Digital Commons Network^™

Does Accuracy Matter?: Methodological Considerations When Using Automated Speech-To-Text For Social Science Research, Steven J. Pentland, Christie M. Fuller, Lee A. Spitzley, Douglas P. Twitchell

IT and Supply Chain Management Faculty Publications and Presentations

The analysis of spoken language has been integral to a breadth of research in social science and beyond. However, for analyses to occur with efficiency, language must be in the form of computer-readable text. Historically, the speech-to-text process has occurred manually using human transcriptionists. Automated speech recognition (ASR) is advertised as an efficient and inexpensive alternative, but research shows this method of speech-to-text is prone to error. This paper investigates the viability of using error prone ASR transcriptions as part of the methodological process of language analysis. Results show that at the individual feature level, analysis of ASR transcriptions differ …

Predicting Microstructure Evolution In Alloys Using Deep Learning, Benjamin Mullins Rhoads

Electronic Theses and Dissertations

Modeling the microstructure evolution and linking them to materials properties is critical in establishing processing-microstructure-property linkage in materials. In this project, the evolution of microstructure of Fe-C alloys is modeled using phase field simulations to understand the behavior of these alloys under various cooling temperatures and initial carbon concentrations. However, these simulations require significant computational resources. Therefore, in this thesis, a convolutional neural network (CNN) and gated recurrent unit (GRU) are coupled with phase field simulations to predict the solidification of Fe-C alloys. In addition to the data-driven approach, the solid-liquid interfacial energy is incorporated during the training process, giving …

Context Aware Neural Machine Translation Using Graph Encoders, Saurabh Kale

Master's Projects

Machine translation presents its root in the domain of textual processing that focuses on the usage of computer software for the purpose of translation of sentences. Neural machine translation follows the same idea and integrates machine learning with the help of neural networks.Various techniques are being explored by researchers and are famously used by Google Translate, Bing Microsoft Translator, Deep Translator, etc. However, these neural machine translation techniques do not incorporate the context of the sentences and are only determined by the phrasesor sentence structure. This report explores the neural machine translation technique dedicated to context-aware translations. It also provides …

Interest-Based Recommendation System Using Gmail Topic Modelling, Pranav Ghaskadbi

Master's Projects

Emails are a fundamental part of modern communication. Much of communicative discourse in modern society occurs over email, resulting in personal collections for each mail user which are rich in latent user’s interests. Conventional recommendation systems require historical data of user activity and interactions to derive user interests. The absence of activity and interaction data poses an interesting challenge for generating relevant recommendations for users. We were motivated to investigate approaches to identify user interests in the absence of historical data to generate personalized content recommendations. There is opportunity to derive user interests from email data, which can be used …

Evaluation Of Different Machine Learning, Deep Learning And Text Processing Techniques For Hate Speech Detection, Nabil Shawkat

Graduate Theses/Dissertations

Social media has become a domain that involves a lot of hate speech. Some users feel entitled to engage in abusive conversations by sending abusive messages, tweets, or photos to other users. It is critical to detect hate speech and prevent innocent users from becoming victims. In this study, I explore the effectiveness and performance of various machine learning methods employing text processing techniques to create a robust system for hate speech identification. I assess the performance of Naïve Bayes, Support Vector Machines, Decision Trees, Random Forests, Logistic Regression, and K Nearest Neighbors using three distinct datasets sourced from social …

Automated Loan Approval System For Banks, Abdulrahman Saeed Almheiri

Theses

Machine learning and deep learning have revolutionized industries. Businesses have seen a boost in revenue through the use of these techniques, including the multibillion-dollar loan and credit industry. This study aims to develop a machine learning model to approve or disapprove loan applications based on customer characteristics, using algorithms such as statistical models, tree- based models, boosting models, and voting/stacking models. An exploratory analysis was conducted to understand customer characteristics, and the decision tree model proved to have the best performance with high precision in loan approval prediction.

Advancing Internet Viewpoint Diversity: A Novel Algorithm And A Corpus Creation Tool, Jeffrey Harwell

CGU Theses & Dissertations

A fundamental requirement for Western democracy is an informed and engaged electorate with access to a wide range of viewpoints. However, concerns have arisen regarding how information technology affects the diversity of viewpoints available. In response to an increasingly polarized society and worries surrounding filter bubbles and algorithmic bias, this research presents a novel tool for constructing internet-based topical corpora and an algorithm tailored for viewpoint detection and the curation of diverse search results.Following a comprehensive exploration of viewpoint diversity through the lenses of mass media, social psychology, and information retrieval, this dissertation presents an approach to operationalize viewpoint diversity …

Machine-Learning-Based Vulnerability Detection And Classification In Internet Of Things Device Security, Sarah Bin Hulayyil, Shancang Li, Li Da Xu

Information Technology & Decision Sciences Faculty Publications

Detecting cyber security vulnerabilities in the Internet of Things (IoT) devices before they are exploited is increasingly challenging and is one of the key technologies to protect IoT devices from cyber attacks. This work conducts a comprehensive survey to investigate the methods and tools used in vulnerability detection in IoT environments utilizing machine learning techniques on various datasets, i.e., IoT23. During this study, the common potential vulnerabilities of IoT architectures are analyzed on each layer and the machine learning workflow is described for detecting IoT vulnerabilities. A vulnerability detection and mitigation framework was proposed for machine learning-based vulnerability detection in …

Feature Selection In High-Dimensional Space With Applications To Gene Expression Data, Nishan Pantha

Theses

Recent years have seen rapid growth in high-dimensional datasets. Most existing machine learning (ML) algorithms fail in high-dimensional settings where many features could be redundant. A critical process of feature selection is thus applied in such a setting that helps in identifying the most relevant features while removing redundant ones. With the increase in high dimensionality, one is also faced with problems of efficiency and interpretation in performing such selection methods. Therefore, this thesis proposes a “novel” feature selection framework that uses an ensemble of interpretable ML algorithms to perform feature selection and the ranking of final features. Finally, this …

Radiomics: A Methodological Guide And Its Applications To Acute Ischemic Stroke, Emily Avery

Yale Medicine Thesis Digital Library

The field of radiomics provides a quantitative approach to medical imaging, wherein a large number of features extracted from medical images are used to detect clinically relevant information that is invisible to the naked eye. This increasingly prevalentmethodology has facilitated improvements in the speed and efficacy of clinical decision-making across specialties. One area where radiomics can make a particular impact is acute stroke imaging. As “time is brain” in acute stroke triage, automated tools for patient evaluation have significant potential to improve outcomes by providing timely, objective data. The present work aimed to create radiomics models from admission CT angiographic …

Applications Of Digital Terrain Modeling To Address Problems In Geomorphology And Engineering Geology, Sarah Johnson

Theses and Dissertations--Earth and Environmental Sciences

This dissertation uses digital terrain modeling and computational methods to yield insight into three topics: 1) evaluating the influence of glacial topography on fluvial sediment transport in the Teton Range, WY, 2) integrating regional airborne lidar, UAV lidar, and structure from motion photogrammetry to characterize decadal-scale movement of slow-moving landslides in northern Kentucky, and 3) applying machine learning methods to surficial geologic mapping.

The role of topography as a boundary condition that controls the efficiency of fluvial erosion in the Teton Range, Wyoming, was investigated by using existing lidar data to delineate surficial geologic units, geometrically reconstruct the depth to …

A Survey On Artificial Intelligence-Based Acoustic Source Identification, Ruba Zaheer, Iftekhar Ahmad, Daryoush Habibi, Kazi Y. Islam, Quoc Viet Phung

Research outputs 2022 to 2026

The concept of Acoustic Source Identification (ASI), which refers to the process of identifying noise sources has attracted increasing attention in recent years. The ASI technology can be used for surveillance, monitoring, and maintenance applications in a wide range of sectors, such as defence, manufacturing, healthcare, and agriculture. Acoustic signature analysis and pattern recognition remain the core technologies for noise source identification. Manual identification of acoustic signatures, however, has become increasingly challenging as dataset sizes grow. As a result, the use of Artificial Intelligence (AI) techniques for identifying noise sources has become increasingly relevant and useful. In this paper, we …

Risk Assessment And Immigration Court, Richard Frankel

Washington and Lee Law Review

Risk assessment and algorithmic tools have become increasingly popular in recent years, particularly with respect to detention and incarceration decisions. The emergence of big data and the increased sophistication of algorithmic design hold the promise of more accurately predicting whether an individual is dangerous or a flight risk, overcoming human bias in decision-making, and reducing detention without compromising public safety. But these tools also carry the potential to exacerbate racial disparities in incarceration, create a false veneer of objective scientific accuracy, and spawn opaque decision-making by “black box” computer programs.

While scholars have focused much attention on how judges in …

Investigating The Effects Of Network Dynamics On Quality Of Delivery Prediction And Monitoring For Video Delivery Networks, Obinna C. Izima

Doctoral

Video streaming over the Internet requires an optimized delivery system given the advances in network architecture, for example, Software Defined Networks. Machine Learning (ML) models have been deployed in an attempt to predict the quality of the video streams. Some of these efforts have considered the prediction of Quality of Delivery (QoD) metrics of the video stream in an effort to measure the quality of the video stream from the network perspective. In most cases, these models have either treated the ML algorithms as black-boxes or failed to capture the network dynamics of the associated video streams.

This PhD investigates …

Learning Infused Quantum-Classical Distributed Optimization Technique For Power Generation Scheduling, Reza Mahroo, Amin Kargarian

Faculty Publications

The advent of quantum computing can potentially revolutionize how complex problems are solved. This article proposes a two-loop quantum-classical solution algorithm for generation scheduling by infusing quantum computing, machine learning, and distributed optimization. The aim is to facilitate employing noisy near-term quantum machines with a limited number of qubits to solve practical power system optimization problems, such as generation scheduling. The outer loop is a three-block quantum alternating direction method of multipliers (QADMM) algorithm that decomposes the generation scheduling problem into three subproblems, including one quadratically unconstrained binary optimization (QUBO) and two non-QUBOs. The inner loop is a trainable quantum …

Machine Learning Approach For Predicting Bridge Components’ Condition Ratings, Md Manik Mia, Sabarethinam Kameshwar

Faculty Publications

Information on bridge condition rating is critical to make decisions regarding rehabilitation or replacement of bridges. Currently, bridge components’ condition ratings are evaluated manually using inspection reports. Markov chain and Petri net models are most commonly used for predicting future values of bridge parameters, however, applicability of these models for a regional or statewide portfolio of bridges may be limited. The existing data based models have low prediction accuracy. Hence, a data and machine learning based approach is presented herein for predicting the future condition values of major components—deck, superstructure and substructure—in a portfolio of bridges with an objective to …

The Basil Technique: Bias Adaptive Statistical Inference Learning Agents For Learning From Human Feedback, Jonathan Indigo Watson

Theses and Dissertations--Computer Science

We introduce a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown parameters. We present both the general framework for our technique and specific algorithms for biases drawn from a normal distribution. We evaluate our approach across various environments and tasks, comparing it to interactive and non-interactive machine learning methods, including deep learning techniques, using human trainers and a synthetic oracle with feedback distorted to varying degrees. …

Exploring Gender Bias In Semantic Representations For Occupational Classification In Nlp: Techniques And Mitigation Strategies, Joseph Michael O'Carroll

Dissertations

Gender bias in Natural Language Processing (NLP) models is a non-trivial problem that can perpetuate and amplify existing societal biases. This thesis investigates gender bias in occupation classification and explores the effectiveness of different debiasing methods for language models to reduce the impact of bias in the model’s representations. The study employs a data-driven empirical methodology focusing heavily on experimentation and result investigation. The study uses five distinct semantic representations and models with varying levels of complexity to classify the occupation of individuals based on their biographies.

Probability Expressions In Ai Decision Support: Impacts On Human+Ai Team Performance, Elias Spinn

Dissertations

AI decision support systems aim to assist people in highly complex and consequential domains to make efficient, effective, and high-quality decisions. AI alone cannot be guaranteed to be correct in these complex decision tasks, and a human is often needed to ensure decision accuracy. The ambition is for these human+ AI teams to perform better together than either would individually. To realise this, decision makers must trust their AI partners appropriately, knowing when to rely on their recommendations and when to be sceptical. However, research has shown that decision makers often either mistrust and underutilise these systems, or trust them …

Architectural Design Of A Blockchain-Enabled, Federated Learning Platform For Algorithmic Fairness In Predictive Health Care: Design Science Study, Xueping Liang, Juan Zhao, Yan Chen, Eranga Bandara, Sachin Shetty

VMASC Publications

Background: Developing effective and generalizable predictive models is critical for disease prediction and clinical decision-making, often requiring diverse samples to mitigate population bias and address algorithmic fairness. However, a major challenge is to retrieve learning models across multiple institutions without bringing in local biases and inequity, while preserving individual patients' privacy at each site.

Objective: This study aims to understand the issues of bias and fairness in the machine learning process used in the predictive health care domain. We proposed a software architecture that integrates federated learning and blockchain to improve fairness, while maintaining acceptable prediction accuracy and minimizing overhead …

Lawyering Somewhere Between Computation And The Will To Act: A Digital Age Reflection, Jeffrey M. Lipshaw

Suffolk University Law School Faculty Works

This is a reflection on machine and human contributions to lawyering in the digital age. Increasingly capable machines can already unleash massive processing power on vast stores of discovery and research data to assess relevancies and, at times, to predict legal outcomes. At the same time, there is wide acceptance, at least among legal academics, of the conclusions from behavioral psychology that slow, deliberative “System 2” thinking (perhaps replicated computationally) needs to control the heuristics and biases to which fast, intuitive “System 1” thinking is prone. Together, those trends portend computational deliberation – artificial intelligence or machine learning – substituting …

The Impact Of Climate Stresses In Water Quality Of Agricultural, Urban And Forested Watersheds In Rhode Island, Shiva Shrestha

Open Access Dissertations

Hydrological regime and nutrient dynamics are associated with hydrological setting of any watershed. Human interventions have direct and indirect impacts on these hydrologic setting and watershed response. The increasing anthropogenic pressure has continued to degrade the water quality. This may lead to eutrophication that can seriously harm the water quality and aquatic ecosystems (Vitousek 1997).

The effective mitigation strategies in land and water management practices should have good understand of water and nutrient fluxes in watershed and relating them to spatio-temporal hydrologic factors (Liang et al., 2020).

The best approaches of the management strategies should always start from monitoring and …

The Antimicrobial Peptide Database Is 20 Years Old: Recent Developments And Future Directions, Guangshun Wang

Journal Articles: Pathology and Microbiology

In 2023, the Antimicrobial Peptide Database (currently available at https://aps.unmc.edu) is 20-years-old. The timeline for the APD expansion in peptide entries, classification methods, search functions, post-translational modifications, binding targets, and mechanisms of action of antimicrobial peptides (AMPs) has been summarized in our previous Protein Science paper. This article highlights new database additions and findings. To facilitate antimicrobial development to combat drug-resistant pathogens, the APD has been re-annotating the data for antibacterial activity (active, inactive, and uncertain), toxicity (hemolytic and nonhemolytic AMPs), and salt tolerance (salt sensitive and insensitive). Comparison of the respective desired and undesired AMP groups produces new knowledge …

Comparing Poor And Favorable Outcome Prediction With Machine Learning After Mechanical Thrombectomy In Acute Ischemic Stroke, Matthias A. Mutke, Vince I. Madai, Adam Hilbert, Esra Zihni, Arne Potreck, Charlotte S. Weyland, Markus A. Mohlenbruch, Sabine Heiland, Peter A. Ringleb, Simon Nagel, Martin Beendszus, Dietmar Frey

Articles

Outcome prediction after mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO) is commonly performed by focusing on favorable outcome (modified Rankin Scale, mRS 0–2) after 3 months but poor outcome representing severe disability and mortality (mRS 5 and 6) might be of equal importance for clinical decision-making.

How Visual Stimuli Evoked P300 Is Transforming The Brain–Computer Interface Landscape: A Prisma Compliant Systematic Review, Jai Kalra, Prashasti Mittal, Nirmiti Mittal, Abhishek Arora, Utkarsh Tewari, Aviral Chharia, Rahul Upadhyay, Vinay Kumar, Luca Longo

Articles

Non-invasive Visual Stimuli evoked-EEGbased P300 BCIs have gained immense attention in recent years due to their ability to help patients with disability using BCI-controlled assistive devices and applications. In addition to the medical field, P300 BCI has applications in entertainment, robotics, and education. The current article systematically reviews 147 articles that were published between 2006-2021*. Articles that pass the pre-defined criteria are included in the study. Further, classification based on their primary focus, including article orientation, participants’ age groups, tasks given, databases, the EEG devices used in the studies, classification models, and application domain, is performed. The application-based classification considers …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyatt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis

Department of Electrical and Computer Engineering Faculty Publications

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Uncovering The Role Of Fat-Infiltrated Axillary Lymph Nodes In Obesity-Related Diseases With Statistical And Machine Learning Analyses, Qingyuan Song

Dartmouth College Ph.D Dissertations

The link between obesity and pathogenesis is a complex and multifaceted area of research that is yet to be fully understood. Ample evidence exists to demonstrate the direct relationship between excessive internal fat and various health conditions such as cancer, and metabolic and cardiovascular diseases. The infiltration of ectopic fat into axillary lymph nodes, observable on breast cancer screening images, has been shown to be correlated with body mass index (BMI) in women undergoing screening. This study aimed to explore the relationship between fat-infiltrated axillary lymph nodes (FIN) and obesity-related diseases, with the goal of evaluating the clinical value of …

A Machine Learning Framework For Hypersonic Vehicle Design Exploration, Atticus Beachy

Browse all Theses and Dissertations

The design of Hypersonic Vehicles (HVs) requires meeting multiple unconventional and often conflicting design requirements in a hostile, high-energy environment. The most fundamental difference between ordinary aerospace design and hypersonic flight is that the extreme conditions of hypersonic flight require parts to perform multiple functions and be tightly integrated, resulting in significant coupled effects. Critical couplings among the disciplines of aerodynamics, structures, propulsion, and thermodynamics must be investigated in the early stages of design exploration to reduce the risk of requiring major design changes and cost overruns later. In addition, due to a lack of validated test data within the …

Using Ml Algorithms To Predict Real Estate Units Valuations In Ajman, Heba Al Yazouri

Theses

This project applies machine learning algorithms to predict the real estate unit’s values in the emirates of Ajman. Adopting machine learning techniques to predict real estate unit prices helps us produce more accurate valuations. It allows us to use historical data that can’t be used in traditional valuation techniques.

Datasets from the Department of Land & Real Estate were used to run an exploratory analysis to explore the most critical factors influencing real estate unit prices in Ajman. It shows that the unit area is the most significant factor affecting Ajman's real estate unit prices. It also shows how the …

Federated Learning For Medical Image Classification, Danica Blazanovic

Electronic Theses and Dissertations 2020 - Present

Machine learning (ML) has traditionally been used to make predictive models by training on local data. However, due to concerns regarding privacy, it is not always possible to collect and combine data from different sources. On the other hand, if there are insufficient data available, it might not be possible to construct accurate models to produce meaningful outcomes. This is where Federated Learning comes to the rescue. Federated Learning (FL) represents a sophisticated distributed machine learning strategy that enables multiple devices hosted at different institutions such as hospitals, to collaboratively train a global model while ensuring that their respective data …