Digital Commons Network^™

Compiling Code Llms Into Lightweight Executables, Jieke Shi, Junda He, Zhou Yang, Chengran Yang, Mykhailo Klymenko, Thong (James) Hoang, Sherry (Xiwei) Xu, Zhenchang Xing, David Lo

Research Collection School Of Computing and Information Systems

The demand for better prediction accuracy and higher execution performance in neural networks continues to grow. The emergence and success of Large Language Models (LLMs) have produced many cloud-based tools for software engineering tasks such as code suggestion. Although effective, cloud deployment raises concerns over privacy, latency, and reliance on network connectivity. Running LLMs locally on personal devices such as laptops would address these issues, because it enables offline use and reduces response time. However, local deployment is challenging, since commodity devices lack high-performance accelerators such as GPUs and are constrained by limited memory and compute capacity, which makes it …

Are We Stuck? Modeling And Detecting Deadlocks In Multi-Autonomous Vehicle Systems, Mingfei Cheng, Xiaofei Xie, Lili Quan, Yuan Zhou

Research Collection School Of Computing and Information Systems

Autonomous driving system (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) prior to deployment. As ADSs are increasingly deployed in multi-AV traffic environments, it becomes crucial to assess their cooperative performance, particularly with respect to deadlock, a fundamental liveness issue in concurrent systems that can lead to traffic congestion and prolonged stalling. However, the analysis and testing of ADSs’ cooperative capabilities with respect to deadlock remain largely underexplored. In this work, we present the first systematic study of deadlock in multi-AV systems. We formalize deadlock in autonomous driving using a time-indexed wait-for relation grounded …

Rent-A-Rag: Embedding-Space Watermarks For Auditing Third-Party Rag, Alexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani, Nikolaos Laoutaris

Research Collection School Of Computing and Information Systems

Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet later have no visibility into whether their documents are being reused without compensation. Auditing this misuse is difficult because the operator is non-cooperative, answers are paraphrased by the generator, and one response may combine evidence from many providers. We propose DirBucket, a provider-side semantic watermarking and black-box auditing framework for document-level reuse in multi-provider RAG. DirBucket watermarks documents by meaningpreserving paraphrases whose embeddings are biased toward provider-bucket secret directions, enabling detection from black-box answers while preserving retrieval utility. On a …

Characterizing And Repairing Obsolete Android Gui Tests Under Ui Evolution, Shiwen Song, Yiheng Xiong, Wenbo Guo, Manqi Sun, Jiaolong Kong, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Graphical user interface (GUI) tests are widely used in regression testing of mobile applications (apps) tovalidate app behavior from the user’s perspective. However, frequent app evolution, such as UI redesignsand feature updates, often renders existing GUI tests obsolete, even when underlying functionality remainsunchanged. Automatically repairing such tests is critical for maintaining test suites and reducing substantialmanual effort. Despite the practical importance, there is still a lack of a systematic understanding of thecharacteristics of obsolete GUI tests and a publicly available benchmark to support their study. To fill thisgap, we construct a benchmark comprising 736 obsolete GUI tests collected from 36 …

Chemnetworks: New Capabilities For High-Throughput, Real-Time Chemical Graph Construction And Analysis, Daniel J. Pope, Jackson Elowitt, Bo Zhang, Manish Parashar, Aurora E. Clark

Michigan Tech Publications

A major revision of the ChemNetworks software (originally published in the Journal of Computational Chemistry, 2014, 35, 495–505) is presented. While the original ChemNetworks provided foundational graph construction capabilities for chemical systems, it was limited to simple distance and 3-body angular edge criteria, was not designed for high-performance computing environments or real-time operation alongside running simulations. This release addresses these limitations through three core contributions. First, a recursive Z-matrix-based search algorithm is introduced that enables chemically intuitive, arbitrarily descriptive three-dimensional structure searches, supporting geometric, energetic, and logical criteria. Second, the DataSpaces data staging framework is incorporated as an optional I/O …

Don’T Sweat Interaction Trees Proof-Guided Local Variable Lifting For Interaction Trees, Yiming Lin, Ian Kariniemi, Yao Li

Computer Science Faculty Publications and Presentations

Verifying existing software is hard: Programs are developed in languages not amenable to verification, involve complicated optimizations that obscure the underlying logic, and are gigantic in size. In this paper, we propose a way to ease this pain via a simplification framework that employs interaction trees as a language-agnostic interface. We show that local variable lifting, the technique underlying AutoCorres for the Simpl language, can be generalized to interaction trees via an implementation in Rocq. A key challenge with simplifying interaction trees is that they are highly dynamic structures and we would like our approach to work with mostly uninterpreted …

Disturbance-Learning Inertia Estimation Using Artificial Neural Networks For Power System Stability, Sospeter Igaanja Gabriel, Francis Mwasilu, Peter Makolo Dr.

Tanzania Journal of Engineering and Technology (TJET)

ABSTRACT

Power systems are progressively shifting towards low inertia as a result of incorporating significant amounts of intermittent and converter-based renewable energy sources, such as wind and solar power, into the current power grid network. This integration poses considerable problems to inertia and frequency control within the network due to a reduction in the proportion of synchronous generators. Furthermore, rapid frequency deviations occur due to the disparity between supply and demand during contingencies, complicating the maintenance of frequency stability within the power system. The disturbance-learning inertia estimation method for power system stability is presented. The simulation analysis is performed using …

Generative Artificial Intelligence, Academic Integrity And Authentic Assessment Within An Irish University, Louise Nagle, Brigid Crowley, Laura Rafferty, Susan Horgan, Colin O'Brien

Publications

Academics need both an overarching policy on Generative Artificial Intelligence (Gen AI) use in teaching and learning, yet agency in its application across various disciplines. Clarity on the use of the technology for both students and staff is therefore a challenge and characterised by uncertainty given how its application is still unfamiliar. This research examines the organisational context in which Gen AI is being embraced and was conducted by the digital teaching support functions within an Irish university. Students and staff were surveyed (n=1,746) on various aspects of digital use within their education and workplace, including Gen AI. …

Thermo-Entropic Analysis Of Unsteady Mhd Nanofluid Couette Flow: A Classical Spectral Approach With An Exploratory Quantum Linear-Solver Application, Serai Israel Mosala, Oluwole Daniel Makinde, Azwinndini Muronga

Mathematical Modelling and Numerical Simulation with Applications

This study presents a thermo-entropic analysis of unsteady MHD nanofluid Couette flow, combining a classical bivariate spectral quasilinearisation (BI-SQLM) and Crank--Nicolson solution with an exploratory application of quantum linear solvers. An incompressible, electrically conducting nanofluid flows between parallel plates under partial slip and convective heat exchange; the discretised linear systems are additionally solved via the Harrow--Hassidim--Lloyd (HHL) algorithm and the Variational Quantum Linear Solver (VQLS). Results are presented for Pure Water, Cu-Water, and Al₂O₃-Water across seven parameter variations. The Hartmann number dominates velocity suppression and entropy amplification, while velocity slip reduces upper-wall entropy generation more than …

Neural Network-Based Analysis Of Heroin Epidemic Models With Modified Fractional Operators, M. A. El-Shorbagy, Sedat Pak, Mati Ur Rahman, Hossam A. Nabwey

Mathematical Modelling and Numerical Simulation with Applications

Heroin and synthetic narcotic abuse have become a major global concern, posing challenges to individuals, families, and communities. Their widespread availability and low cost have intensified the crisis. This study investigates a heroin transmission model using the modified Atangana--Baleanu--Caputo (mABC) fractional operator, with emphasis on non-zero solutions. Series solutions are derived by combining the Laplace transform with the Adomian decomposition method to address nonlinear components. Qualitative analysis is conducted through fixed-point theory, while stability is assessed using the T-Picard method. Numerical simulations explore the effects of different fractional orders and transmission parameters on the system. The study incorporates a deep …

Jpnet: A Multi-Layered Fusion Deep Learning Architecture For The Detection And Classification Of Pests In Jute Crops, Mejbah Ahammad, Md. Ashraful Babu, Muhammad Sajjad Hossain, Md. Fayz-Al-Asad, Nadim Ahmed, Md. Khaled Hossain, Md. Mortuza Ahmmed, M. Mostafizur Rahman, Mufti Mahmud

Mathematical Modelling and Numerical Simulation with Applications

Detecting and classifying insect pests is a critical challenge in agricultural pest management, as infestations can reduce crop yield and quality. This study introduces JPNet, a convolutional neural network (CNN) architecture that uses multi-layer feature fusion to detect and classify insect pests affecting jute crops. The architecture integrates complementary feature representations extracted at different network depths, preserving fine-grained visual characteristics alongside high-level semantic information. JPNet is evaluated on the JutePest dataset, which comprises approximately 6,460 RGB images spanning 17 pest classes. Preprocessing and data augmentation—including resizing, normalization, rotation, shifting, zooming, and flipping—improve the consistency and diversity of the training data. …

A Neutrosophic Memory-Integrity Calculus For Contradiction-Preserving Persistent Ai Agents, Rana Muhammad Zulqarnain, Saalam Ali

Neutrosophic Systems with Applications

Persistent AI agents increasingly convert interaction histories into long-lived memory, making memory transformation not retrieval alone—a central reliability problem. NMIC (Neutrosophic Memory-Integrity Calculus) formalizes the integrity of write, merge, consolidation, revision, and retrieval operations over persistent memory. Each proposition is represented through an evidence ledger carrying independent truth, indeterminacy, and falsity degrees together with reliability, provenance, temporal validity, contextual applicability, and inter-evidence dependence. A dependence-normalized hazard aggregation preserves simultaneous support and opposition while making the resulting state invariant to exact evidence duplication. Pure consolidation is governed by five integrity conditions: no support invention, no opposition invention, no manufactured certainty, contradiction …

Decision Support System For The Selection Of Thumbprint Recognition Algorithms In Biometric Security Systems, Toqeer Jameel, Muhammad Riaz

Neutrosophic Systems with Applications

This study investigates fingerprint recognition in immigration operations, emphasizing the role of biometric verification in enhancing security, fairness, and operational efficiency in international mobility. To address the uncertainty, vagueness, and imprecision inherent in fingerprint identification, a novel decision-making framework is proposed by integrating interval-valued picture fuzzy (IVPF) information. Fairly aggregation operators are introduced to combine decision makers' evaluations, while extracted fingerprint features are modeled using positive, neutral, and negative membership degrees within the IVPF environment. Objective criterion weights are determined using the criteria importance through intercriteria correlation (CRITIC) method, and individual ranking is performed via the alternative ranking order method …

A Data-Driven Neutrosophic Multi-Criteria Intelligent System For Functional Disability Severity Assessment, Ehab Abdel Aziz Al-Beblawi, Mirna Samy, Abduallah Gamal

Neutrosophic Systems with Applications

Functional disability assessment is a multidimensional problem because individuals may experience different levels of difficulty across daily activities such as walking, standing, dressing, eating, grasping objects, and social participation. This paper proposes NIFDA, a data-driven neutrosophic multi-criteria intelligent system for functional disability severity assessment. The proposed framework represents each functional response through three components: confirmed limitation, indeterminacy, and preserved functional ability. This allows the model to handle valid responses, uncertain information, and missing or non-informative data without forcing them into a single crisp score. To reduce dependence on subjective expert weighting, NIFDA derives criterion weights objectively using a hybrid CRITIC–MEREC …

Neutrosophic Indeterminacy-Transport Kolmogorov-Arnold Networks For Structured Uncertainty, Hafiz Muhammd Bilal, Kiran Naz, Anjum Ijaz

Neutrosophic Systems with Applications

Kolmogorov-Arnold Networks (KANs) replace fixed node activations with learnable univariate edge functions, but standard KAN inference treats two equal-valued features identically even when one is accompanied by an explicit quality warning. NIT-KAN introduces a neutrosophic indeterminacy-transport mechanism for this setting. Each node carries an indeterminacy state in [0, 1]; a monotone gate g(I)=⁽1-I)^α attenuates uncertain evidence on the predictive path, while a sensitivity-weighted transport rule carries indeterminacy through the underlying KAN computation. A terminal audit maps signed evidence to truth-support, falsity-support, and conflict-augmented indeterminacy without interpreting these quantities as class probabilities. We …

Neutrokoopman: Channel-Preserving Koopman Spectral Analysis Of Nonlinear Dynamics With Truth, Indeterminacy, And Falsity Evidence, Ahmed Samy, Mohamed M. Abdelhafeez, K Venkatachalam, Mohamed Abouhawwash

Neutrosophic Systems with Applications

Modern dynamical systems increasingly operate with evidence that is not merely noisy but incomplete, contradictory, or only partially trustworthy. Conventional Koopman methods represent nonlinear dynamics through linear evolution of observables, while robust and adaptive variants address parameter and model uncertainty. They do not, however, preserve the semantic distinction between support, indeterminacy, and counter-support when those conditions are compressed into a single uncertainty variable. This paper develops NeutroKoopman, a channel-preserving Koopman framework in which the physical state is augmented by a single-valued neutrosophic evidence state ν_t = ( T_t,I_t,F_t ). Deterministic and Markovian formulations are …

Transforming Military Spectrum Management With Spectrack, Rachel Mccoy, Rafa Gould, Abby Fornadel

James Madison Undergraduate Research Journal (JMURJ)

The U.S. military faces operational and financial challenges due to inefficient electromagnetic spectrum
management. This poster and accompanying research statement introduce our minimum viable product, SpecTrack, which we created in response to a challenge presented by the U.S. Department of Defense's Joint Spectrum Agency. SpecTrack centralizes and visualizes spectrum requests to offer insights, streamline communication, and reduce costs. It integrates with current tools like Spectrum XXI and HUNSWDO while enhancing usability through a visual Common Operating Picture (COP). Our user-centered design process included stakeholder interviews and site visits to Germany. The result: a scalable platform that modernizes and simplifies military …

Enviromental Burden And Financial Performance Of Manufacturing Companies On Borsa Istanbul: An Exploratory Circular-Economy-Aligned Assessment Using The Aroman Method, Sibel Fettahoglu, Ejder Ayçin, Büşra Karslı Günay

Journal of Environmental Science and Sustainable Development

Türkiye's 2053 net-zero emissions target and the critical role of the manufacturing sector in this process necessitate an urgent examination of the financial impacts of circular economy (CE) practices. This study provides an exploratory analysis of the relationship between environmental burden and financial performance using 2023 data from 26 manufacturing companies in Borsa Istanbul. Given the difficulty of measuring holistic circularity at the company level, this study operationalizes the environmental dimension of circular economy performance using selected environmental burden indicators, including energy and water consumption, greenhouse gas emissions, and waste generation. The study uses the alternative ranking order method accounting …

Hands-On Ransomware: An Experiential Wannacry Case Study For Undergraduate Cybersecurity Education, Eli Creek Richmond, Thomas R. Devine

Military Cyber Affairs

Ransomware represents one of the most disruptive threats in the cyber landscape, yet hands-on malware analysis remains rare in undergraduate cybersecurity curricula. This paper presents the design, implementation, and evaluation of an experiential learning module centered on the WannaCry ransomware case study, deployed in a senior-level course at West Virginia University. Students performed static and dynamic analysis using industry-standard tools. Pre- and post-module assessments demonstrated measurable gains in self-reported competency across seven technical dimensions. The module's competencies align directly with DoD Cyber Workforce Framework Work Role 212, Cyber Defense Forensics Analyst, supporting education-to-workforce pipeline development.

From Framework To Toolchain: Implementing Zero Trust Architecture In Cloud-Native Environments For Dow Compliance, Shelby C. Snyder

Military Cyber Affairs

Federal agencies face a fiscal year 2027 target for enterprise-wide Zero Trust deployment, but NIST SP 800-207A defines logical components without identifying the Kubernetes technologies that implement them. This paper proposes a three-tier mapping of the Policy Engine, Policy Administrator, and Policy Enforcement Point to service mesh, microsegmentation, and perimeter tooling, stating the criteria by which each component is classified. It then applies a defined rubric to six Zero Trust vendors across component alignment, Kubernetes capability, federal authorization posture, and evidence quality, finding that no single vendor covers all three tiers. The mapping is a testable architectural proposition; a Stage …

Characterizing Advanced Persistent Threats With Cyber Attack Flow Metrics, Tyler Miller, Caleb Chang, Shouhuai Xu

Military Cyber Affairs

Cyber attack campaigns vary not only in scale but in structure, yet conventional characterizations often reduce them to a single dimension such as technique count or impact severity. In this paper we extend the concept of cyber attack flows by defining three new metrics, novelty, technique complexity and flow complexity. Then we characterize the attack flows of three advanced persistent threat campaigns using these metrics and draw insights regarding their capabilities. Our findings include that low novelty does not equate to low attack capabilities and that exploitation of an internet-facing appliance is a common initial attack vector.

Semantic Shields: Automating Critical Infrastructure Defense Via Nlp-Driven Ransomware Profiling, Henry Trowbridge, Ian Zalcberg, Ryan Schley, Carter Yagemann, Natasha Phan, Srikar Maduposu, Vimal Buck

Military Cyber Affairs

Ransomware poses a growing threat to critical infrastructure, where successful attacks can disrupt operational technology (OT) and industrial control systems (ICS) with significant public safety consequences. However, attributing ransomware incidents to specific threat actors remains challenging due to ransomware-as-a-service ecosystems, actor rebranding, and the obfuscation of traditional indicators of compromise. This paper presents Semantic Shields, an NLP-driven attribution framework that leverages BERT-generated semantic embeddings and DBSCAN clustering to profile ransomware actors through the linguistic characteristics of ransom notes. Using a dataset of 295 ransom notes from 189 distinct threat groups, the framework achieved an 87.2% true positive clustering rate and …

Closing The Interpretability Gap: Explainable Ml-Based Malware Detection For Defensive Cyberspace Operations, Tashi Stirewalt, Sean Hodgson, Puumaaya Tahiru, Assefaw Gebremedhin

Military Cyber Affairs

This paper presents an end-to-end, explainable malware triage pipeline designed for defense-oriented cyber operations. It combines high-performance static detection methods with analyst-centered interpretability. Utilizing the EMBER 2024 Windows PE subset, we train and evaluate four classifiers and select LightGBM as the production model based on its predictive performance, inference efficiency, and compatibility with exact tree-based attribution. The deployed system consists of four sequential components: PE feature extraction, malware probability scoring, dual explainability (using SHAP and LIME), and large language model (LLM) report generation, all integrated within a Flask web interface. On a temporal test set of 1,080,000 samples, LightGBM achieves …

On-Device Computing Systems For Embodied Ai: Current Research Status And Strategic Directions, Shaoshan Liu, Zhenhua Zhu, Yiming Gan, Yu Wang, Yuan Xie

Bulletin of Chinese Academy of Sciences (Chinese Version)

Embodied AI is emerging as a key paradigm empowering general-purpose autonomy, but it requires on-device computing systems that simultaneously support high-throughput “cognition–planning” tasks and millisecond-level real-time “perception–control” loops. Converging solutions now coalesce around three pillars: (1) dataflow- and chiplet-based architectures, (2) memory-centric heterogeneous dies, and (3) RISC-V customizable cores with open tool-chains. This study distills the latest technical progress, pinpoints the remaining core technical bottlenecks, and charts an actionable course for academia, industry, and policymakers. The study calls for unified benchmarking and standardization, open-source software–hardware ecosystems, memory-centric dataflow architectures, and efficient on-device deployment of embodied foundation models. Finally, it outlines …

Construction And Application Of Clinical Evidence Framework For Brain-Computer Interface, Wenxiu Qi, Cheng Zhou

Bulletin of Chinese Academy of Sciences (Chinese Version)

Brain-computer interface systems are emerging neurotechnologies that are gradually moving from laboratory research toward clinical application. However, their inherent features, including small sample sizes, heterogeneous technical pathways, and rapid product iteration, make it difficult to integrate safety and efficacy data across studies or to conduct meaningful cross-study comparisons. These challenges not only hinder the cumulative development of evidence in evidence-based medicine, but also complicate the assessment of clinical access and regulatory review. In addition, subjective evidence, such as patient experience, remains insufficiently captured in existing evaluation frameworks. It is therefore necessary to examine the structure of evidence for brain-computer interface …

A Calibrated And Conformal Deep Learning Framework For Trustworthy Antinuclear Antibody Pattern Recognition With Selective Referral To Experts, Hussein Ali Hussein Al Naffakh, Ahmed Dheyaa Radhi, Raghdah Maytham Hameed, Muntaha Abdullah Reishaan, Fouad A. Majeed, Rozaida Ghazali

Karbala International Journal of Modern Science

Reading antinuclear antibody patterns on human epithelial cells by indirect immunofluorescence is the reference screen for systemic autoimmune rheumatic diseases, but it is slow, subjective, and variable between observers. Deep learning reaches high accuracy on this task, yet most systems return a single prediction without stating how reliable it is, which is unsafe in a diagnostic workflow. This paper presents an intelligent decision support framework built around a single calibrated uncertainty signal. That signal is the control variable for four reliability modules: confidence calibration, conformal prediction, error detection, and selective referral. A feature space out of distribution detector serves as …

Resilient Ethical Governance By Design: Building Resilience For Future-Ready Smart Cities Against Emerging Technology Disruptions In Public Sector – A Case Study Of Dallas Smart City, Emmanuel Asamoah Asare

Doctoral Dissertations and Projects

This dissertation examines how Dallas’s smart city strategic policies foster resilience against disruptions associated with emerging technologies, particularly artificial intelligence and Internet of Things systems. Using a convergent mixed-methods comparative case study, Dallas serves as the primary case, Austin serves as a U.S. municipal comparator, and Barcelona serves as a qualitative benchmark for ethical and trust-centered smart city governance. The study integrates document analysis, broadband and digital equity indicators, stakeholder engagement evidence, and exploratory quantitative comparisons to assess how governance adaptability, preparedness, functionality, equity, and stakeholder trust shape resilience outcomes.

The findings provide partial support for the study’s hypotheses. Dallas …

Application Of Machine Learning To Discover Dynamical Structures In 4d Poincaré Maps In The Circular Restricted Three-Body Problem, Kevin M. Trigg, Daniel J. Broyles, Robert A. Bettinger, Tyler J. Kapolka

Faculty Publications

The spatial Circular Restricted Three-Body Problem (CR3BP) produces complex orbital dynamics that are difficult to classify at scale using traditional, manual Poincaré map analysis. A Poincaré map simplifies continuous orbital motion by recording the points where a trajectory intersects a chosen surface in phase space, converting a continuous path into a discrete set of crossings that reveal underlying topological structure. These crossings make it easier to characterize trajectory behavior, but interpreting them visually becomes impractical for large datasets and as Poincaré maps evolve from two into four dimensions. To address this challenge, an unsupervised clustering pipeline for discovering dynamical structures …

Portrait: Holistic Data Visualization Using Neural Networks, Chayan Maitra

Doctoral Theses

With the exponential growth of complex data across domains, effective visualization has become increasingly crucial for understanding relationships hidden within high-dimensional spaces. However, existing visualization techniques often struggle to effectively capture and represent such high-dimensional data. Motivated by this challenge, we have developed NeuroDAVIS, a neural network model designed to visualize high-dimensional data by extracting meaningful latent representations through deep feature extraction. While NeuroDAVIS has successfully addressed the visualization aspect, we have soon recognized the necessity of identifying the most relevant features that contribute to the visualization and downstream analysis. To address this issue, we have extended our framework and …

Challenges, Trends, And The Role Of Lstm In Ai-Based Predictive Maintenance Of Electrolyzers For Solar Hydrogen Systems: A Review, Yani Koerniawan Kuatno, Muhamad Zahim Sujod

Turkish Journal of Electrical Engineering and Computer Sciences

The transition toward low-carbon energy systems has increased interest in hydrogen as a clean energy carrier, with solar-driven water electrolysis emerging as a promising technology due to its high efficiency and compatibility with renewable energy sources. However, dynamic operating conditions and intermittent renewable input accelerate electrolyzer degradation, reducing reliability and system lifespan. Predictive maintenance (PdM), supported by artificial intelligence (AI), offers a data-driven approach to anticipate failures and improve operational durability. This review systematically investigates AI-based PdM approaches for electrolyzers, with an emphasis on long short-term memory (LSTM) networks and Internet of things (IoT) integration. Following PRISMA 2020 guidelines, 35 …