Digital Commons Network^™

Ai-Driven Credit Card Fraud Detection With Enhanced User Interaction, Toshi Bhat

Master's Projects

This thesis describes the development and testing of a unique system for detecting credit card fraud. The system employs graph neural networks (GNNs) and a real-time user interaction platform. The primary goal of this study is to use advanced machine learning methods and interactive technologies to improve fraud detection accuracy and the speed with which users can receive assistance. GraphSAGE, a type of GNN, was trained on a simulated set of credit card transactions, allowing the system to detect and predict fraud very accurately. Simulating a real-world transaction scenario is an important aspect of the project. In this case, the …

Screening For Adhd In Adult Patients With Epilepsy: Prevalence Of Symptoms And Challenges To Diagnosis, Afroz Shamim, Atul Maheshwari

Faculty, Staff and Students Publications

OBJECTIVE: Given the complex nature of seizure disorders and their treatments, ADHD may be underdiagnosed in this population. We hypothesized that a higher percentage of patients presenting to a seizure clinic would endorse ADHD symptoms compared to rates reported in the general population and that formal screening for ADHD symptoms would identify patients with previously undiagnosed comorbid ADHD.

METHODS: In this study, we surveyed 312 adults in a seizure clinic using the Adult ADHD Self-Report Scale (ASRS-v1.1).

RESULTS: We found that 90 patients (28.8%) screened positive with the ASRS-v1.1, but only nine of these patients were able to complete neuropsychological …

Frame Rate Enhancement Using Gans: A Deep Learning Approach, Shanmukah Sri Harsha Anivilla

Master's Projects

Videos are sequences of frames that are displayed continuously within a time frame, which creates the illusion. FPS is defined as the number of frames per second, and is crucial to determine the smoothness of motion or scene changes in the video. To improve the appearance of the videos, we can a technique called Frame Rate Enhancement. This is an approach to augment generated frames between pairs of frames using Generative Adversarial Networks. There are a few traditional techniques using Convolution Neural Networks and Optical Flow based methods, but they create unwanted artifacts such as blurring or ghosting and might …

Unveiling Gender Bias: An Eye-Tracking Analysis Of Scene Perception, Naga Srija Gopisetty

Master's Projects

Gender bias deeply affects how we perceive and interact with the world around us. This study examined how gender bias affects scene perception by using eye-tracking technology. The relation between gender bias and pupil dilation is examined utilizing art as a stimuli and also studied the underlying cognitive processes. This experiment combines image presentations along with input from participants, drawing on previous research in gender bias, cognitive psychology, and eye-tracking methodologies. The experiment design showcases a series of images to participants, subtly replacing one image during the trial, and then asks participants whether the

replacement took place. This study uses …

Exploring Gender Bias In Large Language Models: Cross-Linguistic Comparisons And Evaluation Letters Analysis, Athira Kumar

Master's Projects

Large language models (LLMs) play a significant role in modern human-computer interaction. They have exploded in popularity recently, becoming widely used for various tasks. However, concerns persist regarding potential biases within these models. This project investigates gender bias in the popular LLMs - GPT-3.5, GPT-4, Gemini, and LLAMA. The first part of our study focuses on analyzing biases using ambiguous sentences across three languages - English, Malayalam, and Tamil. We evaluate the LLMs to see if they associate occupations with commonly held gender stereotypes, by using specific professions within our test sentences. Through the use of two low-resource languages, this …

Continuous Subcutaneous Foslevodopa/Foscarbidopa Infusion For The Treatment Of Motor Fluctuations In Parkinson’S Disease: Considerations For Initiation And Maintenance, Filip Bergquist, Agnita J W Boon, Manon Bouchard, Sarah Bray, Sara Dhanani, Maurizio F Facheris, Nahome Fisseha, Eric Freire-Alvarez, Robert A Hauser, Anna Jeong, Jia Jia, Pavnit Kukreja, Michael J Soileau, Amy M Spiegel, Saritha Talapala, Arjun Tarakad, Enrique Urrea-Mendoza, Jorge Zamudio, Rajesh Pahwa

Faculty, Staff and Students Publications

BACKGROUND: As Parkinson's disease (PD) advances, management is challenged by an increasingly variable and inconsistent response to oral dopaminergic therapy, requiring special considerations by the provider. Continuous 24 h/day subcutaneous infusion of foslevodopa/foscarbidopa (LDp/CDp) provides steady dopaminergic stimulation that can reduce symptom fluctuation.

OBJECTIVE: Our aim is to review the initiation, optimization, and maintenance of LDp/CDp therapy, identify possible challenges, and share potential mitigations.

METHODS: Review available LDp/CDp clinical trial data for practical considerations regarding the management of patients during LDp/CDp therapy initiation, optimization, and maintenance based on investigator clinical trial experience.

RESULTS: LDp/CDp initiation, optimization, and maintenance can be …

Intelligent Caching Using Continuous Machine Learning In Named Data Networking, Sai Sameer Yanamandra

Master's Projects

Our project focuses on improving Named Data Networking (NDN), an alternative network architecture to traditional IP networks, particularly in unstable conditions where connections frequently drop, and data movement is unpredictable. In NDN, data is cached at various routers across the network, enhancing accessibility even amidst unstable connections. A key challenge we address is determining the optimal level of data redundancy in unstable scenarios. We aim to balance the need for data availability with the risk of excessive data duplication. Our solution involves developing a novel data caching approach for the NDN’s content store based on continuous machine learning. This method …

California Carbon Sequestration And Carbon Dioxide Pipeline Regulation In An Era Of Climate Change: Technology And Policy, Robert A. Mason

Master's Projects

This report serves primary purpose of finding prospective policies that could be useful in CARB’s new carbon sequestration program as mandated by S. B. 905. The bill states program goals and provides several objectives that direct the California Natural Resources Agency (CNRA), the California Air Resource Board (CARB), and the California Geological Survey (CGS, or just Survey) with various responsibilities. Curiously, S.B. 905 does not mention the Office of State Fire Marshal (OSFM or CalFire), although it has primary responsibility for issuing permits for hazardous pipelines as an agent of the federal Pipelines and Hazardous Materials Safety Administration (PHMSA).

Pipelines …

Multiple Sclerosis In Central America And Caribbean Countries: Frequency And Clinical Characterization Of An Emergent Disease, Roberto Weiser, Alexander Parajeles-Vindas, Ligia I Portillo Rivera, Ericka López Torres, Luis A García Valle, Alfredo Sanabria-Castro, César Abdón López, Pahola Araujo, Maria J Ayerdis Zamora, Andrea Balmaceda-Meza, Aron Benzadon Cohen, Awilda Candelario Cueto, Diego Castillo, Romy Castro-Escobar, Karla Z Corea Urbina, Anyeri De Peña Rivas, Octavio Duarte Sotelo, Temís Enamorado Claros, José L Giroud Benítez, Karla Gracia, Mario Larreategui, Jorge A Martínez Cerrato, Josmarlin P Medina Báez, Carlos E Menjivar Samayoa, Gustavo Miranda-Loria, Priscilla Monterrey-Alvarez, Lilliam A Morales Arguello, Michelle Ortiz, Carlos D Pérez Baldioceda, Lizeth Pinilla Aguilar, Luis C Rodríguez Salinas, Virginia Rodríguez-Moreno, Sebastián Rojas-Chaves, Norbel Román-Garita, Biany Santos Pujols, Carlos Valderrama, Ivonne Van Sijtveld, Indhira Zabala Angeles, Victor M Rivera, Blas Armien

Faculty, Staff and Students Publications

BACKGROUND: Multiple Sclerosis (MS) is a common neurological disease among white populations of European origin. Frequencies among Latin Americans continue to be studied, however, epidemiologic, and clinical characterization studies lack from Central American and Caribbean countries. Ethnicity in these countries is uniformly similar with a prevalent Mestizo population.

METHODS AND RESULTS: Data from January 2014 to December 2019 from Guatemala, El Salvador, Honduras, Nicaragua, Costa Rica, Panama, Dominican Republic, and Aruba on demographic, clinical, MRI and phenotypic traits were determined in coordinated studies: ENHANCE, a population-based, retrospective, observational study on incidence and clinical characteristics, and from the subgroup with MS …

Employing Large Language Models And Retrieval Augmented Generation For Enhanced Predictive Flexibility In Cancer Mortality Prediction, Mridang Kejriwal

Master's Projects

Today, cancer is a major health risk to thousands of people, and there are over a two-hundred different types of cancer. Luckily, over the past several years, the outcomes and survival rates have increased, all thanks to machine learning, specifically Recurrent Neural Networks (RNN) and Long Short-Term memory (LSTM) networks. However, the current prognostic models don’t allow healthcare professionals to adapt the variables to mimic all the different features of every type of cancer, resulting in a model that works but is not as accurate as it could be. This study explores improving the accuracy and adaptability of the current …

Temporal Dynamics In Diabetes Prediction: A Sensor-Driven Time-Series Exploration, Monica Meduri

Master's Projects

Diabetes is a lifelong illness that, if not detected or managed appropriately, turns into serious complications. Correct glucose forecasting is critical to ensuring timely interventions, thereby minimizing risks of hyperglycemia and hypoglycemia, and optimizing the management strategies of the disease. Classical machine learning models have been applied in the blood glucose forecasting problem for a long time, however, usage of transformer-based architectures is still scarce within the literature. Due to the self-attention mechanism, transformers can capture temporal relationships very effectively, which makes them suitable for time-series data. TFT is a novel framework proposed here to utilize time-series data from CGM …

Cisplatin Vestibulotoxicity: A Current Review

Faculty, Staff and Students Publications

Cisplatin, a commonly used chemotherapy drug, is well-established for its ototoxic effects, primarily attributed to the damage it inflicts on cochlear hair cells. However, its impact on the vestibular system remains inadequately understood. Here, we provide a comprehensive review of existing literature concerning cisplatin-induced vestibulotoxicity. Animal studies have shown that cisplatin induces a vestibular hair cell loss that is dose-dependent, with the severity of damage also varying according to the route of administration. Notably, intratympanic and systemic injections in animal models have manifested significant damage primarily to utricular hair cells, with a lesser degree of damage observed for the other …

Implicit Personality Detection From User Behaviour In Recommendation Systems, Uzma Zubair Shaikh

Master's Projects

Recommendation systems are an integral part of any business, and a crucial factor in determining their success as these systems help businesses in marketing their products to the right kind of audience. Conventional methods of building recommendation systems such as collaborative filtering and content-based recommendation, although effective, suffer from limitations such as cold start and the data sparsity problems. Moreover, these methods aim at finding similar products as user’s past interactions rather than personalizing the recommendations. The upsurge in use of social media, over-the-top content (OTT), and e-commerce platforms has made the task of personalizing recommendations imperative, leading to the …

Facial Expression Mood Classification Using Machine Learning, Tiantong Li

Master's Projects

Facial expression classification is a powerful tool for understanding human emotions, with applications spanning human-computer interaction, healthcare, and entertainment. By analyzing facial cues, systems can interpret emotional states and adapt their responses, creating more personalized and emotionally aware experiences. One emerging application of facial expression classification is in music recommendation systems, where user emotions are integrated to suggest music that aligns with their current mood. While prior research has primarily classified facial expressions into four emotion categories, this study broadens the scope to seven emotions: angry, disgust, fear, happy, neutral, sad, and surprise. The project evaluates four machine learning techniques—CNN, …

Cluster Analysis For Concept Drift Detection In Malware, Aniket Mishra

Master's Projects

The rapid evolution of malware presents significant challenges for detection systems. This is due to malware families adapting through feature manipulation and obfuscation, which causes concept drift. A clustering based approach is used to detect and adapt to these shifts. The KronoDroid dataset is segmented into batch sizes of 50 and analyzed with MiniBatch K-Means clustering. The silhouette coefficient is used to evaluate clustering quality, and help identify drift by detecting significant changes in cluster patterns. Concept drift will cause retraining of supervised classifiers, including Linear SVM, RF, MLP, and XGBoost. Three scenarios are used: static models, periodic retraining, and …

An Attributed And Diverse Encoder-Decoder Processing Technique For Anomaly Detection., Kenneth Antony John

Master's Projects

Attributed graphs are graphs that contain extra information about the attributes of nodes and edges. They can be used to model a plethora of real-world scenarios like social networks, bank transactions, and even academic citation data. Anomalies in such graphs can be irregularities or unusual patterns that are observed in the attributes or the structure of the graph. Anomaly detection in attributed networks is a crucial task, aiming to identify such anomalies. Existing methodologies use various deep learning techniques using graph neural networks, graph encoder-decoder architectures, and multi-layer perceptions. This study proposes a new approach to improve the existing methods …

Enhanced Inter-Satellite Routing With Multi-Path Selection And Congestion Modeling, Jaesung Yoo

Master's Projects

Satellite networks play a crucial role in global connectivity today and making efficient routing algorithms is crucial for optimal performance. While existing routing algorithms have made significant progress using machine learning techniques, they often overlook network congestion and multiple path availability. This report introduces an enhanced routing framework that builds upon LSTM-based predictive routing using dynamic congestion modeling and multi-path selection. Our approach introduces a busy state metric that tracks satellite memory utilization, allowing for adaptive path selection based on both distance and current network load. Through simulations using a constellation of 20 satellites, our enhanced algorithm demonstrates significant improvements …

Malware Detection Using Qr And Aztec Code Representations, Atharva Khadilkar

Master's Projects

In recent years, the use of image-based techniques for malware detection has gained prominence, with numerous studies demonstrating the efficacy of deep learning approaches such as convolutional neural networks (CNNs) in classifying images derived from executable files. In this paper, we consider an innovative method that relies on an image conversion process that consists of transforming executable files into QR and Aztec codes. These codes capture structural patterns in a format that may enhance the learning capabilities of CNNs. We design and implement CNN architectures tailored to the unique properties of these codes and apply them to a comprehensive analysis …

Thrombectomy In Stroke Patients With Low Alberta Stroke Program Early Computed Tomography Score: Is Modified Thrombolysis In Cerebral Infarction (Mtici) 2c/3 Superior To Mtici 2b?, Kazutaka Uchida, Steven Lin, Ilko Maier, Pascal Jabbour, Joon-Tae Kim, Stacey Quintero Wolfe, Ansaar Rai, Robert M Starke, Marios-Nikos Psychogios, Edgar A Samaniego, Adam Arthur, Shinichi Yoshimura, Hugo Cuellar, Jonathan A Grossberg, Ali Alawieh, Daniele G Romano, Omar Tanweer, Justin Mascitelli, Isabel Fragata, Adam Polifka, Joshua Osbun, Roberto Crosa, Charles Matouk, Min S Park, Michael R Levitt, Waleed Brinjikji, Mark Moss, Travis Dumont, Richard Williamson, Pedro Navia, Peter Kan, Reade De Leacy, Shakeel Chowdhry, Mohamad Ezzeldin, Alejandro M Spiotta, Sami Al Kasab

Faculty, Staff and Students Publications

BACKGROUND AND PURPOSE: Outcomes following mechanical thrombectomy (MT) are strongly correlated with successful recanalization, traditionally defined as modified Thrombolysis in Cerebral Infarction (mTICI) ≥2b. This retrospective cohort study aimed to compare the outcomes of patients with low Alberta Stroke Program Early Computed Tomography Score (ASPECTS; 2-5) who achieved mTICI 2b versus those who achieved mTICI 2c/3 after MT.

METHODS: This study utilized data from the Stroke Thrombectomy and Aneurysm Registry (STAR), which combined databases from 32 thrombectomy-capable stroke centers between 2013 and 2023. The study included only patients with low ASPECTS who achieved mTICI 2b, 2c, or 3 after MT …

Welcoming 2024: Supporting Students' Well-Being

Faculty, Staff and Students Publications

No abstract provided.

Population-Based Screening Strategies For Biliary Atresia In The Newborn: A Systematic Review And Meta-Analysis, Kristin Borovsky, Yemisi Takwoingi, Katie Scandrett, Mohan Pammi

Faculty, Staff and Students Publications

BACKGROUND: Newborn screening for biliary atresia (BA) may facilitate earlier diagnosis and intervention for improved clinical outcomes.

METHODS: We systematically reviewed the accuracy of population-based screening strategies for BA in the newborn using PRISMA-DTA guidelines. We included cohort or cross-sectional studies. The screening (index) tests included stool color card (SCC) and direct/conjugated bilirubin (DB/CB) and the reference standard was intraoperative cholangiogram. Meta-analysis was performed using random-effects logistic regression models.

RESULTS: We included 15 studies (1,816,722 participants) that assessed 5 different population-based screening strategies. QUADAS-2 assessment revealed high risk of bias for patient selection in one study and uncertain risks for …

Hepatic Failure And Hyperbilirubinemia Secondary To Hemolytic Disease Of The Newborn

Faculty, Staff and Students Publications

Anti-D antibody is the most common cause of hemolytic disease of the newborn (HDN). Other antigens have emerged, causing significant damage to the newborn. We report a case of a 31-week dichorionic diamniotic twin born emergently to a mother with anti-C and anti-D antibodies who required multiple percutaneous umbilical cord blood sampling (PUBS) and transfusions. Extensive resuscitation at birth was required due to severe anemia, hypovolemia, and prematurity. Ensuing liver damage occurred with subsequent profound coagulopathy, transaminitis, and direct hyperbilirubinemia that required significant support. This patient developed several unique findings including the inability to monitor oxygen saturations due to dermal …

Call The Experts: Identifying Stakeholders In The Long-Term Care Of Youth With Hypospadias, Walid A Farhat, Heidi W Brown, Jane Mahoney, Marisa E Hilliard, Kristina L Penniston

Faculty, Staff and Students Publications

Long-term follow-up for individuals with hypospadias remains a critical area of need, yet evidence-based guidelines for such follow-up are lacking, and the role of involvement of relevant experts is not yet established. Using our hypospadias-specific health-related quality of life conceptual framework and a subsequent qualitative study of prepubertal males and parents of males with hypospadias, we identified potential priorities for long-term follow-up of youth with hypospadias. Using thematic codes from our patient and parent interviews, we searched PubMed for relevant articles and identified the specialties represented by all the authors of these articles. Our search strategy revealed consistent expertise across …

5-Htp Inhibits Eosinophilia Via Intracellular Endothelial 5-Htrs; Snps In 5-Htrs Associate With Asthmatic Lung Function, Samantha L Mccarty, Jeremy E Green, Ryan P Ferrie, Jackson A Campbell, Samantha H Averill, Kenneth B Beckman, Leslie C Grammer, Celeste Eng, Pedro C Avila, Harold J Farber, William Rodriguez-Cintron, Jose R Rodriguez-Santana, Denise Serebrisky, Shannon M Thyne, Max A Seibold, Esteban G Burchard, Rajesh Kumar, Joan M Cook-Mills

Faculty, Staff and Students Publications

BACKGROUND: Previous research showed that 5-hydroxytryptophan (5HTP), a metabolic precursor of serotonin, reduces allergic lung inflammation by inhibiting eosinophil migration across endothelial monolayers.

OBJECTIVE: It is unknown if serotonin receptors are involved in mediating this 5HTP function or if serotonin receptor (HTR) single nucleotide polymorphisms (SNPs) associate with lung function in humans.

METHODS: Serotonin receptor subtypes were assessed by qPCR, western blot, confocal microscopy, pharmacological inhibitors and siRNA knockdown. HTR SNPs were assessed in two cohorts.

RESULTS: Pharmacological inhibition or siRNA knockdown of the serotonin receptors HTR1A or HTR1B in endothelial cells abrogated the inhibitory effects of 5HTP on eosinophil …

Using A Collaborative Learning Health System Approach To Improve Disease Activity Outcomes In Children With Juvenile Idiopathic Arthritis In The Pediatric Rheumatology Care And Outcomes Improvement Network, Cagri Yildirim-Toruner, Michelle Batthish, Danielle R Bullock, Jon M Burnham, Danielle C Fair, Kerry Ferraro, Suhas Ganguli, Mileka Gilbert, Beth S Gottlieb, Olha Halyabar, Melissa M Hazen, Ronald M Laxer, Tzielan C Lee, Alice Liu, Daniel J Lovell, Melissa L Mannion, Edward J Oberle, Nancy Pan, Michael Shishov, Jennifer E Weiss, Esi M Morgan

Faculty, Staff and Students Publications

INTRODUCTION: The Pediatric Rheumatology Care and Outcomes Improvement Network (PR-COIN) is a North American learning health network focused on improving outcomes of children with juvenile idiopathic arthritis (JIA). JIA is a chronic autoimmune disease that can lead to morbidity related to persistent joint and ocular inflammation. PR-COIN has a shared patient registry that tracks twenty quality measures including ten outcome measures of which six are related to disease activity. The network's global aim, set in 2021, was to increase the percent of patients with oligoarticular or polyarticular JIA that had an inactive or low disease activity state from 76% to …

Pre-Clinical Protective Potentials Of Carica Papaya Constituents In Experimentally Induced Anemia, Halimat Yusuf Lukman, Mayowa Solomon Owolabi, Ibrahim Jonathan, Ahmed M El-Gazzar, Mohamed H Mahmoud, Gaber El-Saber Batiha, Bashir Lawal

Faculty, Staff and Students Publications

OBJECTIVE: Anemia is a pathological condition characterized by reduced oxygen bioavailability and/or changes in hematological parameters. This study investigated the anti-anemic activities of

METHOD: Twenty-seven rats were randomized into nine groups of three rats as follows; group 1 was the normal (non-induced) group, 2-9 were anemic rats administered 1 mL distilled water, standard drug (3 mg/kg body weight (bw) ferrous sulphate), 100, 300 and 500 mg/kg bw of crude methanolic extract of CP (CMECP) of the leaf and 100, 300 and 500 mg/kg bw of CMECP of the seed respectively in the first stage of the study. In the second …

Impact Of The Covid-19 Pandemic And Vaccine Availability On Utilization Of Breast Imaging In A Multistate Radiology Practice, Eric M Rohren

Faculty, Staff and Students Publications

METHOD: Data were obtained from medical health records across 77 Radiology Partners practices in the US. The data provided us with the total monthly mammography, breast ultrasound, and breast MRI procedures from January 2019 to September 2022. An interrupted time-series (ITS) analysis was conducted to evaluate the effect of the COVID-19 pandemic and the COVID-19 vaccination. We chose March 2020 and December 2020 as critical time points in the pandemic and analyzed trends before and after these dates.

RESULTS: The starting level (at baseline in January 2019) of the total breast imaging procedure volume was estimated at 114,901.5, and this …

Navigating The Challenges Of Initiating Pediatric Device Trials – A Case Study, Christine Luk, Kara Toman, Michael J Heffernan, Gwenyth Fischer, Matthew Wettergreen, Chester J Koh

Faculty, Staff and Students Publications

INTRODUCTION: Pediatric medical devices lag behind adult devices due to economic barriers, smaller patient populations, changing anatomy and physiology of patients, regulatory hurdles, and especially difficulties in executing clinical trials. We investigated the requirements, challenges, associated timeline, and costs of conducting a multi-site pivotal clinical trial for a Class II pediatric physiologic monitoring device.

METHODS: This case study focused on the negotiation of clinical trial agreements (CTAs), budgets, and Institutional Review Board (IRB) processing times for a pediatric device trial. We identified key factors contributing to delays in clinical trial execution and potential best practices to expedite the process while …

Targeting Sars-Cov-2 Nonstructural Protein 3: Function, Structure, Inhibition, And Perspective In Drug Discovery

Faculty, Staff and Students Publications

As a highly contagious human pathogen, severe acute respiratory syndrome-associated coronavirus-2 (SARS-CoV-2) has infected billions of people worldwide with more than 6 million deaths. With several effective vaccines and antiviral drugs now available, the SARS-CoV-2 pandemic been brought under control. However, a new pathogenic coronavirus could emerge in the future, given the zoonotic nature of this virus. Natural evolution and drug-induced mutations of SARS-CoV-2 also require continued efforts for new anti-coronavirus drugs. Nonstructural protein (nsp) 3 of CoVs is a large, multifunctional protein, containing a papain-like protease (PLpro) and a macrodomain (Mac1), which are essential for viral replication. Here, we …

A Good Death

Faculty, Staff and Students Publications

No abstract provided.