Digital Commons Network^™

Pulsey: Stellar Pulsation Models In Python, Andrew Ayala

Dissertations, Theses, and Capstone Projects

The era of the Kepler/K2 and TESS space-telescope missions has inundated the astrophysics community with photometric data for millions of stars with continuous observation and very high cadence. This data confirms that nearly every observed stellar source exhibits an oscillating luminosity, with stellar pulsation being the driving mechanism behind a large fraction of the cause. The result has been an explosion in the field of asteroseismology, where the recorded luminosity variations, or "light curves", of pulsating stars to probe their interior structures. By modeling observed light curves, we can constrain values of the physical stellar parameters producing them. The brightness …

Multi-Label Classification Using Conformal Prediction, Chhavi Tyagi

Dissertations

In many machine learning applications, such as image tagging, document classi-fication, and medical diagnosis, a data instance can be associated with multiple classes in parallel so that each instance is associated with multiple response variables simultaneously defining multi-label classification. Standard multi-label classification methods that provide point predictions have been developed. They lack in quantifying the uncertainty of predictions. These methods also lack in accounting for label dependencies and are very computationally expensive. This dissertation develops two methods of multi-label classification using conformal prediction that quantify the uncertainty of predictions. Chapter 1 introduces notations and tools that have been used in …

Certifying Stability In Runge-Kutta Schemes: Algebraic Conditions And Semidefinite Programming, Austin Juhl

Dissertations

Numerical stability is a critical property for a time-integration scheme. In the context of Runge-Kutta methods applied to stiff differential equations, A-stability is one of the most basic and practically important notions of stability. Dating back to the work of Dahlquist, it has been known that A-stability is equivalent to the Runge-Kutta stability function satisfying a particular convex feasibility problem. Specifically, up to a transformation, the stability function lies in the convex cone of positive functions. In recent years, sum-of-squares optimization and semidefinite programming have become valuable tools in developing rigorous certificates of stability in dynamical systems. Therefore, it is …

Federated Learning Systems For Mobile Sensing Data, Xiaopeng Jiang

Dissertations

Federated Learning (FL) has emerged as a new distributed Deep Learning (DL) paradigm that enables privacy-aware training and inference on mobile devices with help from the cloud. This dissertation presents a comprehensive exploration of FL with mobile sensing data, covering systems, applications, and optimizations.

First, a mobile-cloud FL system, FLSys, is designed to balance model performance with resource consumption, tolerate communication failures, and achieve scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. In addition, FLSys provides advanced privacy-preserving mechanisms and a common API for third-party app developers to …

A Methodological Framework For Ontology Development, Enrichment, And Application In Natural Language Processing Tasks, Navya Martin Kollapally

Dissertations

Electronic Health Records (EHRs) have been widely used in healthcare to record demographics, vital signs, test results, immunizations, medical imaging reports, differential diagnoses, etc. It is now accepted that non-clinical (e.g., social) factors have a substantial influence on health outcomes. Hence, it is desirable to record these Social and Commercial Determinants of Health (SDoH & CDoH) in an EHR. The "non-text parts" of EHR notes (e.g., data tables) rely on coded terms from underlying ontologies or terminologies to facilitate semantic interoperability. Ontologies help define concepts, the relationships between them, and instances that can be utilized in research.

The first accomplishment …

Antioxidant, Photoprotective, And Cytotoxic Activities Of Tristaniopsis Merguensis Leaf Fractions With Molecular Docking Study Of Potential Fraction, Boima Situmeang, Respati Tri Swasono, Tri Joko Raharjo

Karbala International Journal of Modern Science

Through experimental along with molecular docking techniques of potential fraction, this study intended to evaluate the essential phytochemical elements of Tristaniopsis merguensis leaflets as well as potential antioxidant, photoprotective, along with cytotoxic activities. The DPPH and ABTS tests were used to evaluate the antioxidant efficacy of the n-hexane (HPF), ethyl acetate (EPF), and methanol (MPF) fractions. Using an in-vitro solar protection factor (SPF) assessment, the photoprotective ability of T. merguensis components against UV damage was examined. Subsequently, invitro cytotoxic research were carried out against MCF-7 cell line (breast cancer line) assay. This was followed by molecular docking stimulation testing against …

Health Benefits And Adverse Effects Of Kratom: A Social Media Text-Mining Approach, Abdullah Wahbeh, Mohammad A. Al-Ramahi, Omar El-Gayar, Tareq Nasralah, Ahmed El Noshokaty

All Faculty Scholarship (Archived)

Background: Kratom is a substance that alters one’s mental state and is used for pain relief, mood enhancement, and opioid withdrawal, despite potential health risks. In this study, we aim to analyze the social media discourse about kratom to provide more insights about kratom’s benefits and adverse effects. Also, we aim to demonstrate how algorithmic machine learning approaches, qualitative methods, and data visualization techniques can complement each other to discern diverse reactions to kratom’s effects, thereby complementing traditional quantitative and qualitative methods. Methods: Social media data were analyzed using the latent Dirichlet allocation (LDA) algorithm, PyLDAVis, and t-distributed stochastic neighbor …

Module: Ai And Value-Neutrality, Jonathan Auyer Ph.D., Department Of Philosophy

Artificial Intelligence, 2024-25

Artificial Intelligence is on the tips of everyone’s tongues these days – What exactly is it? What will can it be used for? What will it be used for in the future? What problems will it create or solve or exacerbate? This learning module aims to look at a specific facet of AI — the issue of value-neutrality — by having students look inward at capabilities necessary for human flourishing and then ask whether AI can cultivate (or inhibit) those capabilities. This will lead to a discussion of what values underlie AI and what this says about whether or not …

Chatgpt Can Write My Class Assignments, Right?: A Guided Classroom Activity For Teaching The Strengths And Weaknesses Of Generative-Ai Tools, Dr. Peter J. Kalenda Assistant Professor, Elementary Science & Math, School Of Education

Artificial Intelligence, 2024-25

This module is designed to support your undergraduate or graduate students with developing an understanding of:

• How to use generative-AI tools, like ChatGPT,
• The strengths and weaknesses of generative-AI tools for completing different tasks,
• How to design and revise a classroom presentation that is aligned with course topics and objectives by using generative-AI tools as a resource, and
• How to engage in prompt engineering and prompt revision for generative-AI tools.

Your students are being tasked with creating an engaging presentation they will deliver to their peers that aligns with the topics and learning objectives of your course. However, they will …

Using Ai In Higher Ed: Is It Cheating?, David Levy Associate Professor & Chair Of Philosophy

Artificial Intelligence, 2024-25

Students generate a course-based or college-wide policy regarding the use of Generative AI, based on assigned readings, discussion, practice using the tools on writing assignments.

Psychology And The Digital Everywhere: Artificial Intelligence, Cassie Van Stolk Assistant Professor Of Psychology, Department Of Psychology

Artificial Intelligence, 2024-25

This module within the PSYC 390: Psychology and the Digital Everywhere course investigates the the implications of AI on human experiences using a biopsychosocial lens. Topics covered include an exploration of AI as a tool versus as an autonomous mind, ethical considerations of AI usage, and the promises and pitfalls of AI as a tool within the field of psychology. This module aligns with the "Contemporary Global Challenges, Creativity and Innovation" Participation in a Global Society outcome within the Geneseo GLOBE Curriculum.

Supervised Classification Modeling On Louisiana Medicaid Data: A Comparative Study, Yead Rahman

Master's Theses

This thesis systematically optimizes and compares state-of-the-art supervised classification models for Louisiana Medicaid data targeting clinical services, COVID-19 infection, and tobacco use. These target variables are critically important as they represent key health outcomes and behaviors among Medicaid enrollees in Louisiana, a population often characterized by poverty and limited access to education. This study applies advanced machine learning techniques to identify the best model for multinomial and binary classification tasks. These include models such as Logistic Regression, XGBoost, AdaBoost, Random Forest, Decision Tree, Artificial Neural Networks, and Naïve Bayes. Extensive tuning of the hyperparameters and optimization of each classifier were …

Robotic Odor Source Localization Using Vision And Olfaction Sensing, Sunzid Hassan

Master's Theses

Robotic Odor Source Localization (ROSL) technology allows autonomous agents like robots to find an odor source in unknown environments. A successful odor source location depends crucially on an effective navigation algorithm that directs the robot towards the odor source. This thesis is a combination of three projects. First, we detail development of a versatile multi-modal robotic platform for ROSL real-world ROSL experimentation and discussed real-world validation of a traditional olfactionbased ROSL algorithm. Secondly, we introduced vision in ROSL by proposing a fusion navigation algorithm that integrates deep-learning enabled vision and olfaction-based navigation. This hybrid approach tackles challenges such as turbulent …

Democratization Of Custom, High Quality Large Language Models, Pablo Lopez

College of Computing and Digital Media Dissertations

Large Language Models (LLMs) have shown exceptional performance in several natural language processing (NLP) tasks. Customizing LLMs boosts their performance in domain specific tasks but typically requires substantial resources and effort for training, such as supervised fine-tuning. This research proposes methods to achieve significant accuracy improvements given minimal resources, particularly focusing on open-ended question answering with a given piece of context. We utilize an LLM’s self-generated training data to fine-tune the LLM and partial fine-tuning with on-demand GPU to reduce practitioner training costs. The research shows that these methods give significant performance gains in a Retrieval Augmented Generation (RAG) based …

The Impact Of Model Variations On The Robustness Of Deep Learning Models In Adversarial Settings, Firuz Juraev, Mohammed Abuhamad, Simon S. Woo, George K. Thiruvathukal, Tamer Abuhmed

Computer Science: Faculty Publications and Other Works

Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying variations of sophisticated techniques that improve the performance of models. However, such models are not immune to adversarial manipulations, which can cause the system to misbehave and remain unnoticed by experts. The frequency of modifications to existing deep learning models necessitates thorough analysis to determine the impact on models’ robustness. In this work, we present an experimental evaluation of the effects of model modifications on deep learning model robustness using …

Data Communication Over Power-Lines: A Review On Technical, And Applications Challenges, Abdi Abdalla

Tanzania Journal of Engineering and Technology (TJET)

This paper presents a review study on the data communication over power-lines, commonly referred to as power-line carrier, power-line communication (PLC), mains communications, or power-line digital subscriber line (PDSL). This study examines the technical and application advantages and challenges associated with adopting PLC as a preferred alternative technology for wideband or broadband data communication. The broader coverage area of the PLC network gives it a distinct advantage over other communication network technologies. Additionally, implementing a communication system using the existing power-line network is more cost-effective and less time-consuming compared to constructing a new network from scratch. However, the primary challenge …

Investigations Of Cell Tower Antennas Parameters On Reduction Of Radio Frequency Radiation Levels From Radio Base Stations, Florence U. Rashidi

Tanzania Journal of Engineering and Technology (TJET)

The widespread deployment of mobile cellular base stations in populated areas has raised public health concerns due to increased exposure to radio frequency (RF) radiation emissions. Exposure to high levels of RF radiation can have potential thermal and non-thermal biological effects. Optimizing the configuration of cell tower antenna parameters is crucial for mitigating these radiation levels. This study therefore aims at systematically investigating the influence of different cell tower antenna parameters on reducing the RF radiation levels from mobile base stations. Field measurements were conducted at two cell sites shared by multiple mobile operators. Electric field strengths were measured at …

Evaluation Of Business-Driven Reference Architecture For Big Data Analytics Implementation By Public Sector Organizations In Resource-Constrained Setting: A Case Study Of Uganda, Matendo Didas

Tanzania Journal of Engineering and Technology (TJET)

Big Data Analytics (BDA) is a new area at the nexus of agenda, public sector organizations, and government business. It may satisfy the growing need for trustworthy, cost-effective services in the public sector for better, more informed decision-making processes. BDA has been proposed on the planning schedules of several public sector organizations and the government. Therefore, from the previous work, using Uganda as a case study, specifically the Uganda Bureau of Statistics (UBOS), Ministry of Health (MoH), and Ministry of Education and Sports (MoES), this study aims to evaluate a designed Business-Driven Reference Architecture for Big Data Analytics Implementation (BRABDAI) …

Assessment Of Web Security Vulnerabilities For Common Open Source Virtualization Software, Said Ally

Tanzania Journal of Engineering and Technology (TJET)

Open-source hypervisors have emerged as an integral technology for virtualizing server resources in cloud and data center computing. Hypervisor security efficiency is determined by virtual machine isolation, which is a de facto adoption factor in the selection process, as well as its ability to respond to web attacks. This paper assesses the security performance of Proxmox VE and XenServer for type 1 hypervisors, and Kernel Virtual Machine and Oracle Virtual Box for type 2 hypervisors. Security analysis was conducted using common exposures extracted from vulnerability databases and mapped against the OWASP 2013 and 2017 projects. For clarity, experiments were carried …

Transforming Computer Science Pedagogy: An Exploration Of Self-Recorded Videos (Srv) As A Teaching And Evaluation Tool, Hussam Ghunaim

Computer Science Faculty Publications

This study aims to introduce Self-Recorded Videos (SRV) as a novel method to help improve students’ performance in coding assignments in computer science courses. To our best knowledge, this is the first time the SRV method is applied in the context of computer science classes. The study was conducted with a sample size of 41 students who were registered in the online CSCI 331 Operating Systems course at Fort Hays State University. These students were given specific instructions to create Self-Recorded Videos SRVs for every coding assignment they were tasked with. This approach was designed to encourage students to engage …

Object Classification, Detection And Tracking In Challenging Underwater Environment, Md Modasshir

Theses and Dissertations

The main contributions of this thesis is the applicability and architectural designs of deep learning algorithms in underwater imagery. In recent times, deep learning techniques for object classification and detection have achieved exceptional levels of accuracy that surpass human capabilities. However, the effectiveness of these techniques in underwater environments has not been thoroughly researched. This thesis delves into various research areas related to underwater environments, such as object classification, detection, semantic segmentation, pose regression, and semi-supervised retraining of detection models.

The first part of the thesis studies image classification and detection. Image classification is a fundamental process that involves assigning …

Learning And Planning In Stochastic Interactive Environments With The Presence Of Sparse Dependence Structures, Zihao Deng

McKelvey School of Engineering Graduate Student Theses & Dissertations

When interacting with an environment, an agent would want to make decisions on the fly based on the input of the dynamically changing environmental factors, so as to maximize the rewards or minimize the risks. In order to achieve that, one would want to learn the dynamics of the environment and employ efficient planning based on what has been learned about the environment. However, when the environment is large and convoluted, the planning and learning algorithms can easily become computationally intractable in general. In this thesis, we first quantitatively show that this type of problems is indeed hard to solve …

Interventional Radiology's Exploration Into Artificial Intelligence, Raymond Nguyen

Master's Projects and Capstones

Background: Artificial intelligence (AI) has become more prominent in our daily lives in recent years. This includes various aspects of healthcare. Interventional radiology (IR) is one of these specialties that has taken strides in understanding how AI can be leveraged for patient care. This literature review aims to understand what areas will be most impacted by AI in IR and how it will influence both the patient and interventional radiologist.

Methods: Twenty-six publications from 2019-2024 were selected from PubMed and Scopus. Publications were sourced through a combination of keywords, subject headings (MeSH terms), and citation searching.

Results: This literature review …

On Parallelization Of Graph Algorithms, Performance Modelling And Autonomous 3d Printable Object Synthesis, Shams-Ul-Haq Syed

Theses and Dissertations

The degree of hardware level parallelism offered by today’s GPU architecture makes it ideal for problem domains with massive inherent parallelism potential, fields such as computer vision, image processing, graph theory and graph computations. We have identified three problem areas for purpose of this research dissertation, under the umbrella of performance improvement by harnessing the power of GPUs for novel applications. The first area is concerned with k-vertex connectivity in graph theory, the second area deals performance evaluation using extended roofline models for GPU parallel applications and finally the third problem area is related to synthesis 3D printable objects from …

Automated Data-Flow Optimization For Digital Signal Processors, Madushan Thilina Abeysinghe

Theses and Dissertations

Digital signal processors (DSP), which are characterized by statically-scheduled Very-Long Instruction Word architectures and software-defined scratchpad memory, are currently the go-to processor type for low-power embedded vision systems, as exemplified by the DSP processors integrated into systems-on-chips from NVIDIA, Samsung, Qualcomm, Apple, and Texas Instruments. DSPs achieve performance by statically scheduling workloads, both in terms of data movement and instructions. We developed a method for scheduling buffer transactions across a data flow graph using data-driven performance models, yielding a 25% average reduction in execution time and a reduction of up to 85% DRAM utilization for randomly-generated data flow graphs. We …

Scene Text Detection And Recognition Via Discriminative Representation, Liang Zhao

Theses and Dissertations

Scene texts refer to arbitrary text presented in an image captured by a camera in the real world. The tasks of scene text detection and recognition from complex images play a crucial role in computer vision, with potential applications in scene understanding, information retrieval, robotics, autonomous driving, etc. Despite the notable progress made by existing deep-learning methods, achieving accurate text detection and recognition remains challenging for robust real-world applications. The challenges in scene text detection and recognition stem from: 1) diverse text shapes, fonts, colors, styles, layouts, etc.; 2) countless combinations of characters with unfixed attributes for complete detection, coupled …

Human-Human Vs Human-Ai Therapy: An Empirical Study, Mohammad Amin Kuhail, Nazik Alturki, Justin Thomas, Amal K. Alkhalifa, Amal Alshardan

All Works

In many nations, demand for mental health services currently outstrips supply, especially in the area of talk-based psychological interventions. Within this context, chatbots (software applications designed to simulate conversations with human users) are increasingly explored as potential adjuncts to traditional mental healthcare service delivery with a view to improving accessibility and reducing waiting times. However, the effectiveness and acceptability of such chatbots remains under-researched. This study evaluates mental health professionals’ perceptions of Pi, a relational Artificial Intelligence (AI) chatbot, in the early stages of the psychotherapeutic process (problem exploration). We asked 63 therapists to assess therapy transcripts between a human …

A Method Based On Deep Learning For Assisting Sins/Dvl Integrated Navigation, Xinghong Kuang, Aowei Huang

Journal of System Simulation

Abstract: The navigation and positioning accuracy of an Autonomous Underwater Vehicle (AUV) affects the efficiency of the AUV to a certain extent, and since GNSS cannot be used underwater, the integrated navigation system of Strapdown Inertial Navigation System/ Doppler Velocity Log (SINS/DVL) has been widely favored. However, DVL will fail in some cases, and if DVL is isolated directly, the system will become a pure inertial navigation system, which seriously affects the accuracy of navigation and positioning. In order to cope with the situation that DVL is missing in some beams, a DLinear-Informer assisted integrated navigation algorithm is proposed. Through …

Section Point Cloud Denoising Method Based On Enhanced Dbscan And Distance Consensus Evaluation, Chengpeng Ge, Dong Zhao, Rui Wang, Qinghua Ma

Journal of System Simulation

Abstract: A denoising method based on the improved DBSCAN(density-based spatial clustering of applications with noise) algorithm is proposed to address the problem of removing noise points in point cloud data. The statistical filtering method is applied to pre-screen isolated outliers and remove largescale noise from the point cloud. The DBSCAN algorithm is optimized to reduce computational time complexity and achieve adaptive parameter adjustment, thereby dividing the point cloud into normal clusters, suspected clusters and abnormal clusters, and immediately removing abnormal clusters. Distance consensus assessment is applied, and suspect clusters are further evaluated. By calculating the distance between the suspected point …

Parallax-Tolerant Image Stitching With Geometric Structure Protection For Unmanned Ship Visual Perception, Zhilin Yang, Yong Yin, Rukai Zhang, Qianfeng Jing, Sen Jiang, Wenfeng Zhu

Journal of System Simulation

Abstract: In order to address the artifacts caused by misalignment in maritime image stitch with low texture and large parallax, a geometric structure parallax-tolerant image stitch algorithm based on point-line feature registration and optimal seam fusion is proposed. Line segment features are introduced into the traditional homography transformation based on point features, and potential coplanar local line segments are merged into global line segments to provide accurate alignment conditions for seam line fusion. In the image fusion stage, the energy function of seam cutting method is designed by using the color difference and gradient difference of tanh measure and introducing …