Computer Sciences Commons^™

Adaptive Parallel Downloader For Large Genomic Datasets, Rasman Mubtasim Swargo

Miners Solving for Tomorrow Research Conference

Modern next-generation sequencing (NGS) projects routinely generate terabytes of data that researchers download from public repositories such as SRA and ENA. Existing download tools typically employ static concurrency settings, leading to inefficient bandwidth utilization and prolonged download times under dynamic network conditions. We introduce FastBioDL, a parallel downloader for large biological datasets with an adaptive concurrency controller. FastBioDL frames downloading as an online optimization problem, using a utility function and gradient descent to adjust the number of concurrent socket streams during runtime. This approach maximizes throughput while minimizing resource overhead. Evaluations on public genomic datasets show that FastBioDL achieves up …

Introducing Gridtrees For Streaming, Scalable Hierarchical Data Visualization, Nathan Tibbetts

Miners Solving for Tomorrow Research Conference

File browsing in the consumer sphere has seen very little advancement in recent years, although attempts have been made to improve upon it. With the goal of multi-level visual file browsing in mind, we present a prototype GridTree, a dynamic, recursive, stable, spatial layout data structure based on subdividing grids, represented as a hierarchy of maps whose granularity increases with depth. We motivate this work with characteristics we have identified as important for viability of a multi-level file-browser, which have become our design goals. We touch on the underlying logic of a GridTree and identify its complexity. We briefly discuss …

Thermal Mirage: Towards Robust Thermal Perception Via Gan-Guided Diffusion, Nuzaer Omar

Miners Solving for Tomorrow Research Conference

Thermal object detection systems are critical for safety sensitive applications due to their reliability under adverse conditions. However, existing robustness evaluations in thermal domain primarily focuses on physical or sensor-level perturbations, overlooking vulnerabilities from semantically realistic scene and object manipulations. We introduce Thermal Mirage, a generative framework that leverages GAN-guided diffusion to expose weaknesses in thermal detectors through controlled object and context level perturbations. Our approach learns class-conditional thermal priors via a GAN and uses diffusion to transform object appearances into ambiguous or low-saliency patterns. Simultaneously, a context module degrades scene conditions by simulating harsher night environments. Integrated with a …

Distributed Control Plane For Cross-Silo Federated Learning, Rabin Pandey

Miners Solving for Tomorrow Research Conference

Cross-silo federated learning (FL) trains shared models across geographically distributed institutions without centralizing raw data, but its reliance on wide-area networks makes round completion time highly sensitive to heterogeneous link conditions, congestion, and straggler clients. Existing SDN-based FL frameworks address this through centralized traffic engineering, an approach that breaks down when silos span independent administrative domains where no single entity can maintain complete, timely network knowledge. We replace the centralized control plane with a fully distributed overlay in which each silo gateway operates as an equal peer, continuously probing local links, exchanging EWMA-smoothed metrics via bounded gossip, and computing least-cost …

Robust Federated Learning With Strategic Adversaries, Manoj Twarakavi

Miners Solving for Tomorrow Research Conference

Federated Learning (FL) leverages the intelligence of untrusted distributed devices through collaborative training. This makes the training process susceptible to malicious behavior. Existing defense mechanisms largely consider an adversary who attacks a proactive FL server without any adaptability. However, they overlook the presence of a strategic adversary. To address this challenge, our work proposes a Robust Game-theoretic framework where the adversary is both strategic and is equipped with the capability of performing large-scale poisoning attacks.

Robustness Of Fuzzy Artmap To Adversarial Attacks And Progressive Adversarial Training For Streaming Learning, Shane Cairns

Miners Solving for Tomorrow Research Conference

Incremental learners deployed on streaming data must remain robust to evolving adversarial perturbations, yet most adversarial-robustness studies assume offline multi-epoch training with repeated access to historical data. We investigate adversarial robustness in Fuzzy ARTMAP, a prototype-based Adaptive Resonance Theory model that supports single-pass learning without replay. We propose WB-Softmax, a differentiable relaxation that aggregates category-level activations into class-level scores for gradient-based attacks. WB-Softmax PGD achieves 89–100% attack success on vanilla models, exceeding transfer and query-based baselines. We then study adversarial training under true streaming constraints by comparing offline versus online adversarial example generation and standard versus selective updates. Offline adversarial …

Anti-Inflammatory And Insulin-Modulating Effects Of Tithonia-Curcuma-Moringa (Tcm) Formulation In Type 2 Diabetes: An Experimental Study In Mice, Rif’Atul Hawani Burhan, Nabila Shafa Yumna Salsabila, Devita Zulfa Pratama, La Tazkia Aulia Wibowo, Yulian Ervin Maulana, Moh Dliyauddin, Noviana Dwi Lestari, Agung Pramana Warih Marhendra, Aris Soewondo, Hideo Tsuboi, Muhaimin Rifa’I

Karbala International Journal of Modern Science

Type 2 diabetes is a chronic metabolic disorder characterized by hyperglycemia and chronic inflammation. This study investigated the anti-inflammatory and insulin-modulating effects of Tithonia-Curcuma-Moringa (TCM) formulation in type 2 diabetes model. Male BALB/c mice were divided into six groups: normal control, type 2 diabetes control, metformin treatment, and three TCM formulation treatment groups with three different dose combinations. Type 2 diabetes was induced using a high-fat diet combined with streptozotocin injection, supported by sucrose administration. After 21 days of treatment, the spleen and pancreas were isolated for flow cytometry analysis. The results showed that the expression levels of …

Bridging The Cybersecurity Education Gap: The Role Of Open Educational Resources In Supporting Rural Cybersecurity Programs, Brittni Hardie

Theses and Dissertations

This study examines the intersection of cybersecurity education, open educational resources (OER), and rural higher education through a systematic review of current literature and an exploratory survey of rural community college faculty. The purpose of this research, consistent with the approved Institutional Review Board (IRB) protocol, was to understand how OER can be leveraged to design and deliver an affordable, high-quality System Security course within a rural higher-education environment. As cybersecurity workforce shortages continue to grow across the United States, rural institutions face persistent challenges in sustaining high-quality programs due to financial constraints, limited faculty capacity, and rapidly evolving curriculum …

Elucidating Complex H Behavior In Amorphous Oxide Semiconductors By Machine Learning, Lucas Ethington

Miners Solving for Tomorrow Research Conference

In this project, the disordered oxide structures will be mapped by a machine-learning algorithm (e.g., HDBSCAN) to identify characteristic behaviors of the proton across different material densities and defect types. This should help identify the under-coordinated, highly distorted, weakly-bonded, and dynamically unstable atoms to predict the most probable H locations. This fast and accurate prediction of energetically favorable H distribution will enable a reliable and fast screening of a large number of AOSs with variable cation and/or anion compositions. The approach will help find AOSs with suppressed numbers of M-OH defects (that form deep electron traps, limiting the number of …

Wheel-Spoke Encoding: A Product Quantization-Compatible Radial Encoding Scheme For Convex Polygonal Data, Maris Reinkemeyer

Miners Solving for Tomorrow Research Conference

Product quantization has historically been unapplied to GIS datasets, likely due to a mismatch between quantization’s input precondition of fixed, equal length vectors and GIS data’s inherent variability in the number of data points. Therefore, any quantization-compatible encoding method must operate independently of the data points within GIS records. The challenge is to balance the guarantee of producing fixed, equal length vectors with the preservation of semantic meaning present in the raw data. Here, we develop a radial polygon encoding method that achieves this balance while providing acceptable recall in a time complexity of O(nrv), where n is the number …

Dynamical Transition From A Two-Dimensional Soliton To A Rogue Wave In Quantum Droplets, Punit Sesha Sai Turlapati

Miners Solving for Tomorrow Research Conference

We investigate the nonequilibrium dynamics of two-dimensional quantum droplets: ultracold self-bound many-body states stabilized by the interplay of mean-field attractive interactions and repulsive quantum fluctuations. Flat-top ground state droplets are subject to an external potential, an attractive well and a repulsive barrier. Under the influence of the attractive well, we observe signatures of a Townes soliton formation, which for increasing strength of the well transitions into a two-dimensional rogue wave structure, a time-periodic highly localized configuration with amplitude three times larger than the background. The barrier instead favors a dynamical splitting of the droplet. We have developed a parallelized simulation …

Analysis Of Autonomous Vehicle Survivability To 5g Communication Errors, Sydney Clark

Miners Solving for Tomorrow Research Conference

Autonomous vehicles rely on low-latency, high-reliability data exchange for real-time perception and control. Disruptions such as packet loss, latency variation, protocol-level errors, and malicious interference can pose significant safety risks to both passengers and surrounding environments. This project aims to evaluate, quantify, and predict the survivability of autonomous vehicle systems to communication errors, with focus on 5G network environments. The impact of these communication impairments on vehicle stability and control will be investigated through high-fidelity cyber-physical simulation of the vehicle and its surrounding environment. Experiments designed to capture varying network conditions will be used to assess a broad range of …

A Wearable Mxene-Based Sweat Sensor For Real-Time Monitoring Of Inflammatory Biomarkers, Ariel Pilger

Miners Solving for Tomorrow Research Conference

Many conventional biosensing approaches rely on invasive sampling or bulky benchtop instrumentation, limiting their use in continuous and portable applications. This project focuses on the development of wearable sweat-based biosensors that enable non-invasive, continuous, and portable monitoring of physical, chemical, and biological markers. The system will be designed to target markers present in sweat and transduce the biochemical interactions into measurable electrical signals. These signals will be processed through integrated electronics to produce clear, interpretable outputs for users and medical professionals. Supporting circuitry including filters, amplifiers, and an independent power supply will be implemented as necessary to ensure signal accuracy, …

Lay Summarization For Medical Patents, Manav Raja Vinotha

Miners Solving for Tomorrow Research Conference

Technical documents, such as medical patents, are often inaccessible to non-expert audiences due to specialized terminology. This paper presents a multi-agent system for automated lay summarization that optimizes both quality and computational efficiency through strategic task decomposition. The proposed pipeline utilizes four specialized stages: autonomous medical entity retrieval from the Unified Medical Language System (UMLS), context distillation into lay conceptualizations, and a structured writer-critic loop for iterative refinement. By distributing cognitive load across specialized agents, this architecture effectively leverages smaller, cost-effective language models while maintaining the performance of SOTA LLMs. Evaluated against single-agent baselines using an LLM as a Judge …

Phase 5 - Post Implementation, Anna Pugerud

Distinguished Student Scholarship Collection

This paper presents a post‑implementation analysis and system design plan for digitizing animal health records within the Animal Health Services (AHS) department. The project addresses inefficiencies, data inaccuracies, and physical storage limitations associated with paper‑based documentation by proposing the adoption of a Software as a Service (SaaS) digital records solution. Through stakeholder interviews, observations, and document analysis, the project identifies functional, non‑functional, and system requirements necessary to support streamlined reporting, treatment tracking, and regulatory compliance. The analysis outlines feasibility across technical, economic, and organizational dimensions, demonstrating that the proposed system can reduce documentation time, improve response times, and lower operational …

Autologger: A Multi-Agent Framework For The End-To-End Automated Logging, Renyi Zhong, Yintong Huo, Wenwei Gu, Yichen Li, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with the composite nature of logging. In this paper, we propose AutoLogger, a novel hybrid framework that addresses the complete the end-to-end logging pipeline. AutoLogger first employs a fine-tuned classifier, the Judger, to accurately determine if a method requires new logging statements. If logging is needed, a multi-agent system is activated. The system includes specialized agents: a Locator dedicated to determining where to log, and a Generator focused on …

Is Nostalgia The Hidden Mechanic Of Mmorpgs?, Zoee Sowders

ART 108: Introduction to Games Studies

Since the advent of online gaming, MMORPG video games have allowed players to socialize and collaborate within the bounds of a virtual world. For many, these online worlds were an escape from their daily lives, a place where they could meet people with similar interests and embark on adventures impossible in real life.1 While many of the early MMORPG games faded into obscurity after the genre lost its shiny new sparkle, there are still a handful today that maintain player counts in the millions even after nearly two decades of operation. Specifically, World of Warcraft, Runescape, and Final Fantasy XIV …

Chopchop: The Digital Cookbook, Dominc Mcdevitt, Shane Misley, Katie Cerda, Kobie Henson, Adolfo Duran

Presentations - 2026

Problem With traditional recipe organization methods,

● Recipes are scattered across paper, PDFs, Word docs, and notes

● Paper recipes can be lost, damaged, or left at home

● Digital recipes are difficult to edit, store, and organize

● Manually typing or updating recipes is time-consuming

● Sharing recipes is inconvenient and often confusing

● Limited or inconsistent cloud access reduces accessibility

● Formatting is messy and inconsistent across platforms

● No simple, centralized system for managing recipes

Budgeting Apps, Financial Literacy, And Financial Control, Max Masabo, Abdullah Mohammad Mahi

Presentations - 2026

Our paper shows the real hidden connections between budgeting app usage and financial wellbeing of U.S Households

Match-A-Fit, Adan Diaz De Leon, Juan Marco Saca Dada, Brianna Mendoza, Arsalan Kataneh, Theophile Nsabimana, Pedro Jacobo

Presentations - 2026

Welcome to Match-a-Fit! Match-a-Fit is an iOS application that allows the user to create a digital closet by uploading images of their clothing items. With AI, the program can generate outfits based on the digital closet, the time, and the occasion. Match-a-Fit’s purpose is designed to help users who struggle to get ready, run out of time, or can’t decide on an outfit, by easily generating outfit options based on the occasion.

Comparative Analysis Of Mlp And Cnn Models For Cardiac Arrhythmia Classification, Veltman Okey-Ejowhor, Vahid Emamian

Posters - 2026

Electrocardiogram (ECG) is a record of the electric activity of the heart over time. ECG analysis plays a pivotal role in diagnosing critical heart conditions. Significant developments have been made in the realm of deep learning and applied artificial intelligence. These deep learning models have been utilized heavily because of their ability to analyze deep morphological features of each signal. The model architecture used in this study is a convolutional neural network (CNN) combined with a multi-layered perceptron (MLP). The MLP acts as an input filter that classifies normal heartbeat signals from abnormal. The CNN is the second filter in …

Maddenlite, Sergio Pena

Posters - 2026

Sports simulations often rely on opaque, proprietary algorithms (like EA's Madden NFL). MaddenLite bridges the gap between sports analytics and interactive gaming by utilizing historical NFL Play-by-Play (PBP) data to drive a transparent, mathematically accurate simulation engine. The goal was to create a lightweight, UI-driven desktop application where users can simulate cross-era matchups (e.g., 2007 Patriots vs. 2025 Chiefs), manipulate rosters, and simulate entire seasons complete with official NFL tiebreaker protocols.

Foxbuddy, Luis Eduardo Garza Jr.

Posters - 2026

Emergency preparedness remains a significant challenge for individuals due to disorganized resource management and lack of accessible guidance. Additionally, cybersecurity risks during emergencies are often overlooked, leaving individuals vulnerable to digital threats such as phishing, scams, and data exposure. FoxBuddy provides a centralized, user-friendly platform that enhances both physical preparedness and cybersecurity awareness.

Using Ai-Based Predictive Scheduling To Improve Patient Flow And Reduce Wait Times In Healthcare Clinics, Oscar Martinez

Posters - 2026

• Healthcare systems face increasing challenges in patient access and wait times
• Average wait times for specialist care continue to rise, creating:
  • Delays in treatment
  • Reduced patient satisfaction
  • Increased system inefficiencies (Sanford, 2025)
• A major contributor is operational bottlenecks, defined as:
  • Points of congestion that slow or disrupt service flow
• Hospitals typically operate under process layouts, which:
  • Handle diverse patient needs
  • Reduce specialization efficiency
• Contributing factors to bottlenecks:
  • Physician shortages and burnout
  • Administrative burden
  • Inefficient scheduling systems (Moura & Pinho, 2025)
• AI offers potential solutions through:
  • Predictive scheduling
  • Automation of administrative processes
  • Data-driven optimization of patient flow

Optimizing Retail Grocery Inventory Using Ai And Large Language Models: Evidence On Forecast Accuracy, Waste Reduction, And Cost Efficiency, Robert Miller, Stephen Garcia, Brandon Ermis

Posters - 2026

Aim: To evaluate how AI and LLMs improve forecasting accuracy, reduce waste, and enhance inventory decision-making

Beyond Technology Acceptance: Ai Adoption In The United States And Korean Accounting Firms, Madeline Ortega, Brenda Vazquez Saavedra

Posters - 2026

A comparison of AI adoption between the United States and South Korea

A View Under The Hood: Duquesne Kline's Law And Computing Program, Wesley M. Oliver, Katherine L.W. Norton, Martin Mckown, David Horrigan

West Virginia Law Review

No abstract provided.

Fingerprinting Voice Commands Of Vpn-Protected Smart Speakers, Xiaoguang Guo, Keyang Yu, Qi Li, Dong Chen

Computer Science Faculty Research and Publications

Extensive recent research has shown that it is surprisingly easy to infer Amazon Alexa voice commands over their network traffic data. To prevent these traffic analytics (TA)-based inference attacks, smart home owners are considering deploying virtual private networks (VPNs) to safeguard their smart speakers. In this work, we design a new machine learning-powered attack framework—VoiceAttack that could still accurately fingerprint voice commands on VPN-encrypted voice speaker network traffic. We evaluate VoiceAttack under 5 different real-world settings using Amazon Alexa and Google Home. Our results show that VoiceAttack could correctly infer voice command sentences with a Matthews Correlation Coefficient (MCC) of …

Research Ethics: When Ethics And Legal Rules Collide: Breaking Terms Of Service To Collect Data, Michael Zimmer, Casey Fiesler, Jessica Vitak

Computer Science Faculty Research and Publications

In many ethics classes, one of the early lessons is distinguishing between ethics and law. Ethics are the moral principles that guide decisions based on values, commitments, and purposes. Laws, by contrast, are formal rules enforced by social institutions to regulate behavior. Ethics and law frequently overlap: most people recognize that stealing is (almost always) ethically wrong, and it is also illegal. There are, of course, exceptions often discussed in ethics courses, such as the classic dilemma of stealing for a morally compelling purpose (e.g., to feed the poor).

Ai Models As Cultural Beings: Investigating Ai Cultural Biases And The Impact Of Cultural Alignment On Human-Ai Creative Collaboration, Choon Ngee Tan, Meng Han, Roy Y. J. Chua, Chi-Ying Cheng

Research Collection Lee Kong Chian School Of Business

Existing research on AI cultural biases predominantly focuses on Western models, overlooking critical gaps in non-Western models. We conduct a comparative analysis of AI models – ChatGPT (U.S. developed) and ErnieBot (China developed) – from different cultures to investigate how corresponding cultural biases manifest in their outputs. Additionally, we examine how cultural alignment between human users and AI models impacts their collaborative creative performance and the underlying psychological mechanisms. In Study 1, multi-choice prompt with zero-shot technique was used to evaluate cultural biases in four widely used AI models – ChatGPT-3.5/4, ErnieBot-3.5/4 – comparing their responses to established cultural psychometric …