Digital Commons Network^™

Portrait Shadow Removal Via Self-Exemplar Illumination Equalization, Qian Huang, Cheng Xu, Guiqing Li, Ziheng Wu, Shengxin Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing …

Patchgpt: Multi-Agent Patch Backporting Without Model Fine-Tuning, Ye Liu, Ruidong Han, Chengyan Ma, Yuqing Niu, David Lo

Research Collection School Of Computing and Information Systems

Patch backporting is crucial and prevalent in the maintenance of modern open-source software such as Linux kernels and forked repositories. However, porting patches across program versions remains a challenging problem due to the complexity of synergizing diverse patches with divergent program versions. In this paper, we propose PatchGPT, an agentic patch backporting framework for fine-grained patch generation. PatchGPT encompasses three agents: Miner for decomposing a sequence of atomic change steps as the original patch plan, Adapter for adapting the patch plan, and Executor for executing the adapted patch plan according to predefined change semantics. We conduct experiments on the PPatHF’s …

Understanding Codebase Like A Professional! Human-Ai Collaboration For Code Comprehension, Jie Gao, Yue Xue, Xiaofei Xie, Junming Cao, Soemin Thant, Erika Lee, Bowen Xu

Research Collection School Of Computing and Information Systems

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension remains challenging for both experienced and novice developers, even with the assistance of large language models (LLMs). Existing studies have shown that LLMs often fail to support users in understanding code structures or to provide user-centered, adaptive, and dynamic assistance in real-world settings.To address this, we propose learning from the perspective of a unique role, code auditors, whose work often requires them to quickly familiarize …

Fully Decentralized Hierarchical Federated Learning At The Edge With Post-Quantum Secure Communication, Tariq Qayyum

Dissertations

Federated learning (FL) enables collaborative model training without centralizing raw data, but deploying FL at scale in real edge environments remains challenging because iterative training and aggregation must operate over heterogeneous, resource-constrained, and often mobile devices with time-varying connectivity. Conventional hierarchical federated learning (HFL) partially mitigates communication cost by introducing fog/edge aggregation, yet many designs retain cloud-based global aggregation and cloud-centric coordination. This places wide-area network latency on the critical path of every training round, creates a single point of failure, and limits responsiveness as model sizes and federation scale grow. Moreover, moving coordination and aggregation closer to the edge …

Trustgen: A Platform Of Dynamic Benchmarking On The Trustworthiness Of Generative Foundation Models, Yue Huang, Et. Al

Research Collection School Of Computing and Information Systems

Generative foundation models (GenFMs), such as large language models and text-to-image systems, have demonstrated remarkable capabilities in various downstream applications. As they are increasingly deployed in high-stakes applications, assessing their trustworthiness has become both a critical necessity and a substantial challenge. Existing evaluation efforts are fragmented, rapidly outdated, and often lack extensibility across modalities. This raises a fundamental question: how can we systematically, reliably, and continuously assess the trustworthiness of rapidly advancing GenFMs across diverse modalities and use cases? To address these gaps, we introduce TrustGen, a dynamic and modular benchmarking system designed to systematically evaluate the trustworthiness of GenFMs …

Intelligent Deep Learning-Based Sign Language Translation System, Nada Rasem Shahin

Dissertations

The Deaf and Hard of Hearing (DHH) community uses sign language as a primary means of communication. However, the shortage of sign language interpreters and the existence of hundreds of sign languages limit accessibility and inclusion. Sign Language Machine Translation (SLMT) systems present a promising solution for bridging the communication gap between the DHH and the hearing individuals, supporting inclusive societies. In smart cities, such systems play an essential role in improving the quality of life on a community level. In particular, as the population’s well-being is critical, developing intelligent assistive technologies, such as SLMT systems, is necessary to provide …

A Comparative Study On Performance Of Iot-Driven Ml-Enabled Forecasting Models For Efficient Air Quality Monitoring, Bara Ksiksi

Theses

Air pollution is one of the most critical environmental challenges affecting public health globally, responsible for approximately 4.2 million premature deaths annually according to the World Health Organisation. This thesis presents a comparative study of IoT-driven machine learning forecasting models for air quality monitoring in Abu Dhabi, UAE, introducing a zonal approach combined with satellite-based spatial validation. The primary objective is to evaluate forecasting performance across three distinct activity zones using ground station data from the Environment Agency Abu Dhabi (EAD), and to incorporate a spatial validation component using satellite imagery to assess the consistency of ground-based predictions at a …

Dragging With Geometry: From Pixels To Geometry-Guided Image Editing, Xinyu Pu, Hongsong Wang, Jie Gui, Pan Zhou

Research Collection School Of Computing and Information Systems

Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primarily on the 2D pixel plane with limited use of 3D cues. As a result, they often produce imprecise and inconsistent edits, particularly in geometry-intensive scenarios such as rotations and perspective transformations. To address these limitations, we propose a novel geometry-guided drag-based image editing method—GeoDrag, which addresses three key challenges: 1) incorporating 3D geometric cues into pixel-level editing, 2) mitigating discontinuities caused by geometry-only guidance, and 3) resolving conflicts arising from multi-point dragging. Built upon a unified displacement …

Real-Time Motion-Controllable Autoregressive Video Diffusion, Kesen Zhao, Jiaxin Shi, Beier Zhu, Junbao Zhou, Xiaolong Shen, Yuan Zhou, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to simple control signals or text-to-video generation, and often suffer from quality degradation and motion artifacts in few-step generation. To address these challenges, we propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control. We first fine-tune a base I2V model to support basic motion control, then further improve it via reinforcement learning with a trajectory-based reward model. Our design preserves the …

Reasoning On Time-Series For Financial Technical Analysis, Kelvin J. L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations and …

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 …

Learning Techniques In Prediction Of Functional Epigenomic Events, Mohammad Shiri

Computer Science Theses & Dissertations

Accurately predicting functional epigenomic events from DNA sequences is critical to understanding gene regulation and the functional impact of non-coding variants. Despite considerable progress, critical challenges hamper the effectiveness and efficiency of existing deep learning approaches. These challenges include negative transfer in multi-task learning (MTL), suboptimal network architectures, and pervasive label noise, particularly the positive-unlabeled problem arising from data sparsity in single-cell assays. This dissertation presents a cohesive framework of novel learning techniques to effectively address these challenges. First, a highly scalable task grouping framework is presented to mitigate negative transfer in deep MTL. This method clusters tasks based on …

Behavioral, System, And Informational Cyberattacks: A Human-In-The-Loop Driving Simulator Experiment, Samuel Petkac

Psychology Theses & Dissertations

Advanced technologies such as sensors and AI/ML algorithms have enabled increasing levels of automated driving system that detects, responds, and even predicts changes in a driving environment supported by wireless connectivity to nearby vehicles and infrastructure. Such connected and automated vehicles (CAVs) can be particularly vulnerable to cyberattacks targeting not only infotainment systems but also firmware and other applications, critically compromising driver safety. As we anticipate a “mixed” traffic where vehicles with various levels of automated technologies share the road for the foreseeable future, it is urgent to systematically examine types of possible cyberattacks and control human behaviors in such …

Dissecting The Etiology Of Alcohol Use Disorder By An Integrative Heritable Component Approach, Ivy Garrenton

Computer Science Theses & Dissertations

Alcohol Use Disorder (AUD) is a pervasive condition characterized by complex interplay among genetic, phenotypic, and environmental factors. Although previous studies have identi fied genetic loci associated with alcohol consumption, these efforts have not captured the genetic heterogeneity and gene-environment interactions underlying AUD pathogenesis. To address this critical gap, we developed a novel statistical methodology that integrates phenotypic, genotypic, and environmental data through an environmentally modified Genetic Relationship Matrix (GRM) to derive AUD-related traits with enhanced heritability.

This approach demonstrated superior performance in both simulated and real-world datasets. Traits derived using the environmentally modified GRM exhibited significantly higher estimated heritability …

A General Weighting Theory For Ensemble Learning: Beyond Variance Reduction Via Spectral And Geometric Structure, Ernest Fokoue

Articles

Ensemble learning is traditionally justified as a variance-reduction strategy, explaining its strong performance for unstable predictors such as decision trees. This explanation, however, does not account for ensembles constructed from intrinsically stable estimators-including smoothing splines, kernel ridge regression, Gaussian process regression, and other regularized reproducing kernel Hilbert space (RKHS) methods whose variance is already tightly controlled by regularization and spectral shrinkage. This paper develops a general weighting theory for ensemble learning that moves beyond classical variance-reduction arguments. We formalize ensembles as linear operators acting on a hypothesis space and endow the space of weighting sequences with geometric and spectral constraints. …

Development Of Deep Fused Neural Architecture For Ancient Tamil Palm-Leaf Manuscript Recognition, Hariharan P Mr

Theses and Dissertations

Digitizing Tamil palm-leaf manuscripts is important for education, communication, and the preservation of cultural heritage. The complex structure of the Tamil script, the wide range of handwriting styles, and the degradation seen in ancient Tamil palm-leaf manuscripts make these texts very difficult to read and understand. Digital Image Processing (DIP), document analysis techniques, and traditional Optical Character Recognition (OCR) are unable to handle noise, background interference, faded ink, and limited labelled data, motivating the need for robust, effective Deep Learning (DL)- based solutions.

As a prerequisite to understanding and designing effective recognition systems for ancient manuscripts, this thesis first examines …

Enhancing Introductory Cybersecurity Learning: A Design-Based Research Case Study, Manny Niri Dr.

Journal of Cybersecurity Education, Research and Practice

This study employs a design-based research (DBR) framework to examine the impact of a comprehensive curriculum redesign in an introductory Foundations of Security module for undergraduate students in computing and cybersecurity at a UK public university between 2019 and 2025. The redesign aimed to enhance student learning, engagement, and critical thinking through the embodiment of evidence-based pedagogical strategies, including flipped classroom delivery, blended learning, gamified practical exercises, repeated low-stakes mock assessments, and structured problem-solving activities. Student feedback, assessment outcomes, attendance records, and faculty reflections were analysed to evaluate the effectiveness of the redesign. The results indicate substantial improvements in student …

The Core-Modulation Architecture (Cma): A Structural Overview Of A 14-Paper Research Program (Preprint), Griselda Poe

Publications and Research

This document provides a structural overview of the Core-Modulation Architecture (CMA), a 14-paper research program on cognition, communication, and AI interaction.

The series specifies the conditions under which cognition operates, terminates, fails, and generates structure. Rather than describing cognition by its contents (beliefs, emotions, decisions), it defines cognition through its underlying architecture: constraint-governed processing across layers with distinct termination conditions.

The framework introduces a layered model consisting of Core processing (constraint preservation and structural coherence) and Modulation (affective calibration and social interface adjustment), extended by a Prior layer as the source of constraints. Across the series, phenomena such as miscommunication, …

Classification Of Land Cover In Sentinel-2 Imagery Using Machine Learning Models, Ehsan Ali Al-Zubaidi, Mohammed Ridha Hammoodi, Ahmed Naser Alzurfi

Al-Bahir

Remote sensing data of medium resolution are commonly used to classify land cover, and machine learning (ML) models have taken on a central aspect in the necessary data analysis. Ordinarily, land cover is coded on a pixel basis on the basis of Digital Number (DN) values, which in turn are computed across several spectral bands. This paper is concerned with land cover mapping in Mosul, Iraq, based on satellite images captured by Sentinel-2. Two platforms featuring unsupervised classification algorithms were used, Google Earth Engine and ArcMap, making it possible to use K-means and X-means in Google Earth Engine and ISO …

The Waldo Dataset, Mary E. Koone, Rosie Kallie, Vassilis Athisos, Laurel S. Stvan

Computer Science and Engineering Datasets - Archive

Distinct from the task of predicting the author of a document (authorship attribution), we focus on addressing the issue of how to estimate the similarity between the written language styles of authors. To do so, we present a dataset of metadata derived by asking human annotators, who were presented with three documents, to identify which two were written by the same author and which was written by a different author. The dataset has over 400 such annotations, creating a companion to the Amazon Web Services (AWS) customer review dataset, laying the groundwork for crowdsourcing applications to other natural language processing …

Geospatial Understanding Of Foundation Models: Self-Supervision, Robustness, And Resource-Constrained Learning, Gilbert Kibet Rotich

USF Tampa Graduate Theses and Dissertations

Research on large-scale geospatial understanding from satellite imagery remains relativelyunderexplored. Much of the field still relies on narrow, task-specific pipelines, and there is lim- ited work on developing true foundation models or on systematically evaluating how well these models generalize under domain shift, geographic variation, and real-world scene diversity. This dissertation advances foundation-model pretraining and evaluation for remote sensing along three complementary axes. First, we develop self-supervised multispectral pretrained models for satellite image classification by adapting BYOL, BarlowTwins, DINO, MoCo, and Simsiam to multispectral inputs, addressing the limited amount of curated satellite datasets relative to ImageNet. Pretraining on Eurosat and …

Multi-Modal Tensor Fusion For Alzheimer’S Disease Recognition, Mason Li, Tiffany Le, Jiajing Huang, Yuxin Wen

Engineering Faculty Articles and Research

Accurate and early diagnosis of Alzheimer’s disease (AD) is critical for effective intervention, disease monitoring, and patient care. Traditional diagnostic approaches rely on a single modality, such as clinical assessments, neuroimaging, or genetic markers, which may fail to capture the complex, multifaceted nature of AD. Multimodal learning has therefore been explored to integrate complementary information across data sources. However, conventional fusion strategies, including early feature concatenation and late decision-level fusion, often model modalities independently and fail to capture high-order cross-modal interactions. To address these limitations, we propose a multimodal tensor fusion network (MTFN) that integrates heterogeneous data sources, including visual …

Secure Machine Learning In Networking Systems, Wenwei Zhao

USF Tampa Graduate Theses and Dissertations

With the rapid integration of Machine Learning (ML) into networking systems, ensuring the security and trustworthiness of these intelligent frameworks has become a paramount concern. While ML offers unprecedented capabilities in spectrum management and collaborative learning, it also introduces novel vulnerabilities that can be exploited by sophisticated adversaries. This dissertation investigates and addresses critical security challenges across three key dimensions of ML-driven networking: adversarial spectrum sensing, the security of privacy-preserving unlearning processes, and efficient post-attack model recovery.

First, we address the threat of adversarial spectrum attacks in cognitive radio networks, where malicious nodes manipulate sensing reports to disrupt spectrum access. …

Marine Vehicle Dynamics Using Koopman Operator Theory With Hybrid Observables, Mikhalib A L Green

LSU Master's Theses

Accurate modeling of marine vehicle dynamics remains challenging due to strong nonlinear hydrodynamic effects, environmental disturbances, and sensitivity to configuration changes, particularly for small-scale platforms. Classical physics-based models require extensive parameter identification and often exhibit degraded performance outside narrow operating regimes, while purely data-driven approaches may lack structure or impose high computational cost. This thesis presents a data-driven Koopman operator framework with hybrid observables for modeling the dynamics of unmanned marine vehicles. The proposed approach combines structured monomial observables with a learned neural network embedding to construct a lifted state representation in which the nonlinear vehicle dynamics are approximated by …

Large-Scale File Fragment Classification Via Multi-View Learning, Samuel Hildebrand

LSU Master's Theses

File reassembly is one of the most fundamental tasks in digital forensics, enabling recovery of data from potentially damaged storage media even when file system metadata is unavailable. This thesis reviews more than two decades of work in the realm of file carving, with a particular focus on fragmented file carving, which remains a focus of research, and file fragment classification, a principal component of fragmented file carving. This thesis serves a literature review of both file carving and fragmented file carving, surveys the massive amounts of data needed for the task of fragment classification and the datasets that serve …

Secureai: Toward Experiential Security And Privacy Training For Ai Practitioners, Mujtaba Nazari, Eric Chan-Tin, Loretta Stalans, Mohammed Abuhamad

Computer Science: Faculty Publications and Other Works

The rapid adoption of artificial intelligence across industries has outpaced security and privacy training for AI practitioners. This paper presents methods, modules, and findings from an experiential training program designed to address security and privacy challenges in AI systems development and deployment. We conducted two program iterations: a comprehensive 12-workshop series (May-October 2024) and a condensed 6-workshop format (January-February 2025). The program combined expert-led panel sessions with hands-on laboratory activities, engaging 78 participants from diverse professional backgrounds. Evaluation through pre- and post-evaluation surveys and qualitative observations revealed improvements in cybersecurity knowledge and AI security awareness. Participants demonstrated enhanced ability to …

Clinical Prediction Of Posttreatment Migraine Recurrence Using Biofeedback Data: A Machine Learning Framework For Enhanced Patient Stratification And Treatment Monitoring, Shibbir Ahmed Arif, Ferdib-Al-Islam, Mehidy Hasan Sium

School of Computing Faculty Scholarship and Creative Works

Migraine is a complex neurological disorder with significant implications for individual well-being and public health. Predicting migraine occurrences after treatment is crucial for evaluating therapeutic efficacy and enabling personalized care, yet remains largely underexplored. This study proposes a robust machine learning framework to predict posttreatment migraine headache occurrences using real-world headache log data collected from 133 patients undergoing biofeedback therapy. The methodology includes rigorous data preprocessing, outlier removal via the interquartile range (IQR) method, and class imbalance correction through the synthetic minority oversampling technique (SMOTE). A total of 10 classical and a hybrid ensemble machine learning models were developed and …

Recovery And Validation Of Fragmented Rar Files Through The Scalpel3 Application, Thomas L. Landaiche Iii

LSU Master's Theses

A core component of filesystems includes an address table or other means of tracking metadata on where a given file resides within a disk image. This is crucial for regular operation of a computer, or disk analysis in digital forensics. When filesystem information is missing or corrupted, locating saved files on a disk becomes challenging. Whether the disk was accidentally wiped or intentionally tampered with, data still present on the disk, even while untracked, can possibly be recovered beyond what the filesystem registers. File carving in digital forensics is important for these scenarios when data recovery is necessary but address …

A Taxonomy Of Generative Models With A Focus On Diffusion Models And Denoising Techniques, Aditi Singh, Nikhil Kumar Chatta, Yuvaraj Vagula, Abul Ehtesham, Saket Kumar, Tala Talaei Khoei

Computer Science Faculty Publications

Diffusion models have emerged as a powerful class of generative models, demonstrating impressive results across visual domains such as image and video synthesis. This survey provides a comprehensive taxonomy of generative models, with a particular focus on diffusion models and their applications in enhancing visual fidelity for text-to-image and text-to-video generation. We discuss the theoretical foundations of diffusion models, including their formulation through stochastic differential equations, and analyze the forward noising and reverse denoising processes that enable stable training and high-quality generation. The survey further categorizes diffusion architectures, including pixel-space and latent-space models, and examines their design choices, training strategies, …

Deadmap: Open Yet Locked—Key-Controlled Dataset Protection With Feature-Level Collisions, Ting Yang, Mahabubur Rahman Miraj, Xinyu Lei, Nankun Mu, Hongyu Huang

Michigan Tech Publications

The performance of deep learning models relies heavily on high-quality datasets. However, under the prevailing paradigm of pretrained-model–based applications, once a dataset is publicly released, data owners largely lose control over how it is used for model training. Existing data protection approaches either focus on post hoc accountability or irreversibly destroy the training utility of the data through perturbations, making it difficult to simultaneously satisfy the dual requirements of offline public sharing, authorized and controllable usage. In this paper, we propose DeadMap, a reversible training usability control framework designed for model fine-tuning scenarios. DeadMap introduces a secret label permutation combined …