Digital Commons Network^™

Analysis Of Extended Producer Responsibility In E-Waste Management: Policy Drivers And Challenges In Singapore, Aldy Gunawan, Aidan Marc Wong, Tasaporn Visawameteekul, Minh Phuong Huynh, Linh Chi Tran

Research Collection School Of Computing and Information Systems

This paper examines the role of the Extended Producer Responsibility (EPR) scheme in electronic waste (e-waste) management in Singapore. It investigates the policy drivers and challenges of e-waste management, using data from an online survey to explore the attitudes and behaviors of young consumers, with a particular focus on youth. We employ the Theory of Reasoned Action (TRA) and the Theory of Planned Behavior (TPB) frameworks to develop a model that examines the relationships among attitudes, perceived norms, awareness, and perceived convenience in relation to EPR awareness and perception. The findings highlight the need for customized policies tailored to different …

Generalized Logit Adjustment: Improved Fine-Tuning By Mitigating Label Bias In Zero-Shot Vision Models, Beier Zhu, Qianru Sun, Xun Yang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that such prior work has overlooked the inherent biases in foundation models. Due to the highly imbalanced Web-scale training set, foundation models are inevitably skewed toward frequent semantics, and thus the subsequent fine-tuning or ensembling is still biased. In this study, we systematically examine the biases in foundation models and demonstrate the efficacy of our proposed Generalized …

Learning 1-Bit Lidar-Based Localization With Auxiliary Objective, Kaijie Yin, Zhiyuan Zhang, Tian Gao, Wentao Zhu, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

6-DoF LiDAR-based localization is a fundamental capability for autonomous systems operating in large-scale outdoor environments. Many deep-learning-based localization methods have achieved promising performance so far. However, as one of the always-on modules competing for limited on-board computational resources, the localization module is expected to consume only a small portion of the overall compute budget. Most existing learning-based methods are still too heavy for this purpose. In contrast, binary neural networks (BNNs) offer an appealing solution, but the 1-bit compression causes severe information loss and performance drop. In this paper, we address this challenge by proposing Binarized LiDAR-based Localization (BiLoc), the …

Smart: When Is It Actually Worth Expanding A Speculative Tree?, Lifu Wang, Pan Zhou

Research Collection School Of Computing and Information Systems

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single targetmodel forward pass. However, existing methods prioritize maximizing token-level likelihood or the number of accepted tokens while ignoring a critical “efficiency paradox”: the computational overhead of drafting and verifying big trees can grow super-linearly, particularly at scale. This often leads to negative wall-clock speedup when batch sizes increase or hardware saturation limits are reached. To address this, we propose SMART, a System-aware Marginal Analysis framework for Runtime Tree construction. SMART reformulates tree expansion as a hardware-aware optimization problem that directly maximizes end-toend speedup. …

Autoqresearch: Llm-Guided Closed-Loop Policy Search For Adaptive Variational Quantum Optimization, Monit Sharma, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Configuring variational quantum algorithms for combinatorial optimization remains a difficult, expert-driven process requiring coordinated choices over solver family, ansatz, objective, and optimizer. We present AutoQResearch, an LLM-guided closed-loop experimentation framework that casts this task as sequential policy search over a curated design space. Instead of a single static configuration, the framework searches for adaptive solver-control policies that condition future decisions on diagnostics such as feasibility, optimality gap, and convergence stagnation.The system operates through a structured workflow: an LLM agent edits a small policy surface under a fixed evaluation harness, candidate policies are screened using cheap scout evaluations, and only the …

Between Digital Transformation And Regulatory Vacuum: Cybersecurity Of Public Services In Mozambique, Faztudo Languisse Eng.

Journal of Cybersecurity Education, Research and Practice

The rapid expansion of digital public services in Mozambique—including e-government platforms, digital health systems, and electronic tax administration—has outpaced the development of a coherent legal framework for cybersecurity. While Law No. 3/2017 (Electronic Transactions Law) of 9 January 2017 introduced foundational data-protection principles, Mozambique long lacked a dedicated cybersecurity regulatory authority, mandatory security standards, and formal incident-notification mechanisms. This regulatory vacuum exposed critical public services to escalating cyber risks as digital transformation was actively promoted as a development priority. This article examines the legal and institutional gaps in Mozambique's cybersecurity governance framework prior to the 2026 Cybersecurity and Cybercrime Laws, …

Exposing And Addressing Machine Learning Brittleness Through Constraint Solving, Muyeed Ahmed

Dissertations

Machine Learning (ML) implementations are fundamentally brittle: nondeterministic, inconsistent, and prone to overfitting; however, constraint solving can be used to systematically expose, quantify, and address this brittleness.

This dissertation first establishes that widely-used implementations of popular ML algorithms are nondeterministic (producing different outputs on the same input, across different runs) and inconsistent (different implementations of the same algorithm producing different outputs on the same input). This is more prevalent in Unsupervised Learning (UL) implementations where, due to the lack of a ground truth, subtle execution errors can go unnoticed and are difficult to verify. Nondeterminism and inconsistency also introduce security …

Clinic-In-A-Box: A Portable, Software-Defined Cyber Range For Realistic, Scenario-Based Cybersecurity Training, Ethan Chumley, Aaron Nair, Royce Yaezenko, Joshua Payne, Veronika Kyles, Paul Wagner, Robert J. Honomichl, Ryan Straight, Shengjie Xu

Journal of Cybersecurity Education, Research and Practice

Realistic, hands-on cybersecurity training has traditionally depended on fixed infrastructure such as dedicated lab hardware, cloud subscriptions, or permanent network connectivity, limiting where and how often it can be delivered. This paper presents the design and implementation of a portable, scenario-based cybersecurity training platform housed in a single travel case and built from commodity hardware, type-1 hypervisor virtualization, containerized service orchestration, and software-defined networking. The platform clones, isolates, and resets complete lab environments on demand, allowing the same physical system to support repeated classroom, workshop, or field deployments with minimal manual reconfiguration. Training scenarios are grounded in generated organizational profiles …

A Statistical Mechanics Approach To Reinforcement Learning, Jacob Adamczyk

Graduate Doctoral Dissertations

Reinforcement learning (RL), the study of optimal decision-making over long timescales in stochastic systems, has recently seen remarkable advances due in large part to the efforts of the deep learning community. RL has witnessed great success in solving problems in video games, robotics, biological control, and language modeling. However, a unified statistical mechanics framework to understand and develop the corresponding algorithms is lacking. To address this issue, we begin by showing that the reinforcement learning problem can be formulated and solved using the tools of statistical mechanics. Drawing on physical principles of free energy minimization and invariance, we address important …

Guardians Of The Record: A Two-Tiered Streaming Cascade With Kafka, Flink, And A Real Llm, Ilan Goodman

Generative AI Teaching Activities

Students build a streaming vandalism detector for live Wikipedia edits in which a fast rule-based tier decides which few of ~1,500 edits per minute are worth escalating to a slow, rate-limited real LLM (Gemini) — confronting the cost, latency, and failure modes of putting AI inside a production data pipeline.

Guardians Of The Record (Cs2 Edition): Heaps, Queues, And A Scarce Oracle, Ilan Goodman

Generative AI Teaching Activities

Students defend Wikipedia from vandals with data structures instead of infrastructure: a sliding-window edit-velocity tracker (hash map of queues), a hand-built binary min-heap, and a budget-bounded top-K selection decide which few suspicious edits earn a question to an expensive, rate-limited Oracle — a stand-in for a real LLM.

Analysis Of The Throttle Settings Under Uncertain Information, Latafat Gardashova, Nihad Afandi

Chemical Technology, Control and Management

Although classical fuzzy logic controllers are capable of modelling non-linear control systems, they fail to consider the reliability of linguistic information, sensor measurements, and expert knowledge. In this paper, an intelligent controller based on the use of Z-numbers is developed for steam-turbine throttle control. Linguistic information and its confidence degree are considered simultaneously in such a controller. The temperature and pressure values are taken as input variables, while the throttle rotation is selected as the controller output variable. At first, the Z-number representation system is constructed to include the credibility of linguistic measurements and control rules. Then, a Mamdani Type-1 …

Nonlinear System Identification Based On Fuzzy Radial Basis Neural Network With Multi-Connected Weight Connections, Kabul Khudaybergenov

Chemical Technology, Control and Management

This paper builds on our earlier radial basis function network with multiple connections (RBFMC) by placing it within a fuzzy inference framework for nonlinear system identification. The idea is inspired by the diversity of neurotransmitters found in biological neurons: instead of a single hidden-to-output weight, RBFMC gives each hidden unit a multi-dimensional connection whose components act as independent filters. Once fuzzy logic is added, each hidden neuron becomes a fuzzy rule, and its antecedent is built from several Gaussian membership functions, one per connection. The resulting Fuzzy RBFMC produces an interpretable, multi-filter description of local regions of the input space …

Enhanced Osseointegration Of Functionally Graded Co˗Cr˗Mo˗Ti/Ha Implants: In Vitro And In Vivo Study In A Rabbit Model, Afrah M. Al Hussainey, Randa Kamel Hussain, Aseel Mustafa Abdul Majeed

Karbala International Journal of Modern Science

    The present investigation aims to evaluate the effects of acid and laser surface treatments on the surface characteristics, biocompatibility, and osseointegration of functionally graded implants fabricated from a Co–Cr–Mo–Ti/HA alloy. The implant surfaces were modified using either an Nd: YAG laser or hydrochloric acid (HCl), while untreated implants served as controls. Atomic force microscopy (AFM) showed that the acid-treated surface exhibited the highest mean surface roughness (Sa) of 58.10 ± 0.24 nm compared to the laser-treated surface (42.64 ± 0.83 nm) and the untreated surface (37.73 ± 0.89 nm). The MTT assay also demonstrated a favourable cellular response on the …

Trustworthy Ai At The Air Quality-Health Nexus: A Systematic Review Of Federated Learning, Distributed Ledger Technologies, And Explainable Ai, Nadia Dahmani, Imen Ben Salem, Syed M Salman Bukhari

All Works

Abstract Air quality (AQ) related health risks are increasing globally, creating urgent demand for artificial intelligence (AI) systems that are privacy-preserving, transparent, and auditable. Although Federated Learning (FL), Distributed Ledger Technologies (DLT), and Explainable AI (XAI) are widely recognized as core components of trustworthy AI, existing research remains divided across technical and application domains. This study conducts a computational, multistage systematic review (SR) of scholarly literature records published between 2011 and 2025 using the Semantic Scholar Graph API with intersection and union search strategies. A total of 13 458 records were retrieved and refined into a research-grade corpus of 7 …

Ai, The Liberal Arts, And Indigenous Languages: Forming Code Into Language, Christina Graebner

Summer Research Showcase

During the Summer, Spanish Professor Adam Coon and I worked on creating an annotated biography on AI and Indigenous languages for the Digital Well at the UMN Morris Library. Through this project, we have dived into conversations and research focusing on using AI as a translator. In recent years, the conversation around AI has created a surge of studies and research around the relationship between Indigenous languages and artificial intelligence. AI will only continue to expand, and it creates new ways to open communication but creates new ethical guidelines needed to be followed. Our project gathers research articles, podcasts, and …

Self Efficacy And Instructional Support Predict Cyber Deception Acceptance In Ics And Ot Cybersecurity, Daniel Ward

Journal of Cybersecurity Education, Research and Practice

Cyber deception can produce high-confidence evidence of unauthorized activity in industrial control systems (ICS) and operational technology (OT), but practitioners must consider the technology useful, safe, understandable, and supported before they will use it. This study reports a secondary quantitative analysis of a deidentified survey of United States-based ICS and OT professionals to determine whether psychological and instructional factors predict adoption readiness and effective utilization beyond education, experience, and sector. Hierarchical ordinary least squares regression with HC3 robust standard errors was conducted on 262 complete cases. The demographics-only model was not significant and explained 2.8 percent of outcome variance. Adding …

Opengrcrmf: A Vendor-Neutral Framework For Teaching And Modeling Rmf Automation, Continuous Authorization, And Zero Trust Governance, Anand Janjal

Journal of Cybersecurity Education, Research and Practice

Abstract—Federal and regulated organizations continue to rely on document-centric Authorization to Operate (ATO) processes even as the NIST Risk Management Framework (RMF), continuous monitoring guidance, Zero Trust Architecture (ZTA), and continuous authorization initiatives require more continuous, evidence-driven risk management [1]-[3], [13], [15]. Manual System Security Plan (SSP) updates, spreadsheet-based Plan of Action and Milestones (POA&M) tracking, and disconnected assessment evidence create governance latency: the delay between operational security events and authorization-ready governance response. This paper presents OpenGRCRMF, a proposed open, vendor-neutral reference framework that models RMF lifecycle activities as workflow states, treats authorization artifacts as structured governance objects, and …

Artificial Intelligence And Social Equities: Navigating The Intersectionalities In A Digital Age (Editorial), Daisuke Akiba, Julie Albright

Publications and Research

This editorial article introduces and synthesizes the Special Issue, “Artificial intelligence and social equities: navigating the intersectionalities in a digital age,” which examines how AI systems intersect with race, ethnicity, and interconnected identity dimensions across global contexts. The eight contributions span healthcare, digital media, higher education, organizational communication, and speculative futures, addressing anti-racist psychiatric algorithms, AI-generated visual disinformation, epistemic injustice between the Global North and South, algorithmically mediated rural–urban divides, culturally untranslated technology transfer, accessibility auditing across the AI lifecycle, and the tension between mechanical objectivity and empathic understanding. Read together, they show that AI is neither inherently …

A Vision For The Future Of Academic Publishing In Sports Analytics, Ryan Elmore, B. Baumer, Brian Macdonald, Gregory J. Matthews, Michael E. Schuckers

Statistical and Data Sciences: Faculty Publications

This article introduces the Journal of Statistics and Data Science in Sports (JSDSS), a Diamond Open Access, peer-reviewed journal. The journal is founded on three core principles. First, our commitment to open access is absolute. Second, reproducibility is critical and fundamental to the journal. Third, we believe sport is a rich and underutilized laboratory for statistical and data science innovation. The aim of the Journal of Statistics and Data Science in Sports is to provide an outlet for original, rigorous, practical, state-of-the-art, reproducible, and peer-reviewed analysis of sports data as well as the data science tools (software, applications, data, etc.) …

Personal Authenticity For Engagement And Transfer In Introductory Cybersecurity Education, Daniel T. Hickey, Ronald J. Kantor

Journal of Cybersecurity Education, Research and Practice

Abstract—This conceptual/theoretical paper explores how personal authenticity might promote generative learning in introductory cybersecurity courses. Generative learning transfers confidently to future educational, professional, personal, and testing situations. This cycle of design-based research addresses the concern that more typical professionally authentic contexts (e.g., hospitals, banks, etc.) may be alien and overwhelming to many students, particularly those in introductory courses and/or from non-professional families and communities. If so, this leads to “inert” knowledge that does not transfer. Personal authenticity is rooted in expansive framing, a modern theory of learning transfer. We reframe expansive framing as personal authenticity to make it …

Nasa’S Ecostress Satellite Reveals Widespread Midday Depression In Ecosystem Evapotranspiration, Jingyi Bu, Jingfeng Xiao, Joshua B. Fisher, Yiqi Luo

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Plants often exhibit a midday depression in water use (i.e., transpiration), reflecting a constraint on their ability to sustain maximum water transport, which may occur at the cost of reduced photosynthesis. Eddy covariance observations and geostationary satellites cannot quantify this widespread phenomenon globally while resolving fine-scale spatial variability. Using evapotranspiration measurements from the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) and machine learning, we quantify the global distribution of midday depression in evapotranspiration. Midday depression primarily occurs during peak-growing seasons in temperate zones and dry periods in the tropics, with a morning shift of the peak evapotranspiration time …

Adaptive Rational Approximation In Dynamic Economic Models: A Novel Application Of The Aaa Algorithm To Economic Growth, Adaye Sosthene Yvan N'Guettia

Mathematics, Statistics, and Computer Science Honors Projects

I study adaptive rational approximation for fixed points that arise in infinite-horizon dynamic programming. I integrate the Adaptive Antoulas–Anderson (AAA) algorithm into Bellman- and Euler-based fixed-point solvers by recomputing a barycentric rational interpolant at each update. In addition to standard AAA, which selects support points from interpolation residuals, I study a residual-weighted variant in which Bellman,Euler, or KKT diagnostics act as secondary weights on the greedy pivot rule. This alignment of approximation adaptivity with the underlying equilibrium conditions can concentrate degrees of freedom in regions of steep curvature, sharp transitions in localbehavior, and other localized features that typically degrade polynomial …

An Analysis Of The Effects And Implementations Of The Early Literacy Grant In Arizona, Alicia Severiano Perez

Mathematics, Statistics, and Computer Science Honors Projects

Over the years, states have implemented Science of Reading (SoR) frameworks to address low literacy levels. The Early Literacy Grant (ELG) in Arizona funds and supports such frameworks for schools serving low-income students. This paper is the first to explore the grant through interrupted time series modeling to evaluate effectiveness and text analysis to understand its implementation. We do not find clear evidence of positive effects caused by the grant, other than some cases, such as Yuma County. Schools typically allocate funds toward salaries and hiring instructors. These findings raise questions about whether its allocations should be closely monitored.

Level Sets For Lehmer Codes Of Pattern Avoiding Permutations, Avery Sinclair

Mathematics, Statistics, and Computer Science Honors Projects

We study the poset structures for two families of pattern avoiding permutations. An n-permutation is a list of the numbers [n]={1,2,...,n}. A permutation is 321-avoiding when it does not contain a decreasing subsequence of length 3. A poset (partially ordered set) is a set such that some elements can be compared with one another. Using Lehmer codes, we define a poset for 321-avoiding permutations. We then fully describe the six lowest levels of this poset. We then consider the analogous poset for 123-avoiding permutations (which don't contain an increasing subsequence of length 3) and fully describe the three lowest levels.

Machine Learning For Functional Outcome Prediction After Vestibular Schwannoma Surgery: A Systematic Review And Diagnostic Test Accuracy Meta-Analysis, Shiva Nischal, Shaan Patel, Musa China, Kush Kale, Yi Hein Chai, Santosh Guru, William Muirhead, Patrick Grover

Department of Neurosurgery Faculty Papers

PURPOSE: Machine learning (ML) models have been increasingly applied to predict postoperative facial nerve dysfunction and hearing preservation after vestibular schwannoma (VS) surgery. However, reported performance varies substantially, and the overall diagnostic accuracy and clinical reliability of these models remain uncertain. We conducted a systematic review and diagnostic test accuracy meta-analysis to characterise the current state and methodological readiness of ML-based prediction of these outcomes.

METHODS: PubMed, Embase, and CENTRAL were searched from inception to February 2026. Studies evaluating ML-based prediction of facial nerve function or hearing preservation following VS surgery were included. Diagnostic performance metrics were pooled using random-effects …

Interpretable Multimodal Learning For Integrating Neuroimaging And Genetic Data In Alzheimer’S Disease, Kun Zhao, Siyuan Dai, Yingying Zhang, Guodong Liu, Pengfei Gu, Chenghua Lin, Paul M. Thompson, Alex D. Leow, Heng Huang, Haoteng Tang

Computer Science Faculty Publications

Introduction: Early detection of Alzheimer's disease (AD) requires models that combine brain structure changes with genetic risk, but existing methods struggle to align these different data types.

Methods: We present R-GenIMA, an interpretable multimodal large language model that pairs a region-of-interest vision transformer with genetic prompting to jointly analyze structural MRI and single nucleotide polymorphisms (SNPs). Each brain region becomes a visual token and SNP profiles are encoded as structured text, letting the model link regional atrophy to genetic factors through cross-modal attention. Tested on the ADNI cohort, R-GenIMA performs well in classifying four groups: normal cognition, subjective memory concerns, …

Physical Design Automation For Next Generation Ics: Graph And Machine Learning Based Approaches, Dr. Kritanta Saha

Doctoral Theses

Integrated Circuit (IC) technology has progressed significantly over the last six decades, culminating in billions of transistors on a chip. The widely used 193 nm immersion lithography process exceeds modern feature sizes, leading to layout pattern distortions and electrical violations. Mitigation techniques such as Multiple Patterning and Optical Proximity Correction become ineffective below 45 nm, prompting the development of several Next-Generation Lithography (NGL) methods such as Extreme Ultraviolet Lithography (EUVL), Multiple Electron Beam Lithography (MEBL). MEBL employs thousands to millions of e-beams in parallel to overcome throughput limitations. A 2D layout is partitioned into vertical stripes by stitch-lines (SLs), each …

Energy Security Strategy Empowered By Artificial Intelligence, Qiang Ji, Jiaofeng Pan, Yu Song

Bulletin of Chinese Academy of Sciences (Chinese Version)

Against the backdrop of unprecedented changes in a century, geopolitical restructuring has led to the fragmentation of energy game camps, climate change has impacted the resilience of energy infrastructure, and energy transformation has promoted the multidimensional and coordinated expansion of security connotations. Artificial intelligence, with its core advantages such as optimizing geopolitical risk prevention and control, enhancing infrastructure protection, improving energy system efficiency, and accelerating the integration of renewable energy, has promoted the shift of energy security strategy from experience driven to data-driven intelligence, achieving comprehensive risk identification, dynamic evaluation, collaborative response, and full chain monitoring, significantly improving the efficiency, …

Large Models Empowering Cybersecurity: Opportunities And Challenges, Zhuofeng He, Dongbin Hu, Yige Yuan

Bulletin of Chinese Academy of Sciences (Chinese Version)

Cybersecurity serves as a critical pillar for national security and social stability. Large models in cybersecurity are emerging as key enablers for the intelligent transformation of cyber offense and defense systems. As one of the most advanced core technologies in artificial intelligence, large models are introducing new research directions and application paradigms in the cybersecurity domain. This study systematically reviews the current landscape of cybersecurity-oriented large model applications and products, and explores their deployment scenarios in practice. It further analyzes the development trends in model capabilities, industry ecosystems, and trustworthiness, while identifying major practical challenges such as data privacy protection, …