Digital Commons Network^™

Large Language Model-Assisted Research Question Development In Public Health: A Case Study In The Special Supplemental Nutrition Program For Women, Infants, And Children (Wic), Qi Zhang, Bidusha Neupane, Priyanka Patel, Futun N. Alkhalifah, Yi He, Leslie Hodges

Health Behavior, Policy & Management Faculty Publications

Objective:

To assess the feasibility of using large language models (LLMs) to develop research questions about changes to the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) food packages.

Design:

We conducted a controlled experiment using ChatGPT-4 and its plugin, MixerBox Scholarly, to generate research questions based on a section of the USDA summary of the final public comments on the WIC revision. Five questions weekly for three weeks were generated using LLMs under two conditions: fed with or without relevant literature. The experiment generated 90 questions, which were evaluated using the FINER criteria (Feasibility, Innovation, Novelty, Ethics, …

Missionary Body Politics: Physical Education In West China, 1905-1950, Cory Willmott

Asia Pacific Perspectives

Republican Era China saw a radical transformation in Chinese physical culture as it aimed to compete in the global geopolitics of nation-states. Employing an historical ethnographic approach, this paper outlines how the unique conditions of Sichuanese warlordism and secret societies affected missionary relations with the Guomindang (GMD) as they implemented increasingly militarized physical education programs. Before the 1928 GMD consolidation of power, missionaries and GMD educators aligned with the YM/ WCA in physical education programs. After the GMD moved their headquarters to Chongqing in 1938, relations soured between the GMD and the Sichuan missionaries. Although the latter had been the …

A Critical Perspective On The Society Of Environmental Toxicology And Chemistry's Adherence To Founding Principles— Opportunities For The Future, Barnett A. Rattner, Annegaaike Leopold, Carys L. Mitchelmore, Glenn W. Suter, Mark S. Johnson, Adriana C. Bejarano, Lawrence A. Kapustka, Niranjana Krishnan, Derek C. G. Muir, Beatrice O. Opeolu, Martha Georgina Orozco-Medina, April Reed, Bruce W. Vigon, Adam R. Wronski

Epidemiology, Biostatistics, & Environmental Health Faculty Publications

The Society of Environmental Toxicology and Chemistry (SETAC) is a global organization whose mission is the advancement of environmental science and management through collaboration, leadership, communication and education. On SETAC's 45th anniversary, the following question was raised: Are the 1979 founding principles of SETAC, multidisciplinary approaches to solving environmental problems, multisector engagement and scientific objectivity, still useful, adequate and effective in fulfilling its mission? In a special session held at the 45th Annual Meeting in Fort Worth, Texas, United States, a critical evaluation of the founding principles was initiated by reviewing SETAC's history and ongoing activities, and recommendations were made …

The Crucial Role Of Machine Learning Models In Predicting Current Childhood Asthma: Model Comparison, Calibration, And Shap-Based Interpretation, Aditya Chakraborty, A. K.M. Raquibul Bashar

Epidemiology, Biostatistics, & Environmental Health Faculty Publications

Background: Asthma is one of the most prominent chronic diseases in children and one of the most challenging ailments to diagnose in infants and preschoolers in the United States. Predictive models can be instrumental in improving early diagnosis, personalized treatment strategies, and disease progression. By utilizing nationalized data, this study focuses on building and comparing high-performing analytical predictive models based on the relevant risk factors and identifying the most influential predictors.

Methods: We analyzed cross-sectional BRFSS Asthma Call-Back Survey data (2011-2020; N = 9,813) and randomly split participants into training and testing sets. An XGBoost model (hyperparameters tuned via grid …

Imperfections And Scars: The Aesthetics Of Curated Decay In Urban Conservation: The Aesthetics Of Curated Decay In Urban Conservation, Ioana Moldovan, Connell Vaughan, Michael O’Hara, Silivan Moldovan, Ioana Cecălășan

Research Outputs: 2025-Present

This paper explores the value of imperfections and curated decay in the conservation of architecture and public art as vehicles of cultural memory. While conventional heritage practice treats physical degradation as a threat, newer conservation ethics argue for embracing material impermanence within an aesthetics of care. We examine how acknowledging patina, weathering, and even structural decline can become an act of care, maintaining the “spirit” and authenticity of a place. The theoretical framework integrated the aesthetics of imperfection, including concepts like the Japanese wabi-sabi, which finds beauty in the incomplete and impermanent, critical heritage theory (which questions whose memories and …

Staphylococcus Aureus Strain Heterogeneity Modulates Virulence Traits Associated To Dual-Species Biofilms With Candida Albicans, Laure Nicolas Annick Ries, Beata Adrienn Brezniczky, Binduja Srelatha Pradeep, Esther Olabamiji, Lee Hutt, Glenn M. Harper, Alexander Strachan, Gyorgy Fejer

School of Biomedical Sciences

Staphylococcus aureus is a commensal Gram-positive bacterium and opportunistic pathogen that exhibits substantial variation in antimicrobial resistance and virulence traits. S. aureus is frequently co-isolated with the fungus Candida albicans, and together they represent the most common microorganisms recovered from biofilm-associated infections originating from both biotic and abiotic surfaces. Despite this clinical relevance, the impact of bacterial intra-species variation on interkingdom interactions remains poorly understood. This study therefore investigated how S. aureus strain heterogeneity influences C. albicans within dual-species biofilms. The majority of the 60 S. aureus strains tested suppressed fungal growth in a contact-dependent manner across different nutrient conditions …

Fleet: A Federated Learning Emulation And Evaluation Testbed For Holistic Research, Osama Abu Hamdan, Hao Che, Engin Arslan, Md Arifuzzaman

Computer Science Faculty Research & Creative Works

Federated Learning (FL) presents a robust paradigm for privacy-preserving, decentralized machine learning. However, a significant gap persists between the theoretical design of FL algorithms and their practical performance, largely because existing evaluation tools often fail to model realistic operational conditions. Many testbeds oversimplify the critical dynamics among algorithmic efficiency, client-level heterogeneity, and continuously evolving network infrastructure. To address this challenge, we introduce the Federated Learning Emulation and Evaluation Testbed (FLEET). This comprehensive platform provides a scalable and configurable environment by integrating a versatile, framework-agnostic learning component with a high-fidelity network emulator. FLEET supports diverse machine learning frameworks, customizable real-world network …

Dcmm-Transformer: Degree-Corrected Mixed-Membership Attention For Medical Imaging, Huimin Cheng, Xiaowei Yu, Shushan Wu, Luyang Fang, Chao Cao, Jing Zhang, Tianming Liu, Dajiang Zhu, Wenxuan Zhong, Ping Ma

Computer Science Faculty Research & Creative Works

Medical images exhibit latent anatomical groupings, such as organs, tissues, and pathological regions, that standard Vision Transformers (ViTs) fail to exploit. While recent work like SBM-Transformer attempts to incorporate such structures through stochastic binary masking, they suffer from non-differentiability, training instability, and the inability to model complex community structure. We present DCMM-Transformer, a novel ViT architecture for medical image analysis that incorporates a Degree-Corrected Mixed-Membership (DCMM) model as an additive bias in self-attention. Unlike prior approaches that rely on multiplicative masking and binary sampling, our method introduces community structure and degree heterogeneity in a fully differentiable and interpretable manner. Comprehensive …

Explaining The Unseen: Multimodal Vision-Language Reasoning For Situational Awareness In Underground Mining Disasters, Mizanur Rahman Jewel, Mohamed Elmahallawy, Sanjay Kumar Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

Underground mining disasters produce pervasive darkness, dust, and collapses that obscure vision and make situational awareness difficult for humans and conventional systems. To address this, we propose MDSE, Multimodal Disaster Situation Explainer, a novel vision-language framework that automatically generates detailed textual explanations of post-disaster underground scenes. MDSE has three-fold innovations: (i) Context-Aware Cross-Attention for robust alignment of visual and textual features even under severe degradation; (ii) Segmentation-aware dual pathway visual encoding that fuses global and region-specific embeddings; and (iii) Resource-Efficient Transformer-Based Language Model for expressive caption generation with minimal compute cost. To support this task, we present the Underground Mine …

Surgical Treatment Of Osteoradionecrosis Of The Jaw Following Radiotherapy For Oropharyngeal Cancer: A Retrospective Clinical Analysis In A Single-Center, Yu Nakai, Ken-Ichiro Sakata, Kazuhito Yoshikawa, Taku Maeda, Tougo Tanabe, Masayuki Shinohara, Kenji Imamachi, Hiroshi Hikasa, Jun Sato, Ikuya Miyamoto

Journal of Dental Sciences

Background/purpose: Osteoradionecrosis of the jaw (ORNJ) is an intractable disease that develops within the radiation field in patients with head and neck cancer. This study aimed to investigate differences in healing rates among surgical treatments for mandibular ORN that developed after radiotherapy for oropharyngeal cancer.

Materials and methods: We retrospectively evaluated 318 patients who underwent radiotherapy or chemoradiotherapy for oropharyngeal cancer at our institution to determine the incidence of ORNJ. Furthermore, 16 patients (15 males and 1 female) with a mean age of 63.3 years were included in the surgical analysis. Healing was defined as the absence of …

N-Acetylcysteine Restores Osteogenesis In Human Periodontal Ligament Stem Cells By Attenuating Hif-1Α-Driven Oxidative Stress And Glycolytic Reprogramming, Xiaochi Chang, Yanghao Zhao, Yang Wang, Chang Shu, Yi Feng, Yichong Sun, Guangxun Zhu, Jianxia Hou

Journal of Dental Sciences

Background/purpose: Periodontitis-associated hypoxia signaling and oxidative stress severely impair the regenerative capacity of human periodontal ligament stem cells (hPDLSCs). This study investigated whether antioxidant intervention rescues hPDLSC osteogenesis under CoCl₂-induced HIF-1α stabilization by modulating PI3K/Akt/HIF-1α/HO-1 signaling and glycolytic reprogramming.

Materials and methods: Primary hPDLSCs isolated from healthy premolars were characterized by flow cytometry and multilineage differentiation. To simulate periodontitis-associated stress, a CoCl₂-induced HIF-1α-stabilizing condition was established. Cells were treated with the antioxidant N-acetylcysteine (NAC), the glycolysis inhibitor 2-deoxy-D-glucose (2-DG), or the PI3K inhibitor LY294002. Redox balance (DCFH-DA, MDA, GPX activity), glycolysis-related markers (HK2, GLUT1, lactate), and osteogenic-related markers …

Modulation Of Osteoclast Differentiation By Epigallocatechin-3-Gallate (Egcg)/Type I Collagen–Coated Titanium Implant Surface In Vitro, Her-Hsiung Huang, Yu-Ying Cheng, Chia-Fei Liu, Wei-Cheng Chen

Journal of Dental Sciences

Background/purpose: Implant osseointegration depends not only on osteogenesis but also on coordinated bone remodeling. Our previous study demonstrated that epigallocatechin-3-gallate (EGCG)/type I collagen–coated titanium (Ti) surfaces enhance angiogenesis and osteogenic differentiation in vitro. However, their influence on osteoclast differentiation remains unclear. This study evaluated the modulatory effects of this coating on osteoclast responses in vitro.

Materials and methods: Sandblasted and acid-etched (SLA) Ti surfaces followed by alkaline treatment (SLAA) were prepared. Type I collagen was immobilized onto SLAA surfaces using the natural crosslinker EGCG (10 or 50 μg/mL). Surface morphology, roughness, hydrophilicity, and functional groups were characterized. RAW 264.7 macrophages …

Rigorous Validation Of Machine Learning Models For Orthodontic Extraction Prediction Using Nested Cross-Validation And Smotenc-Integrated Pipelines., Anh Thi-Ngoc Do, Hung Trong Hoang, Thuy-Trang Thi Ho, Hieu Ngoc Le

Journal of Dental Sciences

Background/purpose: Machine learning (ML) in orthodontics often suffers from optimistic bias due to data leakage and improper handling of class imbalance. This study implemented and evaluated a production-grade validation framework - nested cross-validation (CV) - for three distinct algorithm classes (logistic regression, random forest, and gradient boosting) using a consensus-labeled orthodontic dataset.

Materials and methods: A retrospective dataset of 500 patients (334 non-extraction/166 extraction) was curated with 41 processed features. Two stratified split protocols (70/30 and 80/20) were evaluated to assess model robustness. To ensure methodological rigor, a 5-fold outer/3-fold inner nested cross-validation was implemented. Crucially, SMOTENC (synthetic minority over-sampling …

In Vitro Characterization Of Tooth-Derived And Dentin-Derived Graft Particles: Comparative Analysis Of Particle Size, Mineral Composition, And Cytotoxicity, Vinh Quang Luu, Nhan Duc Le

Journal of Dental Sciences

No abstract provided.

Active Learning-Assisted Deep Learning For Automated Maxillary Sinus Segmentation In Dental Cone-Beam Computed Tomography, Hsuan Chen, Khoa Dang Nguyen, Chih-Ling Chang, Hong Thi-Phuong Doan, Ya-Chu Chang, Thantrira Porntaveetus, Guang Hong, Wen-Liang Lo, Ding-Han Wang, Ming-Lun Hsu

Journal of Dental Sciences

Background/purpose: Accurate automated segmentation of the maxillary sinus in cone-beam computed tomography (CBCT) scans is crucial for dental implant planning, sinus lift procedures, and pathological assessment, yet there remains a notable lack of publicly available models and datasets for this task. This study developed and evaluated a deep learning model for automated maxillary sinus segmentation using an active learning approach to minimize annotation effort while achieving high accuracy.

Materials and methods: We utilized 249 CBCT scans from the publicly available CTooth+ and STS-Tooth datasets. Ground truth annotations were generated through semi-automated segmentation in 3D Slicer with validation by five expert …

Digital Dialectic: Why Every “Ai-Generated” Work Has A Human Author, Lea Bishop

FIU Law Review

Are ChatGPT and Midjourney tools or creators? Ownership of billions of AI-assisted creative outputs hangs in the balance. Copyright scholars have long debated whether an autonomous artificial intelligence could qualify as an author, but this remains a hypothetical question. Despite widespread application of the term “AI” to software products of the 2020s, autonomously creative artificial intelligence still does not exist. Today’s commercial AI products—such as ChatGPT, Midjourney, Dall-E, Copilot, Gemini, Claude, Suno, Perplexity, and Lumo—are simply the newest generation of computer software. They do not qualify as “artificial intelligence” in either the scientific or science fiction senses. They are mere …

The Protection Of Geographical Indications Under Comparative Lens: Whether Law Artificially Creates Scarcity Of Goods, Domenico Di Micco

FIU Law Review

The economic principles of supply and demand dictate that market prices are contingent on the conditions under which supply and demand converge. Within this theoretical framework, the concepts of scarcity and abundance assume paramount significance. When goods are scarce, prices tend to escalate, while in cases of abundant supply, prices tend to decline. But what factors determine scarcity and abundance? In many cases, scarcity is inherent to the nature of the commodity (for example, diamonds are rarer than common stones). In other cases, such as geographical indications, scarcity is constructed through the legal denomination associated with the commodity, thereby creating …

Contracting For Innovation In The Global South: Empirical Evidence From Brazil, Pablo Marcello Baquero

FIU Law Review

As innovation cycles accelerate, companies seeking to remain at the forefront of the knowledge economy increasingly partner with sophisticated firms to co-create innovation. These collaborations involving pervasive uncertainty are structured through hybrid contractual arrangements that combine features of market-based independence with those of the close coordination typical of the firm. To date, contracting for innovation has been examined primarily in the context of the Global North. In the United States, the literature has focused on the governance mechanisms that parties employ to continuously define their obligations and mitigate opportunism amid profound uncertainty. In Europe, scholarship on contractual networks or organizational …

The Making Of Egyptian Cotton: An Alternative Narrative Between Empire And Global Capital, Dina I. Waked

FIU Law Review

Egyptian cotton has become a celebrated brand. Referring to cotton as “Egyptian” signals a certain quality, luxury, and durability. Egyptian cotton has, thus, become its own trademark, a signifier of value, and a symbol of national heritage. This image is carefully curated. It is now protected under a licensing scheme of branding and marketing that assures that fraudulently claimed “Egyptian cotton” does not benefit from the added value this geographic location ascribes to it. The Egyptian Cotton Association was thus created 2005 to license and accredit the brand. Part of the curation of the brand image is a historical narrative …

Adaptive Multi-Grade Deep Learning For Highly Oscillatory Fredholm Integral Equations Of The Second Kind, Jie Jiang, Yuesheng Xu

Mathematics & Statistics Faculty Publications

This paper studies the use of Multi-Grade Deep Learning (MGDL) for solving highly oscillatory Fredholm integral equations of the second kind. We provide rigorous error analyses of continuous and discrete MGDL models, showing that the discrete model retains the convergence and stability of its continuous counterpart under sufficiently small quadrature error. We identify the DNN training error as the primary source of approximation error, motivating a novel adaptive MGDL algorithm that selects the network grade based on training performance. Numerical experiments with highly oscillatory (including wavenumber 500) and singular solutions confirm the accuracy, effectiveness and robustness of the proposed approach.

Changepoint Analyses Confirms Global Tropical Cyclone Frequency Decline, Michael Wehner, Thomas Fisher, Norou Diawara, Robert Lund

Mathematics & Statistics Faculty Publications

Changes in tropical cyclone frequencies as the climate warms is a topic of significant current debate [1, 2]. There is no accepted theory of how tropical cyclogenesis might respond to a warmer ocean-atmosphere system as multiple controlling factors exist [3–7]. Anthropogenic warming of surface ocean temperatures due to increased greenhouse gas concentrations [8] increases the potential for tropical cyclogenesis [9–11]; however, realized cyclogenesis also requires an initial local disturbance [12–16] to develop. Most multi-decadal tropical cyclone permitting climate models (i.e. resolutions of 15-50km) exhibit frequency decreases in warmer climates, despite the increase in tropical cyclogenesis potential [17–25]. In this paper, …

From Screens To Stress: Public Health Implications Of Cancer Worry In A Digitally Connected World, Shreya Mathur, Ethan Burns, Michael Pokojovy, Tzu-Liang Bill Tseng, Sunil Mathur

Mathematics & Statistics Faculty Publications

Aims:

This study examines how digital information environments, genetic testing experiences, health behaviors, and psychological distress influence cancer-related worry among adults in the United States. It further considers the public health implications of elevated or reduced cancer worry for prevention and risk communication.

Methods:

Data were drawn from a nationally representative survey of 6,252 U.S. adults. Measures included reliance on social media for health decision-making, smoking status, history of genetic testing, and psychological distress. Multivariable analyses assessed associations between these factors and levels of cancer worry.

Results/Findings:

Reliance on social media for health decisions was associated with greater cancer worry, …

A Composite Narxnn Approach To Photovoltaic Power Forecasting With Integrated Weather Inputs And Uncertainty Quantification, Denisse Urenda Castañeda, Sharmin Abdullah, Jackson Morgan, Honglun Xu, Michael Pokojovy, Tzu-Liang Tseng

Mathematics & Statistics Faculty Publications

Solar photovoltaics (PV) are a major source of sustainable energy. Yet, their power output is highly sensitive to environmental variability, particularly solar irradiance, cloud cover, wind, and temperature. Accurate forecasting of PV power is essential for efficient grid integration and energy planning, especially in applications requiring reliable longer-term forecasting rather than one-step-ahead predictions. This study presents a PV power forecasting approach using Nonlinear Autoregressive models with Exogenous Inputs (NARX), integrating large-scale numerical weather historical data as exogenous variables. Although NARX models effectively capture temporal dependencies, they can become overly dependent on historical power values, reducing responsiveness to real-time weather changes. …

Academic Integrity In The Age Of Ai: A Student's Guide To Citation And Disclosure, Steve Baule

Essays in Education

The rapid emergence of generative artificial intelligence (AI) has reshaped academic work, creating new opportunities for learning while introducing complex challenges for maintaining academic integrity. This article presents a clear, practical three question framework to help students determine when and how to disclose AI use in their coursework. Grounded in principles of transparency and intellectual honesty, the framework consists of three guiding questions addressing AI‑generated content, meaningful process support, and purely mechanical assistance. Through detailed explanations and real‑world scenarios, the article clarifies distinctions among these categories and outlines appropriate citation and disclosure practices for each. It emphasizes that AI use …

Machine Learning Acceleration Of Micro-Credentialing, Knowledge Gap Remediation, And Micro-Recruiting Of Stem Assessments: From Learner Data To Hardware, Paul Amoruso

Graduate Studies Theses and Dissertations 2026

The growing demand for a skilled STEM workforce calls for adaptive, data-driven education that personalizes learning while aligning competencies with industry needs. This work introduces a multi-layered framework that integrates artificial intelligence (AI), data mining and hardware-aware optimization to support this goal. At its core, the AchieveUp system applies generative AI-assisted skill tagging to digitized assessments, enabling multi-semester tracking of student progress. Analysis across 14 semesters shows that underperforming students were found to benefit most from attending score clarification sessions, a relationship validated by an R² value of 0.83, indicating strong predictive validity between attendance and skill acquisition. To remediate …

Low-Energy Co2 Sequestration Via Palm Waste Biochar Activated With Carbide Lime For Mineral Carbonation Of Industrial Wastes, Maisa El Gamal, Ameera F. Mohammad, Basim Abu-Jdayil, Imen Ben Salem, Suhaib Hameedi

All Works

A sustainable method for enhancing CO₂ capture and sequestration was developed by accelerating the carbonation of alkaline industrial wastes using carbide lime-activated biochar (BC(CLW)), an alkaline by-product of acetylene production. The biochar was produced from palm tree waste through slow pyrolysis at 400 °C, followed by activation with carbide lime slurry to enhance its alkalinity, surface basic sites, and reactivity toward CO₂. Three industrial residues, namely ladle furnace slag (LF), baghouse dust (BH), and cyclone silo dust (CD), were blended with 0, 5, 7, and 10 wt. % BC(CLW) and carbonated under ambient conditions. Characterization by thermogravimetric analysis (TGA), Fourier-transform …

Mapping Multiclass-Targeted Hate Speech In Online Discourse: An Open Dataset, Sanaa Kaddoura, Sumaia Al-Kohlani

All Works

Online social networks have become central spaces for public discourse, where hostile and discriminatory language toward social groups can cause psychological and social consequences for marginalized communities. Although multiple public hate speech datasets are available, many rely on binary categorization practices that obscure linguistic, cultural, and contextual variation across targeted groups. As a result, minority and less visible forms of hate speech remain insufficiently documented and analyzed. This discussion paper examines methodological limitations in existing hate speech annotation schemes and presents a re-annotation framework applied to the HatEval2019 dataset. The proposed framework introduces target-specific multiclass labels that distinguish subcategories of …

Urban Trees In The Urban Hydrology Cycle, Jorge R. Vera

Theses, Dissertations and Capstones

In urban forestry, trees provide numerous economic, ecological, and aesthetic benefits to the surrounding community. One of their key roles is intercepting stormwater runoff, reducing flooding risk, and improving water quality. Chapter 1 of this thesis characterized the ecological and economic contributions of urban trees on the Marshall University campus and provides guidance on their management and conservation in the future. Chapter 2 examined how urban tree species modify the urban hydrology cycle by altering the volume and timing of precipitation delivery. In Chapter 1, we inventoried 114 acres of Marshall University's main campus in Huntington, WV, from June 28 …

Solubility And Dissolution Mechanism Of Novel Multi-Ester Headgroup Surfactants In Supercritical Co2, Ning Xu, Yan Ling Wang, Baojun Bai, Shi Zhang Cui, Yu Zhang, Wen Jing Shi, Zhao Nian Zhang, Wen Hui Ding, Pei Xu Ma, Zan Gao

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

To address the limited solubility and applicability of conventional hydrocarbon surfactants in supercritical CO₂, a series of multi-ester headgroup surfactants were designed and synthesized by leveraging the CO₂-philic properties of ester groups. The molecular structures were characterized using Fourier transform infrared (FT-IR) spectroscopy and ¹H NMR. A custom-designed laser-based apparatus was developed to quantify surfactant solubility and systematically investigate phase behavior in CO2. Molecular dynamics (MD) simulations were employed to elucidate structure–solubility relationships across multiple scales, including solubility parameters, interaction energies, radial distribution functions (RDFs), and free volume fractions. Results indicate that, at 323.15 K, …

Lorawan-Based Asset Tracking System Development And Performance Analysis Within Stem-Pbl Framework: A Mixed-Method Study, Yousef Alfarraj, Ghada Abdelhady, Abdelrahman Ahmed, Mahmoud Elaasar, Jair J. Aguilar

Teaching and Learning Faculty Publications

This study examines the integration of project-based learning (PBL) within the integrative STEM framework to advance practical problem-solving skills and investigate students' perceptions of the STEM-PBL approach through developing an IoT-enabled asset tracking system using Long-Range Wide Area Network (LoRaWAN) technology to tackle real-world logistical challenges. Adopting a mixed-methods approach, the study combines an experimental approach utilizing quantitative system performance analysis with qualitative insights gathered through participant interviews with ten graduate students. Results reveal that the LoRaWAN system demonstrated high reliability with only 0.437% downtime, validating the technical feasibility of the educational project. Furthermore, participants perceived the STEM-PBL approach positively, …