Digital Commons Network^™

Accuracy-Enabling Differential Privacy-Preserving Truth Discovery, Man Zhang, Xinghua Li, Yinbin Miao, Bin Luo, Siqi Ma, Robert H. Deng

Research Collection School Of Computing and Information Systems

Perturbation-based privacy-preserving truth discovery requires the Service Provider (SP) to calculate the truthful aggregation result from perturbed data of the Data Sources (DSs), which inevitably damages the aggregation accuracy due to perturbation noise added in the data. Thus, the existing works attempt to relieve the perturbation errors by reducing noise amounts or adjusting aggregation weights of DSs. However, the former sacrifices DSs’ privacy preservation and the latter has the limited accuracy recovery performance. Aiming at it, we propose an accuracy-enabling differential privacy-preserving truth discovery consisting of an independence-guaranteed data perturbation module and a progressive-private noise elimination module. Specifically, in the …

Bias Testing And Mitigation In Llm-Based Code Generation, Dong Huang, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code generated by five widely studied LLMs (i.e., …

General Test-Time Backdoor Detection In Split Neural Network-Based Vertical Federated Learning, Shunjie Yuan, Xinghua Li, Xuelin Cao, Haiyan Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

As a new distributed machine learning framework, vertical federated learning (VFL) has been widely applied in the industry. However, recent studies have demonstrated that VFL faces serious challenges from backdoor attacks, which significantly hinder its further development. Although a few studies have focused on defending against VFL backdoor attacks, these defenses either do not consider the latest attack methods or show limited effectiveness. Moreover, most existing backdoor defense efforts primarily focus on backdoor attacks in horizontal federated learning (HFL) and centralized learning. Due to the unique architecture of VFL models, these methods cannot be directly applied to backdoor defense in …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Kpiroot+: An Efficient Integrated Framework For Anomaly Detection And Root Cause Analysis In Large-Scale Cloud Systems, Wenwei Gu, Renyi Zhong, Guangba Yu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

To ensure the reliability of cloud systems, their runtime status reflecting the service quality is periodically monitored with monitoring metrics, i.e., KPIs (key performance indicators). When performance issues happen, root cause localization pinpoints the specific KPIs that are responsible for the degradation of overall service quality, facilitating prompt problem diagnosis and resolution. To this end, existing methods generally locate root-cause KPIs by identifying the KPIs that exhibit a similar anomalous trend to the overall service performance. While straightforward, solely relying on the similarity calculation may be ineffective when dealing with cloud systems with complicated interdependent services. Recent deep learning-based methods …

Genscore: Agent-Based Short-Answer Question Generation And Scoring In Software Engineering Courses, Nguyen Binh Duong Ta, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Short-answer questions are commonly used in educational assessments, as they are often viewed as a more effective way than multiple-choice questions to determine whether students have achieved the intended learning outcomes. However, manually creating appropriate questions targeting different cognitive levels such as those defined by the Bloom’s Taxonomy, and grading text answers from students are not trivial tasks for instructors. Existing work on auto-question generation and scoring in computing education typically targets coding-based questions. However, in software engineering courses, assessments can extend beyond coding to understanding of processes, DevOps methodologies, system design, etc. This work aims to address the dual …

Reliable-Data-Split (Rds): Maximizing Model Potential With Reinforced Selection Strategy, Hoang D. Nguyen, Xuan-Son Vu, Quoc Tuan Truong, Duc-Trong Le

Research Collection School Of Computing and Information Systems

The nexus between data characteristics and parametric models is fundamental for developing effective and reliable artificial intelligence (AI) systems. Mismatches in data properties for model development may lead to deleterious effects on AI model performance in machine learning practice. This paper proposes a Reliable Data Split (RDS) procedure to learn how to select data points that will generalise the target domain adequately by employing prior knowledge of the data generative process. We introduce a reinforced selection strategy using deep reinforcement learning with diverse black box predictors in maximising ensemble rewards as the proxy of model performance potential while maintaining an …

Cropcapsnet: Enhanced Capsule Network For Crop Disease Classification, Juan Qin, Linfan Deng, Cong Li, Junjie He, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The prevention and treatment of crop diseases are crucial for the development of smart agriculture. The classification of crop diseases based on deep learning for early disease monitoring and control has become the mainstream direction of research. This paper proposes a novel deep learning model called ”CropCapsNet”, which combines Squeeze-and-Excitation Inception (SE-Inception) module and has improved capsule structure for crop disease classification. The network first extracts shallow features of input samples through double-layer convolution, then uses SE-Inception to achieve deep multi-scale feature acquisition, and finally outputs classification results through an improved capsule structure. SE-Inception adds Squeeze-and-Excitation(SE) attention after each multi-scale …

Scalable Graph Indexing Using Gpus For Approximate Nearest Neighbor Search, Zhonggen Li, Xiangyu Ke, Yifan Zhu, Bocheng Yu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Approximate nearest neighbor search (ANNS) in high-dimensional vector spaces has a wide range of real-world applications. Numerous methods have been proposed to handle ANNS efficiently, while graph-based indexes have gained prominence due to their high accuracy and efficiency. However, the indexing overhead of graph-based indexes remains substantial. With exponential growth in data volume and increasing demands for dynamic index adjustments, this overhead continues to escalate, posing a critical challenge.In this paper, we introduce Tagore, a fasT library accelerated by GPUs for graph indexing, which has powerful capabilities of constructing refinement-based graph indexes such as NSG and Vamana. We first introduce …

Pilot-C: Physics-Informed Low-Distortion Optimal Trajectory Compression, Kefei Wu, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Location-aware devices continuously generate massive volumes of trajectory data, creating demand for efficient compression. Line simplification is a common solution but typically assumes 2D trajectories and ignores time synchronization and motion continuity. We propose PILOT-C, a novel trajectory compression framework that integrates frequency-domain physics modeling with error-bounded optimization. Unlike existing line simplification methods, PILOT-C supports trajectories in arbitrary dimensions, including 3D, by compressing each spatial axis independently. Evaluated on four real-world datasets, PILOT-C achieves superior performance across multiple dimensions. In terms of compression ratio, PILOT-C outperforms CISED-W, the current state-of-the-art SED-based line simplification algorithm, by an average of 19.2%. For …

Bridging The Gut And The Heart-Exploring Pathophysiology, Risk Factors, And Therapeutic Implications Of Cardiovascular Disease In Inflammatory Bowel Disease, Diana Othon-Martinez, Sylvia Valeria Peña-Muñoz, Margarita Riojas-Barrett, Genesis Vidales-López, Josué Moisés Sánchez Guzmán, Lukasz Kwapisz

School of Medicine Publications

Inflammatory bowel disease (IBD), including Crohn’s disease and ulcerative colitis, is a chronic systemic immune dysregulated disorder affecting the gastrointestinal tract that often has extraintestinal manifestations. Limited data exist on the cardiovascular (CV) implications of IBD, but a higher prevalence of CV disease (CVD) has been observed compared to the general population, resulting in increased mortality risk. This review examines the pathophysiology and risk factors linking IBD to CVD, highlighting several key mechanisms: The “lipid paradox” in active IBD, arterial stiffness and endothelial dysfunction, proinflammatory cytokine activity, gut microbiota dysbiosis, and drug-induced myocardiopathy. The main findings include information about IBD …

Principals’ Perceptions Of Their Preparedness To Facilitate And Support Technology Integration In Schools: A Case Study Of Four Rural Texas Principals, Christina J. Campbell Ed.D.

Electronic Theses and Dissertations

School administrators face the challenge of leading technology integration that provides meaningful learning opportunities to prepare students for 21st-century skills and careers. Research has shown that administrative leadership support, behaviors, assumptions, and policies impact technology integration in the classroom. The International Society for Technology in Education (ISTE) standards include guidelines for education leaders and their role in supporting educators using technology. However, leaders underestimate the impact of their leadership on effective use in the classroom. The purpose of this qualitative case study was to explore the perceptions of South Texas rural public school principals working in Chapman Independent School District …

Secondary Special Education Teachers: Perceptions On Burnout Since The Start Of Covid-19, Regina Perez

Electronic Theses and Dissertations

This study examined burnout among secondary special education (SPED) teachers following the COVID-19 pandemic, which significantly disrupted education and intensified teacher stress. Burnout, defined by emotional exhaustion, depersonalization, and reduced personal accomplishment, has been linked to teacher attrition and decreased student achievement. The problem addressed was the increased levels of burnout and stress among SPED teachers and the lack of sufficient administrative support to mitigate these effects. The purpose was to explore SPED teachers’ perceptions of burnout since the pandemic and identify the supports needed to reduce it. Using a qualitative case study design grounded in Maslach’s burnout theory, the …

Exploring The Role Of Christian Religiosity In The Acceptance Or Rejection Of Ai Chatbot Use Among Faculty At Church Of Christ Universities, Amos Gutierrez

Electronic Theses and Dissertations

Higher education institutions are navigating the benefits and challenges of generative AI chatbot use and preparing faculty and students to engage with these tools ethically and responsibly. The problem is that there are many challenges and barriers to using these technologies in higher education, and Christian higher education institutions must also address context-specific considerations regarding mission and vision rooted in biblical faith and practice. The purpose of this quantitative, nonexperimental, cross-sectional study using confirmatory factor analysis and multiple regression through structural equation modeling was to examine faculty perceptions of AI chatbots and how Christian religiosity moderates acceptance. An online survey …

The 4-Day School Week: Impacts On Rural Texas School Districts, Geoffery Bowdoin

Electronic Theses and Dissertations

This study examined how school administrators, teachers, and parents in rural Texas districts view the effects of the 4-day school week. Across Texas, a growing number of districts have adopted shorter calendars to address teacher shortages, boost morale, and manage tight budgets. The goal of this research was to gain a clearer understanding of how this schedule shift influences student performance, district finances, and teacher recruitment and retention. The study followed a qualitative descriptive approach. Data were collected through two means. Semistructured interviews were conducted with 12 school administrators, while 29 teachers and 42 parents completed surveys. Research participants came …

Leading With Strength: The Relationship Between Character Strength Awareness And Teacher Self-Efficacy, Ashton Lynn Knox

Electronic Theses and Dissertations

Traditional educational leadership practices have historically emphasized weakness-based approaches to leadership regarding teacher interventions. Emerging research grounded in positive psychology suggests that strength-based interventions may offer a more effective pathway for supporting educators. The purpose of this action research study was to examine the influence of character strength awareness on teacher self-efficacy. Guided by a strength-based leadership framework, the researcher investigated whether intentional character strength interventions could positively impact teachers’ perceptions of their instructional effectiveness. The study employed an action research design with 14 K–12 teachers from a rural public school district in Texas. Participants completed the Values in Action …

Freshwater Turtle Assemblages And Densities In Agricultural Ditches And Aquaculture Ponds Of Eastern Arkansas, Andrhea D. Massey, John D. Willson, Brett A. Degregorio

Biological Sciences Faculty Publications and Presentations

The Mississippi Alluvial Plain (MAP) of Arkansas is a landscape where many wetlands have been altered for use as aquaculture ponds or agricultural ditches. Commercial harvest of freshwater turtles within the MAP is not restricted or limited, with reported harvest numbers for 2019 alone exceeding 4000 for spiny softshell turtles (Apalone spinifera) and 39,000 for red-eared sliders (Trachemys scripta elegans). Herein, we attempt to provide baseline estimates of freshwater turtle densities and community composition in aquaculture ponds and agricultural ditches of eastern Arkansas, the habitat types most frequently trapped by commercial harvesters. We used a capture-mark-recapture approach over 3 summers …

Learning To Be Trauma-Informed: An Examination Of Individual-Level Factors Predicting Perceptions Of And Response To Trauma-Informed Practice Trainings, Kelly Daniel

Electronic Theses and Dissertations

Trauma is a substantial threat to public health. As such, significant effort has been exerted into developing interventions which mitigate the consequences of trauma. Trauma-informed practice (TIP) aims to alleviate the effects of trauma by building policies and practices focused on safety, trust, transparency, support, collaboration, and empowerment. This study investigated how individual-level factors, including readiness for organizational change, perceived benefit of TIP training, and personal trauma history affect one’s ability to apply a TIP lens in a sample (n =100) of members of a graduate-level college. Further, it explored if one’s perceptions of and response to trauma-informed practice training …

The Impact Of Screentime In Childhood, Kyla P. Shirley

Informatics

The increased dependency on technological devices as a result of the digital age being upon us impacts a multitude of individuals from all age groups. For older groups, they might find an easier time navigating the world wide web due to their awareness of the potential dangers these digital spaces may bring. On the other hand, younger age groups are more susceptible to the dangers posed due to their lack of maturity which in turn makes them extremely vulnerable to being negatively impacted when using these electronic devices. The goal of this project was to generate awareness concerning screen time …

Isolation, Chemical Characterization, And In-Vitro Cytotoxic Evaluation Of Novel Polar Flavonoids From Chromolaena Leivensis, Matthew Tohatsu Tetteh

Electronic Theses and Dissertations

This study focuses on isolation, chemical characterization, and in-vitro cytotoxic evaluation of novel polar flavonoids from chromolaena leivensis. A 95% ethanolic extract of c. leivensis shipped by Prof. Ruben Torrenegra from University of Applied and Environmental Sciences, Bogota, Colombia, was dissolved in 1:1 methanol/chloroform mixture and its purity analyzed by TLC. The sample was eluted with toluene/methanol in an increasing order of polarity on silica gel, resulting in 49 fractions labelled CLA1 to CLA49. Among these fractions, CLA10 (1) and CLA19 (2) obtained yellow and white crystals. They were analyzed by GCMS, IR, and …

The People’S Medicine: Modern Perspectives On Folk Medicine In South Central Appalachia, Stacey M. Horton

Electronic Theses and Dissertations

The study addresses the critical need to document Appalachian folk medicine conventions and cultural practices from a modern perspective. In so doing, it addresses folk medicine research gaps in understudied places in South Central Appalachia, particularly in Southwestern Virginia and Northeast Tennessee. This research utilizes participant observation and oral history interviews to research modern Appalachian folk medicine practices among a select group of practitioners. Interviews focused on individuals who center their professional careers and subsequent lifestyles around herbalism, foraging, folk medicine, ethnobotany, and botanicals. By utilizing a critical praxis framework, the study seeks to move beyond lists of symptoms and …

Learning To Think, Thinking To Learn: A Qualitative Investigation Of Inquiry-Based Learning And Metacognition In Preschools, Jessica Carter

Electronic Theses and Dissertations

In response to an increased focus in the field of early childhood on inquiry-based practices and metacognition, this qualitative study was designed to investigate a variety of approaches to planning and facilitating classroom inquiry. Additionally, this research was designed to discover the ways in which metacognitive strategies are used in preschool classrooms to foster the learning process. Using teacher interviews, classroom observation, and analyses of teachers’ planning documents in a multiple case study design, this study focused on five Reggio-inspired classrooms to investigate the planning and teaching practices of preschool teachers related to inquiry-based learning. Of importance was their use …

Strategic Enhancement Of Biofuel Production Using Bacillus Subtilis As A Model Organism: A Dual Approach Of Gene Essentiality Mapping And Optimization, Angela A. Zebede

Electronic Theses and Dissertations

With rising global demand for renewable energy, enhancing microbial platforms for biofuel production is vital. This study engineered Bacillus subtilis to improve resilience to solvent stress by targeting membrane lipid biosynthesis pathways essential for integrity. Growth curve analysis (OD₆₀₀) showed that phosphatidylserine (PS) and phosphatidylethanolamine (PE) knockout strains grew significantly slower than wild type (168), indicating the importance of these lipids under stress. Laurdan fluorescence spectroscopy was used to assess membrane properties. Generalized polarization (GP) analysis revealed a concentration-dependent reduction in membrane order upon 1%–2% 1-butanol exposure. GP values declined progressively from control to 2% treatment, reflecting increased membrane fluidity …

Tennessee Reconnect And Adult Learner Retention, Brandon R. Dotson

Electronic Theses and Dissertations

This study examined the relationship between participation in the Tennessee Reconnect (TNReconnect) program and the retention of adult learners at two community colleges in northeast Tennessee. Grounded in Astin’s (1993) Input–Environment–Outcome (I-E-O) model, the study employed quantitative methods to investigate whether program duration, demographic characteristics, academic performance, and financial aid status predicted the likelihood of retention among adult learners.

Using institutional records of 2,355 students, binary logistic regression analyses were conducted across three models. The first model tested whether the duration of TNReconnect participation predicted retention. Results indicated that both program duration and GPA were significant predictors. Each additional semester …

Assessing Post-Pandemic Engagement In The Supplemental Nutrition Program For Women, Infants, And Children (Wic) In Northeast Tennessee, Christen Minnick

Electronic Theses and Dissertations

Since 1974, the federal Supplemental Nutrition Program for Women, Infants, and Children (WIC) has provided healthy food resources, nutrition education, and provider referrals for families at risk for poor nutrition. Public health professionals have consistently presented evidence that WIC engagement reduces premature births and infant mortality, improves child health and development, and increases specialized care access for participants. While average monthly participation in WIC has increased since the program’s inception, trends indicate that only around half of eligible families have consistently engaged with the program since 2011. Research has linked declining WIC participation to administrative burden, citing learning, psychological, compliance, …

Educator Perceptions Of Mindfulness Education In Rural Elementary Schools In Tennessee, Mary C. Shepherd-Mcgown

Electronic Theses and Dissertations

The purpose of this phenomenological study was to examine educator perceptions of mindfulness instruction and the alignment of school policies in rural elementary schools in Tennessee. Despite growing interest in mindfulness in education, few studies have investigated how these practices are experienced and implemented within under-resourced, rural contexts.

Guided by Bandura’s Social Learning Theory (SLT) and framed conceptually by the Whole-School Mindfulness (WSM) model, the study explored how social, organizational, and policy factors influence the adoption of mindfulness practices. SLT provided a theoretical lens for understanding how educator behaviors are shaped through observation, modeling, and reinforcement, while the WSM framework …

Stochastic Functional Data-Driven Models For Real-Time Battery Health Forecasting Under Dynamic Operating Conditions, Joshua Owusu

Electronic Theses and Dissertations

This thesis provides an effective statistical model to predict the real-time state of lithium-ion batteries for reliable Battery Management Systems (BMS). It highlights battery data (voltage, current, temperature) as smooth functional curves. The principal method demonstrates diminishing trends to health outcomes like State of Health (SoH) and Remaining Useful Life (RUL) by employing Functional Principal Component Analysis (FPCA) and Bayesian Functional Linear Models (FLMs). The primary objective is to figure out how uncertain forecasts are. Simulations demonstrate that the highest accuracy (lowest MSE) is achieved through low noise levels along with large sample sizes. The final system provides a highly …

Teacher Perceptions Of The Effectiveness Of Voluntary Pre-Kindergarten Attendance, Kimberly Taylor

Electronic Theses and Dissertations

The purpose of this study was to identify the perceptions of educators with respect to student enrollment in voluntary pre-kindergarten classes provided through the Tennessee Department of Education in public schools. The data collection strategy used to gain teacher perspectives was through conducting one-on-one interviews with 15 educators in three Tennessee school districts. To qualify for the study, teachers must have been teaching in kindergarten classrooms that receive students who had previously been enrolled in the school’s pre-kindergarten program. Data collection and analysis were based on the Grounded Theory approach which uses data that is systematically gained and analyzed to …

Deep Learning With Kalman Filter, Rexford Julius Quaye

Electronic Theses and Dissertations

This thesis presents an extension of the Kalman filter to handle nonlinear and non-Gaussian systems. The standard Kalman filter is optimal under Gaussian assumptions but struggles with more complex noise models. This work introduces a novel loss function based on the Mahalanobis distance, which incorporates the covariance structure of measurement errors, enabling the filter to adapt to non-Gaussian scenarios. The neural network framework is applied to predict the system’s process model, while retaining the classical Kalman measurement update. The proposed methodology is demonstrated through examples of car position and rocket altitude tracking. The results show that the new approach performs …

Perceptions Of Practitioners: An Examination Of Practices For Retention And Support Of Special Education Teachers, Megan L. O'Dell

Electronic Theses and Dissertations

Teacher attrition remains a critical challenge in public education, particularly among special education teachers who face unique legal, instructional, and emotional demands. This phenomenological study explored the lived experiences of current and former K–5 special education teachers to better understand the practices and resources that influence their decision to remain in or leave the profession. The central research question investigated how leadership, professional learning, and working conditions shape teacher sustainability in special education roles. Twelve participants, including six currently employed special education teachers and six who had exited the profession, participated in semi-structured interviews. Data analysis revealed five major themes: …