution to extract students' cognitive skills. Our evaluations on compupting courses show that …

Hip Osteoarthritis: A Novel Network Analysis Of Subchondral Trabecular Bone Structures, Mohsen Dorraki, Dzenita Muratovic, Anahita Fouladzadeh, Johan W Verjans, Andrew Allison, David M Findlay, Derek Abbott

Faculty, Staff and Student Publications

Hip osteoarthritis (HOA) is a degenerative joint disease that leads to the progressive destruction of subchondral bone and cartilage at the hip joint. Development of effective treatments for HOA remains an open problem, primarily due to the lack of knowledge of its pathogenesis and a typically late-stage diagnosis. We describe a novel network analysis methodology for microcomputed tomography (micro-CT) images of human trabecular bone. We explored differences between the trabecular bone microstructure of femoral heads with and without HOA. Large-scale automated extraction of the network formed by trabecular bone revealed significant network properties not previously reported for bone. Profound differences …

Personal Comfort Models Based On A 6‐Month Experiment Using Environmental Parameters And Data From Wearables, Federico Tartarini, Stefano Schiavon, Matias Quintana, Clayton Miller

Research Collection College of Integrative Studies

Personal thermal comfort models are a paradigm shift in predicting how building occupants perceive their thermal environment. Previous work has critical limitations related to the length of the data collected and the diversity of spaces. This paper outlines a longitudinal field study comprising 20 participants who answered Right-Here-Right-Now surveys using a smartwatch for 180 days. We collected more than 1080 field-based surveys per participant. Surveys were matched with environmental and physiological measured variables collected indoors in their homes and offices. We then trained and tested seven machine learning models per participant to predict their thermal preferences. Participants indicated 58% of …

Generating Realistic Cyber Data For Training And Evaluating Machine Learning Classifiers For Network Intrusion Detection Systems, Marc W. Chalé, Nathaniel D. Bastian

Faculty Publications

No abstract provided.

From Machine Learning To Deep Learning: A Comprehensive Study Of Alcohol And Drug Use Disorder, Banafsheh Rekabdar, David L. Albright, Haelim Jeong, Sameerah Talafha

Computer Science Faculty Publications and Presentations

This study aims to train and validate machine learning and deep learning models to identify patients with risky alcohol and drug misuse in a Screening, Brief Intervention, and Referral to Treatment (SBIRT) program. An observational cohort of 6978 adults was admitted in the western region of Alabama at three medical facilities between January and December of 2019. Data were cleaned and pre-processed using data imputation techniques and an augmented sampling data method. The primary analysis involved the multi-class classification of alcohol and drug misuse. Our study shows that accurate identification of alcohol and drug use screening instrument scores was best …

Finite Element-Based Machine Learning Model For Predicting The Mechanical Properties Of Composite Hydrogels, Yasin Shokrollahi, Pengfei Dong, Peshala T. Gamage, Nashaita Patrawalla, Vipuil Kishore, Hozhabr Mozafari, Linxia Gu

Department of Mechanical and Materials Engineering: Faculty Publications

In this study, a finite element (FE)-based machine learning model was developed to predict the mechanical properties of bioglass (BG)-collagen (COL) composite hydrogels. Based on the experimental observation of BG-COL composite hydrogels with scanning electron microscope, 2000 microstructural images with randomly distributed BG particles were created. The BG particles have diameters ranging from 0.5 μm to 1.5 μm and a volume fraction from 17% to 59%. FE simulations of tensile testing were performed for calculating the Young’s modulus and Poisson’s ratio of 2000 microstructures. The microstructural images and the calculated Young’s modulus and Poisson’s ratio by FE simulation were used …

Measurement In Chemistry, Mathematics, And Physics Education: Student Explanations Of Organic Chemistry Reaction Mechanisms And Instructional Practices In Introductory Courses, Brandon J. Yik

USF Tampa Graduate Theses and Dissertations

The work in this dissertation is presented in two parts. The first part (Chapters 3 and 4) details work relating to students’ explanations of reaction mechanisms in organic chemistry. The second part (Chapters 5 and 6) details work relating to the evaluating the uptake of research-based instructional practices in introductory chemistry, mathematics, and physics courses.

To evaluate learning of organic chemistry reactions, instructors must ask students to construct written explanations of reaction mechanisms. Written assessments should focus on what is happening and why it is happening to promote deeper student understanding. However, for instructors to gain insight into students’ understanding, …

Emotion Quantification Using Variational Quantum State Fidelity Estimation, Jaiteg Singh, Farman Ali, Babar Shah, Kamalpreet Singh Bhangu, Daehan Kwak

All Works

Sentiment analysis has been instrumental in developing artificial intelligence when applied to various domains. However, most sentiments and emotions are temporal and often exist in a complex manner. Several emotions can be experienced at the same time. Instead of recognizing only categorical information about emotions, there is a need to understand and quantify the intensity of emotions. The proposed research intends to investigate a quantum-inspired approach for quantifying emotional intensities in runtime. The inspiration comes from manifesting human cognition and decision-making capabilities, which may adopt a brief explanation through quantum theory. Quantum state fidelity was used to characterize states and …

Tntdetectai: A Deep Learning Model For Automated Detection And Counting Of Tunneling Nanotubes In Microscopy Images, Yasin Ceran, Hamza Ergüder, Katherine Ladner, Sophie Korenfeld, Karina Deniz, Sanyukta Padmanabhan, Phillip Wong, Murat Baday, Thomas Pengo, Emil Lou, Chirag B Patel

Faculty, Staff and Student Publications

BACKGROUND: Tunneling nanotubes (TNTs) are cellular structures connecting cell membranes and mediating intercellular communication. TNTs are manually identified and counted by a trained investigator; however, this process is time-intensive. We therefore sought to develop an automated approach for quantitative analysis of TNTs.

METHODS: We used a convolutional neural network (U-Net) deep learning model to segment phase contrast microscopy images of both cancer and non-cancer cells. Our method was composed of preprocessing and model development. We developed a new preprocessing method to label TNTs on a pixel-wise basis. Two sequential models were employed to detect TNTs. First, we identified the regions …

A Machine Learning Model For The Identification Of The Holy Quran Reciter Utilizing K-Nearest Neighbor And Artificial Neural Networks, Meshal Mohammed Al Anazi, Osama R. Shahin

Information Sciences Letters

The method of identification of the Holy Quran reciter, which is entered on the various features of the acoustic wave, is referred to as the Holy Quran Reciter Identification. The Muslim communitys Holy Book is the Holy Quran. Listening to or reading the Holy Quran is one of the obligatory activities for Muslims. This research proposes a machine learning model for identifying the Holy Quran reciter using a machine learning language. Here, the presented system comprises the essential phases for a voice recognition system encompassing the processes of classification, extraction of features, preprocessing, and data acquisition. Moreover, the voices of …

Improving Protein Succinylation Sites Prediction Using Embeddings From Protein Language Model, Suresh Pokharel, Pawel Pratyush, Michael Heinzinger, Robert H. Newman, Dukka Kc

Michigan Tech Publications, Part 1

Protein succinylation is an important post-translational modification (PTM) responsible for many vital metabolic activities in cells, including cellular respiration, regulation, and repair. Here, we present a novel approach that combines features from supervised word embedding with embedding from a protein language model called ProtT5-XL-UniRef50 (hereafter termed, ProtT5) in a deep learning framework to predict protein succinylation sites. To our knowledge, this is one of the first attempts to employ embedding from a pre-trained protein language model to predict protein succinylation sites. The proposed model, dubbed LMSuccSite, achieves state-of-the-art results compared to existing methods, with performance scores of 0.36, 0.79, 0.79 …

Netbce: An Interpretable Deep Neural Network For Accurate Prediction Of Linear B-Cell Epitopes, Haodong Xu, Zhongming Zhao

Faculty, Staff and Student Publications

Identification of B-cell epitopes (BCEs) plays an essential role in the development of peptide vaccines and immuno-diagnostic reagents, as well as antibody design and production. In this work, we generated a large benchmark dataset comprising 124,879 experimentally supported linear epitope-containing regions in 3567 protein clusters from over 1.3 million B cell assays. Analysis of this curated dataset showed large pathogen diversity covering 176 different families. The accuracy in linear BCE prediction was found to strongly vary with different features, while all sequence-derived and structural features were informative. To search more efficient and interpretive feature representations, a ten-layer deep learning framework …

Multi-Label Prediction For Political Text-As-Data, Aaron Erlich, Stefano G. Dantas, Benjamin E. Bagozzi, Daniel Berliner, Brian Palmer-Rubin

Political Science Faculty Research and Publications

Political scientists increasingly use supervised machine learning to code multiple relevant labels from a single set of texts. The current “best practice” of individually applying supervised machine learning to each label ignores information on inter-label association(s), and is likely to under-perform as a result. We introduce multi-label prediction as a solution to this problem. After reviewing the multi-label prediction framework, we apply it to code multiple features of (i) access to information requests made to the Mexican government and (ii) country-year human rights reports. We find that multi-label prediction outperforms standard supervised learning approaches, even in instances where the correlations …