Digital Commons Network^™

Uc-173 Leveraging Large Language Models To Empower Caretakers Of People With Dementia, Mercy Olaniran, Emily A Centeno

C-Day Computing Showcase

Behavioral symptoms of Alzheimer's Disease and Related Dementias (ADRD) are detrimental to the quality of life for individuals with ADRD and their caregivers. Symptoms such as wandering, agitation, and confusion can often overwhelm caregivers leading to stress, depression, or burnout which can lead to a decrease in the quality of care. These challenges often result in increased hospitalizations and care costs, creating a need for a solution to support informal caregivers. This project proposes the development of an AI-based Dementia Care Voice Assistant application to meet the needs of caregivers. Using large language models, the application will provide real-time and …

Uc-180 Intelligent Object Retrieval Using Mobile Manipulator, Zhiwen Zheng, Ellie Ireland

C-Day Computing Showcase

A mobile manipulator for intelligent object retrieval is presented. The system was integrated using state of the art R&D hardware and software, which implemented autonomous navigation, object recognition, and object pose estimation based optimal grasping. The retrieval of an object of interest is commanded that involves subsequent object detection and recognition while autonomously navigating using the known map and starting from an arbitrary position. From close proximity, object pose estimation based optimal grasp is selected to pick up the object. The object is retrieved back to the start position in this scenario. An 84% trial-phase precision in object retrieval is …

Ur-147 An 8-Bit Digital Computer Design & Implementation (Team Coa-Wm1), Adrian L Sherard, Jesus Flores, Biswash Lamsal, Blake Hammontree, William Pitts

C-Day Computing Showcase

8 bit computer design using NI multisim

Gmr-208 Automatic Categorization Of Behavioral Health Issues In Police Reports, Mason V Pederson, Abm Adnan Azmee, Francis E Nweke

C-Day Computing Showcase

911 is often the first place contacted for dealing with behavioral health related (BHR) issues. Its estimated at least a fifth of all calls are related to behavioral health, and with BHR affected convicts having a recidivism rate of around 30%, its not hard to see how straining these issues can become on systems already stretched thin, where chronic understaffing is often a reality. A great solution would be if we could intervene as soon as possible to get people the treatment they need, police reports would be excellent for identifying and treating these individuals, but annotation is a long …

Gmr-210 Cogni-Resource: Ai-Driven Reflective Feedback Analysis For Enhanced Learning Insights And Resource Discovery, Ashrith Kumar Devara

C-Day Computing Showcase

Cogni-Resource is a unified platform enhanced by AI that merges the introspective analysis of Cogni-Reflect with the precise resource exploration functions of the Learning Resource Finder, providing a holistic tool to improve educational environments. The Cogni-Reflect component uses advanced Large Language Models (LLMs) to examine student reflections, giving educators instant insights into learning results, difficulties, and areas where students may require extra assistance. Cogni-Reflect allows instructors to adjust their teaching by analyzing key themes and topics in reflective narratives, leading to a more adaptive and successful learning atmosphere. Using both web scraping and OpenAI API integration, the Learning Resource Finder …

Gpr-6128 Joint Encryption And Error Correction For Quantum Communication, Nitin Jha

C-Day Computing Showcase

Secure quantum networks are foundational for developing a quantum internet in the future. However, current age quantum channels are prone to noise, which can introduce errors in transmitted data. Traditionally, error correction is applied to the message separately, after encryption, resulting in additional overhead that should be minimized. In response, we propose a unified approach that combines encryption and error correction into a single process. This work represents an initial effort to integrate these functions for secure quantum communication by integrating the Calderbank-Shor-Steane (CSS) Quantum Error Correction (QECC) code with the three-stage secure quantum communication protocol. Additionally, the protocol supports …

Improving Data Curation With Spectral Clustering And Shannon Entropy: An Unsupervised Approach Within The Data Washing Machine, Erin Hathorn

Theses and Dissertations

In the ever-expanding landscape of digital technologies, the exponential growth of data presents both challenges and opportunities, demanding innovative approaches to data curation. Effective data curation is pivotal for extracting meaningful insights from vast and complex datasets. This study explores the integration of spectral clustering and Shannon Entropy within the Data Washing Machine (DWM), a novel tool designed to streamline unsupervised data curation processes. The DWM incorporates Shannon Entropy into its clustering process, allowing for adaptive refinement of clustering strategies based on entropy levels observed within data clusters. Spectral clustering, known for its ability to handle complex and non-linearly separable …

Strategies To Alleviate Flickering: Bayesian And Smoothing Methods For Deep Learning Classification In Video, Noah Miller, Glen Ryan Drumm, Lance Champagne, Bruce A. Cox, Trevor Bihl

Faculty Publications

Excerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations.

Enhancing 3d Knowledge-Based Authentication In Vr By Having Fun, William James Doyle V, Christopher Kreider

Cybersecurity Undergraduate Research Showcase

In the modern era of cyber attacks, and an ever-changing online world, safety and security must constantly evolve to fit the current standards. In virtual reality (VR) simple keyboard-typed passwords are a thing of the past. These passwords are complicated and frustrating to input. Along with the creation of VR, it also opened the door to a new era of password-based authentication. Using these systems' technology, password inputting can be a fun experience. These passwords are not only easier, and less frustrating to input, but as shown in previous studies, they can also be faster while still being secure. In …

Beyond Human-Centric Models In Cybersecurity Education: A Pilot Posthuman Analysis Of The Nice Workforce Framework For Cybersecurity, Ryan Straight

Journal of Cybersecurity Education, Research and Practice

This study applies a posthuman lens to the National Initiative for Cybersecurity Education (NICE) Workforce Framework, examining two key Work Roles in cybersecurity education. Employing a novel posthuman coding scheme, the associated Tasks, Knowledge, and Skills (TKS) statements were analyzed. Findings reveal significant posthuman elements within the framework while identifying opportunities for further integration. The analysis demonstrates a strong presence of human-technology entanglement and adaptive learning concepts, yet highlights areas where the framework could emphasize system complexity and interconnectedness. This research contributes to ongoing discussions on cybersecurity education in complex technological landscapes, proposing a theoretical framework for integrating posthuman concepts …

Between Copyright And Computer Science: The Law And Ethics Of Generative Ai, Devin R. Desai, Mark Riedl

Northwestern Journal of Technology and Intellectual Property

Copyright and computer science continue to intersect and clash, but they can coexist. The advent of new technologies such as digitization of visual and aural creations, sharing technologies, search engines, social media offerings, and more, challenge copyright-based industries and reopen questions about the reach of copyright law. Breakthroughs in artificial intelligence research, especially Large Language Models that leverage copyrighted material as part of training, are the latest examples of the ongoing tension between copyright and computer science. The exuberance, rush-to-market, and edge problem cases created by a few misguided companies now raises challenges to core legal doctrines and may shift …

Integrating Humanities Into Cybersecurity Education: Enhancing Ethical, Historical, And Sociopolitical Understanding In Technical Training, Joseph Frusci

Journal of Cybersecurity Education, Research and Practice

The increasing complexity of cybersecurity challenges necessitates a holistic educational approach that integrates both technical skills and humanistic perspectives. This article examines the importance of infusing humanities disciplines such as history, ethics, political science, sociology, law, and anthropology—into cybersecurity education. Through a pilot course developed for Staten Island Technical High School, aligned with the New York State K-12 Computer Science and Digital Fluency Standards, students were introduced to an interdisciplinary curriculum that combined technical cybersecurity training with historical analysis, ethical reasoning, and sociopolitical context. The results of pre- and post-course assessments demonstrated significant improvements in critical thinking, ethical decision-making, and …

Machine Learning-Driven Process Analysis And Optimization In Solid-State Welding And Fusion-Based Additive Manufacturing, Radif Uddin Ahmed

Master's Theses

In the modern era of advanced manufacturing, optimizing process parameters is pivotal in ensuring the quality and reliability of sophisticated component fabrication. This study presents a novel, data-driven approach to parameter optimization in two cutting-edge manufacturing techniques: Friction Stir Welding (FSW) and Laser Powder Bed Fusion (LPBF). By leveraging machine learning methodologies, this research addresses the critical challenge of efficiently determining optimal process parameters, a task traditionally relying on time-consuming and resource-intensive trial-and-error methods. This study will lead to a robust data-driven framework for process analysis of more advanced manufacturing techniques like the Additive Friction Stir Deposition (AFSD) process. Friction …

Developing Robotic Task Planning Methods For Diverse Real-World Challenges, Md Sadman Sakib

USF Tampa Graduate Theses and Dissertations

The deployment of robotic systems across various domains has expanded significantly, with applications ranging from domestic tasks, such as cleaning and cooking, to industrial operations requiring precision and automation. These advancements highlight the critical importance of effective task planning in ensuring that robots can perform tasks safely, efficiently, and autonomously. However, task planning in robotics faces challenges related to generalization, executability, flexibility, and limitations in existing knowledge bases.

This dissertation addresses these challenges through innovative strategies aimed at enhancing robotic task planning and execution. We first focus on adapting to unknown scenarios by utilizing the Functional Object-Oriented Network (FOON) to …

Balancing Context And Clarity Through Visualizations For Better Decision-Making, Bhavana Doppalapudi

USF Tampa Graduate Theses and Dissertations

In this era of a data driven world, the effective communication of data through visualizations is pivotal for converting complex information into accurate insights. Effective visualizations not only enhance users' comprehension of complex data but also induce trust, leading to better decision-making. This dissertation explores methods to improve trust in visualizations by providing additional context and enhancing their clarity, ensuring appropriate data interpretations and better decisions from users.

The work in the dissertation begins by examining the impact of scatterplots combined with statistical metrics such as accuracy on users' trust and decision-making focused on recommender systems. In addition, we show …

Coding Connections: Exploring Relationships Between Computer Science Learning And Mathematics Achievement In Secondary Education, Bradley Hayes

USF Tampa Graduate Theses and Dissertations

This dissertation in practice explores the intersection of computer science education, specifically computational thinking and programming, with mathematics achievement among 15-year-old students in selected English-speaking countries. The research addresses a gap in understanding whether skills developed through computer science can positively influence mathematics performance by assessing the extent to which learning in computer science transfers to mathematics.

To achieve this, a quantitative methodology was employed, incorporating pilot study data from a single school and large-scale survey data from the Programme for International Student Assessment (PISA) 2022. The analysis assessed the correlation between regular participation in programming activities and mathematics attainment, …

Internet Of Medical Things: Integrating Machine Learning And Wearables For Healthcare, Jingwen Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

The Internet of Medical Things (IoMT), which integrates Internet of Things technologies into healthcare, has become a powerful tool for enhancing health monitoring and predicting clinical outcomes. By leveraging wearable devices, IoMT facilitates continuous, cost-effective, and convenient tracking of patients' health conditions over time. This dissertation applies data-driven methods to address critical clinical challenges involving wearable devices. Specifically, it focuses on three significant clinical problems: (1) indoor contact tracing for healthcare workers using Bluetooth Low Energy (BLE) beacons, (2) predicting surgical outcomes using wearable data, and (3) developing robust models for surgical outcome prediction that account for patient variability using …

Internet Of Medical Things: Integrating Machine Learning And Wearables For Healthcare, Jingwen Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

The Internet of Medical Things (IoMT), which integrates Internet of Things technologies into healthcare, has become a powerful tool for enhancing health monitoring and predicting clinical outcomes. By leveraging wearable devices, IoMT facilitates continuous, cost-effective, and convenient tracking of patients' health conditions over time. This dissertation applies data-driven methods to address critical clinical challenges involving wearable devices. Specifically, it focuses on three significant clinical problems: (1) indoor contact tracing for healthcare workers using Bluetooth Low Energy (BLE) beacons, (2) predicting surgical outcomes using wearable data, and (3) developing robust models for surgical outcome prediction that account for patient variability using …

Platform Path Optimization Method Based On Cumulative Detection Probability Of Sonar Search, Xiang Wei, Xingxuan Liu, Dianzheng Fu, Tianji Yang, Jiaxuan Yang

Journal of System Simulation

Abstract: To address the lack of research on the optimal path of mobile search platform to search for moving targets, this paper proposes a path optimization method of mobile search platform based on cumulative search probability theory. Based on the cumulative detection probability (CDP), one of the important criteria of sensor performance evaluation, a single-peak CDP calculation formula is constructed by using a time series correlation model, namely the (λ, σ) process model. A set of target motion scenarios are constructed, and the trajectory probability of target scenarios and their CDP at different time are corrected by Bayesian posterior probability. …

Video Label Refinement And Temporal Localization Using Motion Signal Patterns, Jennifer Piane

College of Computing and Digital Media Dissertations

Performing video analysis for activity recognition presents challenges beyond classification, including obtaining class labels and performing temporal localization. One such challenge is precisely labeling a video with class labels having the exact start and end frames of an activity - a difficult task for a human to perform. Moreover, the task of annotating a video at any level of precision can quickly become tedious, impacting the attentiveness of the annotator and resulting in class label errors. Temporally localizing an activity within a video presents a second challenge. This dissertation investigates novel signal and image processing methods for motion features extracted …

Hacker, Their Actions, And Fear Appeal: A First Look Through The Lens Of Children, Rizu Paudel, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

With the increasing use of computers and smartphones by children, their online safety has become a major concern due to the lack of security awareness. Prior studies pointed to children's poor password habit and vague perceptions on the significance of passwords. While users must be sufficiently motivated to perform a target behavior, a little study to date, focused on understanding how we can encourage children towards strong password creation. As we begin to address this gap, we examined children's perceptions of adversary's actions that instill fear in the context of password compromise. Our semi-structured interviews with 20 children (aged between …

The Unfairness Of Fair Machine Learning: Leveling Down And Strict Egalitarianism By Default, Brent Mittelstadt, Sandra Wachter, Chris Russell

Michigan Technology Law Review

In recent years, fairness in machine learning (ML), artificial intelligence (AI), and algorithmic decision-making systems has emerged as a highly active area of research and development. To date, most measures and methods to mitigate bias and improve fairness in algorithmic systems have been built in isolation from policymaking and civil societal contexts and lack serious engagement with philosophical, political, legal, and economic theories of equality and distributive justice. Many current measures define “fairness” in simple terms to mean narrowing gaps in performance or outcomes between demographic groups while preserving as much of the original system’s accuracy as possible. This oversimplified …

The Implications Of Chatgpt For Legal Services And Society, Andrew Perlman

Michigan Technology Law Review

On November 30, 2022, OpenAI released a chatbot called ChatGPT.1 To demonstrate the chatbot’s sophistication and its potential implications, both for legal services and society more generally, most of this paper was generated in about an hour through prompts within ChatGPT. Only this abstract, the preface, the outline headers, the footnotes, the epilogue, and the prompts were written by a person. ChatGPT generated the rest of the text with no human editing. To be clear, the responses generated by ChatGPT were imperfect and at times problematic, and the use of an AI tool for law-related services raises a host of …

Inferring Tlb Configuration With Performance Tools, Cristian Agredo, Tor J. Langehaug, Scott R. Graham

Faculty Publications

Modern computing systems are primarily designed for maximum performance, which inadvertently introduces vulnerabilities at the micro-architecture level. While cache side-channel analysis has received significant attention, other Central Processing Units (CPUs) components like the Translation Lookaside Buffer (TLB) can also be exploited to leak sensitive information. This paper focuses on the TLB, a micro-architecture component that is vulnerable to side-channel attacks. Despite the coarse granularity at the page level, advancements in tools and techniques have made TLB information leakage feasible. The primary goal of this study is not to demonstrate the potential for information leakage from the TLB but to establish …

Automated Verification Of Compiler Transformations, Yanzhao Wang

Dissertations and Theses

The ever-growing complexity of software and its target hardware makes it increasingly challenging to develop reliable compilers that preserve the semantics of source code during compilation. Traditional testing methods often lack sufficient test coverage and fail to identify subtle errors and undefined behaviors that can lead to compiler malfunctions. Furthermore, while formal compiler certification ensures semantic preservation through theorem proving, the inherent complexity of this process makes re-certification after each compiler revision substantially labor-intensive. This often significantly hinders the improvement of compilers.

This research aims to bridge the gap between increasing compiler complexity and the limited scalability of formal verification …

Ethical Responsibility In The Design Of Artificial Intelligence (Ai) Systems, David K. Mcgraw

International Journal on Responsibility

This article aims to provide an overview of the ethical questions surrounding the responsibilities of designers of artificial intelligence (AI) systems. First, the author delves into the philosophical underpinnings of this responsibility, examining various ethical theories to grasp the moral obligations individuals have towards others and society. The author contends that designers of technology bear the responsibility of considering the broader societal implications of their creations. Subsequently, the author scrutinizes the fundamental question of whether AI systems present unique ethical concerns compared to conventional technologies, pinpointing factors such as complexity, opacity, autonomy, unpredictability, uncertainty, and the potential for significant social …

Telu Activation Function For Fast And Stable Deep Learning, Alfredo Fernandez

USF Tampa Graduate Theses and Dissertations

We propose the Hyperbolic Tangent Exponential Linear Unit (TeLU), a neural network hidden activation function defined as $TeLU(x)=x \cdot tanh(e^x)$. TeLU’s design is grounded in the core principles of key activation functions, achieving strong convergence by closely approximating the identity function in its active region while effectively mitigating the vanishing gradient problem in its saturating region. Its simple formulation enhances computational efficiency, leading to improvements in scalability and convergence speed. Unlike many modern activation functions, TeLU seamlessly combines the simplicity and effectiveness of ReLU with the smoothness and analytic properties essential for learning stability in deep neural networks. TeLU’s ability …

Exploring Llm Integration And Its Influence On Agent Behavior And Productivity In Insurance Call Centers, Gerardo L. Wibmer Gonzalez

USF Tampa Graduate Theses and Dissertations

This study investigates the theoretical impacts of supportive AI tools, specifically Large Language Models (LLMs), on agent behavior and communication dynamics in call centers. While technological advancements have streamlined operations, limited research addresses the indirect ways these tools influence agent behavior. Using frameworks like context switching—the cognitive shift required when external stimuli prompt attention shifts—and the Hawthorne effect, where perceived observation modifies behavior, we examine how LLMs shape communication patterns. In call centers, this context switching occurs indirectly as agents adapt to AI note-taking features, whereas in industries like Architecture, Engineering, and Construction (AEC), automation tools prompt more immediate changes …

A Novel Algorithmic Approach To Safeguarding Inter-Vehicular Communications And Privacy, Susan Zehra

Graduate Student Government Association Research Conference

Vehicular networks have become a crucial technology for implementing various safety applications for both drivers and passengers. These networks are currently receiving significant attention due to their ability to facilitate access to a diverse range of ubiquitous services. However, the growing popularity of vehicular networks has also led to an increase in security vulnerabilities within their inter-vehicular services and communications, resulting in a rise in security attacks and threats.

Ensuring the security of vehicular networks is paramount, as their deployment should not compromise the safety and privacy of stakeholders. Effectively defending against a broad spectrum of attacks necessitates the development …

On The Work Of Cartan And Münzner On Isoparametric Hypersurfaces, Thomas E. Cecil, Patrick J. Ryan

Mathematics and Computer Science Department Faculty Scholarship

A hypersurface Mⁿ in a real space form Rⁿ⁺¹, Sⁿ⁺¹, or Hⁿ⁺¹ is isoparametric if it has constant principal curvatures. This paper is a survey of the fundamental work of Cartan and Münzner on the theory of isoparametric hypersurfaces in real space forms, in particular, spheres. This work is contained in four papers of Cartan [3]–[6] published during the period 1938–1940, and two papers of Münzner [47]–[48] that were published in preprint form in the early 1970’s, and as journal articles in 1980–1981. These papers of Cartan and Münzner have been the …