Digital Commons Network^™

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Hindi

Theses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). The thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows.

The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Opencil: Benchmarking Out-Of-Distribution Detection In Class Incremental Learning, Wenjun Miao, Guansong Pang, Trong-Tung Nguyen, Ruohuan Fang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning ability, while being able to reject unknown samples that are drawn from different distributions of the learned classes. This capability is crucial to the safety of deploying CIL models in open worlds. However, despite remarkable advancements in the respective CIL and OOD detection, there lacks a systematic and large-scale benchmark to assess the capability of advanced CIL models in detecting OOD samples. To …

Comprehensively Evaluating The Perception Systems Of Autonomous Vehicles Against Hazards, Xiaodong Zhang, Jie Bao, Jianlei Chi, Jun Sun, Zijiang Yang

Research Collection School Of Computing and Information Systems

Perception systems are vital for the safety of autonomous driving. In complex autonomous driving scenarios, autonomous vehicles must overcome various natural hazards, such as heavy rain or raindrops on the camera lens. Therefore, it is essential to conduct comprehensive testing of the perception systems in autonomous vehicles against these hazards, as demanded by the regulatory agencies of many countries for human drivers. Since there are many hazard scenarios, each of which has multiple configurable parameters, the challenges are (1) how do we systematically and adequately test an autonomous vehicle against these hazard scenarios, with measurable outcome; and (2) how do …

Interpretable Machine Learning For Personalized Profiling Of Mild Cognitive Impairment From Daily Activities, Budhitama Subagdja, Ah-Hwee Tan, Kenneth Kwok, Iris Rawtaer

Research Collection School Of Computing and Information Systems

Continuous monitoring of individual daily activities is essential to detect mild cognitive impairment (MCI) wherein timely intervention can still be applied to prevent more severe mental decline. Recent approaches in predicting MCI are mostly considering digital biomarkers across individuals but often neglecting specific indicators from a single person over a long period of time. Making this personalized, dynamic, and highly noisy prediction model with irregular distribution of missing information to be explainable and actionable for clinical use, remains a challenge. This paper presents a study on a personalized MCI prediction and profiling from an in-home and mobile cognitive health monitoring …

Plm-Effector: Unleashing The Potential Of Protein Language Models For Bacterial Secreted Protein Prediction, Dandan Zheng, Lihong Chen, Guansong Pang, Jian Yang

Research Collection School Of Computing and Information Systems

Bacterial secreted proteins, particularly effectors delivered by specialized secretion systems, are key mediators of virulence and host-pathogen interactions. However, accurate computational identification remains challenging, as many existing methods rely heavily on sequence similarity or handcrafted features, and often focus on a single secretion system. Recent studies have reported that some bacterial effectors may be associated with more than one secretion system, highlighting the complexity of secretion system annotation and motivating the development of system-aware computational prediction approaches. Here, we present PLM-Effector, a hybrid deep learning framework that integrates modern protein language models (PLMs) with multiple neural architectures via a two-layer …

A Cryptographic Perspective On The Verifiability Of Quantum Advantage, Nai-Hui Chia, Honghao Fu, Fang Song, Penghui Yao

Computer Science Faculty Publications and Presentations

In recent years, achieving verifiable quantum advantage on a NISQ device has emerged as an important open problem in quantum information. The sampling-based quantum advantages are not known to have efficient verification methods. This article investigates the verification of quantum advantage from a cryptographic perspective. We establish a strong connection between the verifiability of quantum advantage and cryptographic and complexity primitives, including efficiently samplable, statistically far but computationally indistinguishable pairs of (mixed) quantum states (EFI), pseudorandom states (PRS), and variants of minimum circuit size problems (MCSP). Specifically, we prove that a) a sampling-based quantum advantage is either verifiable or can …

Transfer Learning Neural Networks For Nuclear Forensic Image Morphology Using Image Splitting Techniques, Niko A. Petrocelli, Lee C. Lambert, Brett J. Borghetti, Abigail A. Bickley

Faculty Publications

Manual morphological analysis of actinide particles from scanning electron microscope (SEM) imagery is a critical component of nuclear forensics but is prone to significant inter-analyst variability. To address this challenge, this work develops and evaluates an automated classification method using deep learning. We introduce a methodology based on partitioning 1906 SEM images, representing 13 classes of uranium compounds, into smaller patches for analysis. Three convolutional neural network (CNN) architectures of increasing complexity were compared: a custom baseline CNN, a simple transfer learning model using ResNet50v1, and a complex model featuring hierarchical feature extraction and a spatial attention mechanism built upon …

Stard-Net: Spatiotemporal Attention For Robust Detection Of Tiny Airborne Objects From Moving Drones, Hasibur Rahman, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

The rapid adoption of drones across various domains, alongside advancements in computer vision, has driven growing interest in vision-based airborne object detection from moving aerial platforms. However, this task remains challenging due to the small scale of objects, camouflage within cluttered backgrounds, and occlusions. To address these challenges, we introduce an end-to-end detection framework that integrates a Drone Receptive Field Block (DRFB) to extract multiscale and geometrically diverse features, specifically designed to enhance the detection of small and camouflaged airborne objects. To model motion patterns over time while preserving spatial structure, particularly for detecting camouflaged, cluttered and occluded objects with …

Graph Convolution Neural Network And Deep Q-Network Optimization-Based Intrusion Detection With Explainability Analysis, Kelvin Mwiga, Mussa Dida, Leandros Maglaras, Ahmad Mohsin, Helge Janicke, Iqbal H. Sarker

Research outputs 2022 to 2026

As networks expand in size and complexity, coupled with an exponential increase in intrusions on network and IoT systems, this leads to traditional models failing to capture increasingly intricate correlations among network components accurately. Graph Convolution Networks (GCNs) have recently acquired prominence for their capacity to represent nodes, edges, or entire graphs by aggregating information from adjacent nodes. However, the correlations between nodes and their neighbours, as well as related edges, differ. Assigning higher weights to nodes and edges with high similarity improves model accuracy and expressiveness. In this paper, we propose the GCN-DQN model, which integrates GCN with a …

An Explainable Transformer-Based Model For Phishing Email Detection: A Large Language Model Approach, Mohammad Amaz Uddin, Md Mahiuddin, Iqbal H. Sarker

Research outputs 2022 to 2026

Phishing email is a serious cyber threat that tries to deceive users by sending false emails with the intention of stealing confidential information or causing financial harm. Attackers, often posing as trustworthy entities, exploit technological advancements and sophistication to make the detection and prevention of phishing more challenging. Despite extensive academic research, phishing detection remains an ongoing and formidable challenge in the cybersecurity landscape. In this research paper, we present a fine-tuned transformer-based masked language model, RoBERTa (Robustly Optimized BERT Pretraining Approach), for phishing email detection. In the detection process, we employ a phishing email dataset and apply the preprocessing …

N-Dqn: Neutrosophic Deep Q-Network For Uncertainty-Aware Forecasting And Decision Optimization, Rania Lutfi

Neutrosophic Systems with Applications

Uncertainty remains a critical challenge in dynamic spatiotemporal forecasting. This study proposes the Neutrosophic Deep Q-Network (N-DQN), a framework that integrates neutrosophic logic with deep reinforcement learning to enhance decision optimization under uncertainty. Features are modeled through truth, indeterminacy, and falsity membership functions, enabling robust handling of ambiguous data. The framework incorporates attention-guided preprocessing and horizon-aware optimization to adapt predictions across short- and long-term intervals. Experiments on benchmark traffic datasets (METR-LA and PEMS-BAY) demonstrate improved forecasting accuracy and reduced error rates compared with established baselines. The results highlight the scalability and resilience of N-DQN, positioning it as a promising approach …

Neutrosophic Finsler–Cohomological Framework For Engineering Systems Under Uncertainty, Mona Gharib, Ghulam Muhammad, Muhammad Idrees, Zeeshan Gul

Neutrosophic Systems with Applications

This paper introduces a novel mathematical framework that combines Neutrosophic Finsler Geometry with Neutrosophic Cohomology for evaluating the performance of Brushless Direct Current (BLDC) motors under uncertain and indeterminate operating conditions. Classical motor performance models typically assume precise measurements of torque, current, and efficiency; however, in real-world settings, these parameters are often affected by noise, incomplete information, and conflicting observations. By embedding motor operating states into a neutrosophic Finsler space, the proposed approach captures variations not only in magnitude but also in direction, uncertainty, and conflict of performance metrics. In addition, neutrosophic Cohomology is employed to characterize global invariants of …

An Uncertainty-Aware Entropy-Oreste Framework For Big Data Platform Selection In Complex Multi-Sector Environments, Ahmed M. Ali, Ibrahim Alrashdi, Karam M. Sallam

Neutrosophic Systems with Applications

The increasing reliance on Big Data platforms across various industries has necessitated the development of systematic decision-support frameworks to guide their evaluation and selection. Given the diversity of available platforms, each offering different capabilities, scalability, and computational efficiency, choosing the optimal solution remains a complex challenge. This research proposes a novel analytical framework that integrates Spherical Fuzzy Sets (SFS) with the Entropy and ORESTE methods to address uncertainty and enhance the accuracy and robustness of Big Data platform evaluation. This hybrid integration, not previously applied to Big Data platform selection, enables objective criteria weighting through the Entropy method and comprehensive …

Single-Valued, Double-Valued, Triple-Valued, Quadruple-Valued, And Quintuple-Valued Neutrosophic Graph, Takaaki Fujita, Arif Mehmood, Arkan A. Ghaib

Neutrosophic Systems with Applications

Concepts such as fuzzy sets, neutrosophic sets, rough sets, and plithogenic sets have been extensively studied as formal tools for modeling uncertainty, and they have found broad applications across many disciplines. A Double-Valued Neutrosophic Set (DVNS) extends the classical neutrosophic framework by splitting indeterminacy into two distinct components: one leaning toward truth and the other leaning toward falsity. In recent years, further refinements—namely Triple-Valued, Quadruple-Valued, and Quintuple-Valued Neutrosophic Sets—have also been introduced and investigated. These uncertainty models have naturally been lifted to graph-theoretic settings, where vertices and edges represent entities and relationships under ambiguity. Although fuzzy graphs and neutrosophic graphs …

Evaluating Domains' Trustworthiness Based On Uncertainty-Driven Methodologies In The Era Of Sixth Generation, Zekra Sakr, Mona Mohamed

Neutrosophic Systems with Applications

The onset of today's innovations pledges to have a beneficial influence on contemporary civilization in an era of intelligent revolutions, setting a precedent for unrivaled efficiency, creativity, and connectedness. The integration between these technologies contributes to the mutual benefit of each one, wherein this relation is a so-called ``reciprocal partnership''. For instance, the sixth generation (6G) wireless networks permit blockchain nodes to coordinate huge volumes of transaction data in real-time. On the other hand, blockchain is considered a secure valve because spectrum sharing can be automated with blockchain and smart contracts. Accordingly, analyzing and evaluating the contribution of these technologies …

Client Feedback Effects On Enjoyment, Motivation And Self-Efficacy In A Project-Based Learning Course, Krista Stacey, David M. Bourrie

University Faculty and Staff Publications

This paper reports a mixed-methods evaluation of how feedback/project source (faculty-led versus client-led) shapes student outcomes in a two-course undergraduate game and simulation development sequence (N = 29 across two academic years). Quantitative measures (enjoyment, intrinsic motivation, self-efficacy) were collected with a six-point Likert survey and analyzed, but due to small sample sizes were not used to empirically evaluate the constructs. Instead, qualitative data comprised of de-identified focus-group transcripts and open-ended survey responses were analyzed with a keyword-assisted codebook and manual validation. Year 1 (faculty feedback) exhibited more consistent post-course gains, especially in self-efficacy, while Year 2 (client feedback) produced …

Ai Transformation In Education: Examining Teachers’ Perceptions Using An Integrated Tam-Tpack-Genai Framework, Areej Elsayary, Ghadah Al Murshidi, Karim Ragab, Ahmed Al Zaabi

All Works

Artificial intelligence (AI) is transforming educational systems by enhancing teaching, assessment, and learning personalization. This study investigated teachers’ perceptions of AI integration using an integrated technology acceptance model (TAM), technological pedagogical content knowledge (TPACK), and generative artificial intelligence (GenAI) framework. The main constructs used are perceived usefulness (PU), attitudes toward use (ATU), and behavioral intention (BI), with GenAI dimensions (agency, amplification, adaptivity, and authenticity) embedded within them. The study employed a cross-sectional design with 332 teachers in the emirate of Al Ain, United Arab Emirates. Results showed that PU was the strongest predictor of both ATU and BI, while ATU …

Sensi-Train: Context-Aware Sensitive Content Detection Using Transformers And Large Language Models, Nazeefa Muzammil

USF Tampa Graduate Theses and Dissertations

The detection of sensitive content has become a critical task in natural language processing due to the widespread use of online platforms and the social harm caused by it. Even though current methods have advanced significantly, many of them mainly rely on surface-level text and neglect to take into consideration contextual and cultural elements that are crucial for correctly assessing sensitivity of any content to a particular individual. Due to this, implicit offense, sarcasm, and culturally grounded expressions frequently cause problems for such systems. To enable culturally grounded sensitive content detection, this thesis presents Sensi-Train, a context-rich dataset and modeling …

Bl(U)E Crab: Bluetooth Low Energy Connection Risk Assessment Benchmarking, Dylan Christopher Conklin

Dissertations and Theses

The usage of Bluetooth Low Energy (BLE)-based tracker devices for stalking has become a salient privacy concern. Detecting unwanted or suspicious trackers is challenging due to their cross-platform compatibility issues, inconsistent detection methods, and lack of an industry-wide standard for detecting malicious devices. BL(u)E CRAB, Bluetooth Low Energy Connection Risk Assessment Benchmarking, scans data and generates risk factors about nearby devices to classify them as suspicious or not. These risk factors include the number of encounters the user had with a device, the duration of time a device has been near the user, the distance a device has traveled …

Artificial Intelligence-Driven Materials Science: Evolution, Framework, Dilemmas, And Breakthroughs, Yanglili Zhou, Weihua Wang, Ziwei Zhao

Bulletin of Chinese Academy of Sciences (Chinese Version)

Artificial intelligence-driven materials science (AIMS) represents a revolutionary and disruptive paradigm in materials research, promising to fundamentally break through the traditional bottlenecks of research cycles and efficiency. Historically, the evolution of materials science research paradigms from empirical trial and error, theoretical modeling, and computational simulation to the new data-driven stage has been driven by innovations in cognitive tools and methods. Currently, artificial intelligence, as a disruptive cognitive tool, is fundamentally reconstructing the core elements and interaction logic of materials science: the research process achieves intelligent iteration and full-process closed-loop; the capabilities of researchers are reshaped and teams are organized; and …

Study On Strategies And Measures And Insights For Introducing Artificial Intelligence Talents In Japan, Fangxin Hu, Ru Ma, Yujun Su

Bulletin of Chinese Academy of Sciences (Chinese Version)

In response to the aging population and the need for innovation in science and technology development, Japan regards AI as a key technology to solve social problems. In addition to accelerating the training of domestic AI talents, Japan is also vigorously introducing overseas AI talents. This study sorts out and analyzes Japan’s long-term, annual, and AI-specific strategic planning for the introduction of AI talents, including Basic Plan for Science, Technology and Innovation, Comprehensive Innovation Strategy, Strategic Plan for Artificial Intelligence Technology, and AI Strategy, and explores Japan’s specific implementation measures such as updating the national residence management system, improving the …

Unraveling Patch Size Effects In Vision Transformers: Adversarial Robustness In Hyperspectral Image Classification, Shashi Kiran Chandrappa, Sidike Paheding, Abel A. Reyes-Angulo

Michigan Tech Publications

Highlights: This work investigates the effect of spatial patch size on the classification accuracy and adversarial robustness of Vision Transformer-based architectures for hyperspectral image analysis. What are the main findings? Smaller patch sizes generally exhibit stronger adversarial robustness while maintaining comparable clean classification performance. Larger patch sizes tend to reduce robustness by increasing sensitivity to localized adversarial perturbations, with some dataset-dependent variations. What are the implications of the main findings? Spatial patch size is an important design consideration when applying Vision Transformers to hyperspectral image classification tasks. The findings provide practical guidance for informed patch-size selection in robust, deployment-aware transformer-based …

Cerebral Documents And Algorithmic Sensemaking: Searching For Expressions In Human And Artificial Cognitive Collaborations, Rebekah L. Cowell

Proceedings from the Document Academy

Generative Artificial Intelligences (AIs) and current advanced large language models (LLMs) are algorithmically designed to generate text-based conversations as conversational agents (CAs), by replicating human language and conversational communication. Pairing human cognition with generative computationally coded cognition. We have never been here before: cerebral and artificial information collaborations and processing producing expressions that may or may not become visible as second-hand/secondary source documents.

Sensemaking or sense(un)making is a unique autonomous human drive cognitively, our information processing is sensemaking in action and expressions and articulations are evidence of the sensemaking cycle. Documentation [expressed or articulated through various mediums] are a product …

Ai-Guided Binding Mechanisms And Molecular Dynamics For Mers-Cov, Pradyumna Kumar, Lingtao Chen, Rachel Yuanbao Chen, Yin Chen, Seyedamin Pouriyeh, Progyateg Chakma, Abdur Rahman Mohd Abul Basher, Yixin Xie

Faculty Articles

The MERS-CoV (Middle East respiratory syndrome coronavirus) is a zoonotic virus with a high mortality rate and a lack of antiviral drugs, underscoring the need for effective therapeutic methods. Viral entry depends on interactions between viral surface proteins and human receptors, with Dipeptidyl Peptidase-4 (DPP4), a transmembrane glycoprotein, acting as the receptor for MERS-CoV. We employed Molecular Dynamics (MD) Simulations to identify critical interface residues under a high-performance computing (HPC) workflow for accelerated results. Target residue pairs were identified through analysis of salt bridge and hydrogen bond occupancy. The stability of these residues was confirmed through three independent MD Simulations …

Evolutionary Game-Based Analysis Of Responses To Hallucinations In Generative Artificial Intelligence, Qiang Yan, Qianyu Zhang, Na Wei

Journal of System Simulation

Abstract: The accelerated deployment of generative artificial intelligence, particularly large language models, has amplified the social risks of hallucinations, posing systemic threats to the credibility of the information ecosystem, the effectiveness of users’ cognitive decision-making, and the governance security in the public domain. Research primarily focuses on hallucination mitigation mechanisms at the technical level or the design of regulatory frameworks at the policy level, lacking a systematic theoretical analysis of the evolutionary logic of strategic interactions among the “large language models, users, and regulators” under conditions of bounded rationality. By introducing evolutionary game theory into the field of generative artificial …

Simulation Method For Multi-Crew Construction Processes Based On Large Language Model-Powered Agent, Yifan Wang, Bin Yang, Congjun Wang

Journal of System Simulation

Abstract: Traditional construction simulation methods typically rely on predefined rules or static scheduling mechanisms, making it difficult to simulate interactive decision-making under complex constraints by dynamically adapting multi-crew construction scenarios. As a result, workforce idleness caused by process dependencies and spatial occupation fails to be solved. A simulation method for multicrew construction processes based on a LLM-powered agent was proposed. The distributed crew agents endowed with construction scenario understanding and reasoning capabilities were constructed, as well as a centralized project manager agent. A “single-manager and multiple-crew” decision-making mechanism for multi-agent interaction in construction was designed. Autonomous decision-making and coordination mechanism …

Hybrid 3d Modelling Framework For Indoor Navigation Using Federated Learning And Internet Of Things-Enabled Edge Devices, Noopur Tyagi, Jaiteg Singh, Saravjeet Singh, Ahmad Ali Alzubi, Farman Ali, Sukhjit Singh Sehra, Babar Shah

All Works

Background There has been a recent trend towards using three-dimensional (3D) models to enhance spatial awareness and maximize resource utilization in complex environments. 3D building model can be used in various applications, such as real-time guidance and tracking the positions of individuals in multi storied buildings. Cities are now being modeled and studied in three dimensions as an improved method of urban planning. Method This study proposes an advanced indoor navigation framework that combines 3D modelling, federated learning (FL), and Internet of Things (IoT) integration to deliver reliable floor-level localization and real-time guidance. In Phase 1, highly accurate 3D models …

Empowering Neurodiverse Talent In Cybersecurity Through Fair And Inclusive Ai Education, Sheikh Rabiul Islam, Yansi Keim, Mohiuddin Ahmed, Maanak Gupta, Ingrid Russell, Mahmoud Abdelsalam

Research outputs 2022 to 2026

Cybersecurity demands creativity, persistence, and sharp pattern recognition—strengths frequently reported among neurodivergent people (e.g., autism, ADHD, dyslexia). Yet AI-driven hiring pipelines can systematically disadvantage neurodivergent applicants by misreading communication styles or valuing narrow proxies of “fit.” Demand for cybersecurity talent is growing, and experts note that neurodiverse individuals are both underrepresented and highly valuable to security teams. However, progress remains uneven without targeted educational interventions [1]. We present a curricular module that simultaneously (a) centers neurodiversity as a strength in the cybersecurity workforce and (b) trains students to audit and redesign AI hiring systems using open-source fairness and explainability toolkits …

Molecular Detection Of Genes Encoded For Biofilm Formation In Bacteria Isolated From The Oral Cavity Of Patients, Tebarek Al-Taei, Ali A. Al-Hisnawi

Karbala International Journal of Modern Science

Background: A biofilm is a collection of the microbial cells attached to the surface that are encased in a matrix of extracellular polymers. Biofilm formation creates a physical and chemical barrier that prevents antibiotics from reaching bacterial cells, resulting in treatment failure and reinfection. The present study aimed to investigate the biofilm formation in bacteria isolated from the oral cavity of patients.

Methods: In this study, 150 bacterial isolates were obtained from tooth and gum surface swabs of male and female patients of different ages who visited specialized centers and dental clinics in Babylon City after they were clinically diagnosed …

On Cartan’S Examples Of Isoparametric Hypersurfaces And Their Focal Submanifolds, Thomas E. Cecil, Patrick J. Ryan

Mathematics and Computer Science Department Faculty Scholarship

This paper is a survey of Cartan’s examples of isoparametric hypersurfaces in spheres and their focal submanifolds that were described in his fundamental work on the subject, which appeared in four papers [2]–[5] published during the period 1938–1940.