Digital Commons Network^™

Pahina: Precision-Aware Hierarchical In-Network Aggregation For Edge Distributed Training, Yingpu Nian, Bo Yi, Qiang He, Xingwei Wang, Geyong Min, Keqin Li, Sajal K. Das

Computer Science Faculty Research & Creative Works

The rise of edge intelligence is driving distributed machine learning toward a new paradigm of edge-collaborative computing. To overcome the severe communication bottleneck in this paradigm, In-Network Aggregation is a critical enabling technology. However, its effectiveness is fundamentally undermined by the profound resource heterogeneity of edge networks. Specifically, edge devices, adapting to hardware constraints, operate at varying numerical precisions, leading to significant data inflation as gradients are aggregated. Compounding this, unevenly distributed network resources and traditional, precision-oblivious routing strategies often misallocate critical, high-precision gradients to low-quality paths. This mismatch creates severe network congestion, crippling the efficiency of distributed training. To …

Fairrfl: Fair And Robust Federated Learning In The Presence Of Selfish Clients, Andrea Augello, Ashish Gupta, Giuseppe Lo Re, Sajal K. Das

Computer Science Faculty Research & Creative Works

Federated Learning (FL) is a paradigm that enables collaborative machine learning without disclosing the local data of the participants. However, in real-world FL deployment scenarios, some unscrupolous clients may alter the training process to skew the global model towards their local optimum, unfairly prioritizing their data distribution. Their influence can degrade overall model performance for normal clients and reduce fairness in the system. We call this novel category of misbehaving clients 'selfish'. This work proposes a Fair and Robust strategy for aggregation in the Federated Learning (FL) server to mitigate the effect of Selfish clients (FairRFL). FairRFL incorporates a novel …

Future Mining: Learning For Safety And Security, Md Sazedur Rahman, Mizanur Rahman Jewel, Sanjay Madria

Computer Science Faculty Research & Creative Works

Mining industry is rapidly transforming into an AI-driven cyber-physical ecosystem where safety and operational reliability depend on robust perception, resilient communication, trustworthy distributed intelligence and continuous monitoring of miners and equipment. Real-world mining environments impose severe constraints like poor illumination, dust, occlusion, GPS-denied conditions, irregular underground topologies, and intermittent connectivity. These factors degrade perception quality, disrupt situational awareness, impair trajectory prediction and weaken the reliability of distributed learning systems. Emerging cyber-physical threats, including backdoor triggers, sensor spoofing, label-flip attacks and poisoned model updates, further jeopardize operational safety, particularly as mines increasingly adopt autonomous vehicles, humanoid assistance, and federated learning for …

Qura: Reinforcement Learning Based Routing For Quantum Networks, Tasdiqul Islam, Engin Arslan, Md Arifuzzaman

Computer Science Faculty Research & Creative Works

Quantum routing deals with identifying a set of quantum repeaters to use to create entanglement between distant endpoints. Previous approaches proposed shortest-path and linear programming methods to find a solution to this problem. While the shortest path approach results in suboptimal performance, linear programming takes too long to find a solution as the network size and constraints increase. In this paper, we apply Deep Q-Reinforcement Learning (DQRL) to optimize routing in quantum networks both in terms of execution time and performance. The proposed Quantum Routing Algorithm (QuRA) first chooses which request to schedule among all requests. It then determines which …

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 …

Feddot: Defending Federated Learning Against Overwhelming Targeted Attacks, Priyesh Ranjan, Ashish Gupta, Federico Coro, Sajal K. Das

Computer Science Faculty Research & Creative Works

Federated Learning (FL), which facilitates collaborative model training and protects users' privacy, has drawn great interest from the research community. With FL, participants train their models on local data and submit the corresponding updates for aggregation to a server. While concealing the identities of the participants, FL may attract adversaries in order to hamper the underlying model. In this paper, we propose an FL framework, FedDOT, to defend against adversaries performing targeted attacks. FedDOT incorporates two powerful defense algorithms, Maximum Spanning Tree based attacker detection (MSTAD) and Densest graph-based attacker detection (Density-AD), which leverage correlation between weight updates and graph …

You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image, Taoyue Wang, Xiang Zhang, Xiaotian Li, Huiyuan Yang, Lijun Yin

Computer Science Faculty Research & Creative Works

We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for objects or faces typically require a high-resolution RGB image as input. When dealing with degraded images, the conventional pipeline follows a two-stage process: first restoring the image to high resolution, then synthesizing novel views from the restored result. However, this approach is highly dependent on the quality of the restored image, often leading to inaccuracies and inconsistencies in the final output. To address this limitation, we extract single-view features directly from the blind face image …

Dynamic Hub-Aware Knowledge Distillation For Efficient Traffic Flow Forecasting, Xiangjie Kong, Can Shu, Wenchao Weng, Zhenzhen Zhao, Guojiang Shen, Lei Wang, Sajal K. Das

Computer Science Faculty Research & Creative Works

Real-time traffic forecasting acts as a critical enabling service for IoT-driven Intelligent Transportation Systems (ITS). While existing Spatiotemporal Graph Neural Networks (STGNNs) achieve superior forecasting accuracy, their intensive computational complexity and high latency create a deployment bottleneck for resource-constrained IoT edge devices. To address this resource-accuracy mismatch, we propose a novel framework termed Dynamic Hub-Aware Knowledge Distillation (DHKD). Unlike traditional uniform distillation paradigms, DHKD introduces a topology-aware strategy to transfer knowledge from a complex teacher to a lightweight Spatiotemporal Multi-Layer Perceptron (STMLP) student model. Specifically, we design a dynamic hub-aware gating (DHAG) mechanism that adaptively identifies time-varying pivotal sensing nodes …

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 …

Utility-Preserving Federated Graph Learning With Dual-Perspective Fairness, Renqiang Luo, Huafei Huang, Shuo Yu, Fengqi Yu, Feng Xia, Sajal K. Das, Chengqi Zhang

Computer Science Faculty Research & Creative Works

Fairness-aware federated graph neural networks (FedGNNs) necessitate consideration of both the server and the clients. However, fairness-aware methods struggle to enhance dual-perspective (i.e., server and clients) fairness without sacrificing utility due to the distributed learning framework. As a consequence, the utility sacrifices of fairness-aware graph learning methods are even exacerbated in federated frameworks. In this work we propose F3GL, a dual-perspective fairness federated graph learning method that enhances both global (for the server) and local fairness (for clients) while preserving utility. Through theoretical analysis, we delineate the similarity between original sensitive features and those after convolution under different spectra. Our …

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 …

Aim5b: Ai Integrated Semantic Framework For 5g And Beyond Network Management, Thanveer Sulthana, Ava Sharif Jourabchi, Venkat Rao Manavarthi, Jayadithya Nalajala, Ankitha Srirama Reddy, Baek Young Choi, Sejun Song

Computer Science Faculty Research & Creative Works

Scalable, interpretable, and intelligent network monitoring and management are critical for 5 G and future networks. This paper introduces Aim5B, an AI-integrated semantic framework for 5 G and beyond network management to address these challenges. Aim5B processes unstructured logs from key 5G core network functions, and transforms them into a knowledge graph aligned with the semantic structure of control-plane events. Leveraging a large language model (LLM), Aim5B enables natural language queries to be translated into Cypher graph queries, facilitating precise log retrieval, event analysis, temporal correlation, and statistical summarization-without relying on static parsing rules or predefined dashboards. Integrated on a …

Escher: Efficient And Scalable Hypergraph Evolution Representation With Application To Triad Counting, S. M. Shovan, Arindam Khanda, Sanjukta Bhowmick, Sajal K. Das

Computer Science Faculty Research & Creative Works

Higher-order interactions beyond pairwise relationships in large complex networks are often modeled as hypergraphs. Analyzing hypergraph properties such as triad counts is essential, as hypergraphs can reveal intricate group interaction patterns that conventional graphs fail to capture. In realworld scenarios, these networks are often large and dynamic, introducing significant computational challenges. Due to the absence of specialized software packages and data structures, the analysis of large dynamic hypergraphs remains largely unexplored. Motivated by this gap, we propose ESCHER, a GPU-centric parallel data structure for Efficient and Scalable Hypergraph Evolution Representation, designed to manage largescale hypergraph dynamics efficiently. We also design …

Corrigendum To "Human Umbilical Cord Mesenchymal Stem Cells Secretome And Nanoemulsion Propolis Combination Ameliorate Osteoclastogenesis In Lipopolysaccharide-Induced Osteolysis In Hyperglycemia Rats"

Journal of Dental Sciences

No abstract provided.

Evaluating The Use Of Machine Learning For Road Maintenance Cost Estimation, Shahla Shirinzad, David Enke

Engineering Management and Systems Engineering Faculty Research & Creative Works

Accurate estimation of highway maintenance costs is essential for efficient resource allocation and long-term infrastructure sustainability. This study evaluates the effectiveness of advanced machine learning models, including ResNet, Transformer, and other neural network architectures, for forecasting maintenance costs using historical data from the Highway Maintenance Improvement Program (HMIP) provided by the North Carolina Department of Transportation (NC DOT). A comprehensive comparative analysis is conducted across multiple models using standard performance metrics, including R², MAE, RMSE, and MSE. The results demonstrate that advanced architectures, particularly ResNet and Transformer, consistently outperform traditional statistical approaches and baseline machine learning models, achieving …

Performance Of Chatgpt-4, Gemini, And Deepseek-V3 On English-Translated Questions From The Taiwan National Dental Technician Licensing Examination Over A Three-Week Period, Yi-Pang Lee, Ching-Yi Huang, Andy Sun, Chun-Pin Chiang

Journal of Dental Sciences

Background/purpose: Large language models (LLMs) have shown potential in answering professional examination questions. This study evaluated the performance of ChatGPT-4, Gemini, and DeepSeek-V3 in answering English-translated questions from the 2023 Taiwan National Dental Technician Licensing Examination (TNDTLE) over a three-week period.

Materials and methods: A total of 194 English-translated, text-based multiple-choice questions were selected from the 2023 TNDTLE. ChatGPT-4, Gemini, and DeepSeek-V3 were used to answer the same set of English-translated questions at four time points: baseline and one-, two-, and three-week follow-ups. Accuracy rates (ARs) were calculated and compared to evaluate changes over time and differences among the three …

Performance Of Chatgpt-4, Gemini, And Deepseek-V3 In Answering The Prompt-Engineered Questions From The Taiwan National Dental Technician Licensing Examination Over A Three-Week Period, Yi-Pang Lee, Ching-Yi Huang, Andy Sun, Chun-Pin Chiang

Journal of Dental Sciences

Background/purpose: Large language models (LLMs) have shown promise in answering professional examination questions. This study evaluated the performance of ChatGPT-4, Gemini, and DeepSeek-V3 in answering prompt-engineered questions selected from the 2023 Taiwan National Dental Technician Licensing Examination (TNDTLE) over a three-week period.

Materials and methods: A total of 194 Chinese-language text-based multiple-choice questions were selected from the 2023 TNDTLE. The three LLMs answered these questions using a standardized prompt referring to 17 dental technology textbooks. Accuracy rates (ARs) were recorded at baseline and after one, two, and three weeks. Comparisons of ARs over time, among three LLMs, between basic and …

Ensemble Learning For Predicting Periapical Lesions From Dental Radiographs, Fang-Yuan Liao, Ming-Jyun Jian, Abdullah Sarini, Yulianto Jesica, Yen-Kun Lin, Hsun-Yu Huang

Journal of Dental Sciences

Background/purpose: Diagnosing periapical cysts and granulomas using periapical radiographs is challenging due to subtle radiographic differences. This study aimed to develop a machine learning–based diagnostic framework to improve lesion classification through ensemble learning and dentin standardization.

Materials and methods: Five models—Support Vector Classifier (SVC), Nu-SVC, K-Nearest Neighbors (KNN) and Decision Tree—were trained on 144 pre-treatment periapical radiographs (70 cysts and 74 granulomas). Dentin standardization normalized grayscale values to ensure feature consistency. A weighted soft voting strategy was employed to integrate predictions, with model weights derived from individual diagnostic performance. Model performance was evaluated via five-fold cross-validation. Statistical significance among models …

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 …

Influence Of All-On-4 Implant Angles On Stability And Crestal Bone - A Finite Element Optimization Analysis,, Jing-Jie Chen, Chen-Sheng Chen

Journal of Dental Sciences

No abstract provided.

Mesenchymal Stem Cells Derived From Gingiva Normoxic Or Hypoxic-Preconditioning Allogenous Transplantation Affect Orthodontic Tooth Movement In Vivo, Alexander Patera Nugraha, Guang Hong

Journal of Dental Sciences

No abstract provided.

A Bibliometric Evolution Of Molecular Mechanisms And Emerging Research Trends Of Therapeutic Resistance In Oral Cancer, Chu-Yen Chien, Ying-Chen Chen, Jia-Rong Wu, Hsu-Hua Chu, Yi-Jen Hung, Yi-Shing Shieh

Journal of Dental Sciences

Background/purpose: Drug resistance has served as a primary determinant of treatment failure and disease recurrence in oral cancer. The present study aimed to evaluate the global research landscape of drug resistance mechanisms in oral cancer by integrating bibliometric mapping with bioinformatic validation.

Materials and methods: A comprehensive dataset of 1660 publications was retrieved from the Scopus database. Bibliometric analyses were performed using Biblioshiny and VOSviewer to evaluate publication trends, collaborative networks, and thematic evolution. To bridge research trends with biological mechanisms, 1469 genes associated with oral cancer and drug resistance were extracted from the GeneCards database and subjected to functional …

Digital Twin Freshness Maximization In Edge Computing, Jing Li, Jianping Wang, Weifa Liang, Quan Chen, Sajal K. Das, Xiaohua Jia

Computer Science Faculty Research & Creative Works

Mobile Edge Computing (MEC) shifts powerful computing resource provisioning from remote powerful data centers to the edge of core networks. Meanwhile, Digital Twin (DT) has surfaced as a promising technology to provide comprehensive and dynamic descriptions of physical objects in cyberspace with bidirectional and real-time interactions. Moreover, Internet of Things (IoT) devices have contributed abundant, heterogeneous and continuous data from interconnected devices to the explosion of DTs. With technologies evolution, there is an increasing necessity to address the freshness of both DT states and DT data, through timely synchronizations between DTs and their objects in a highly dynamic IoT environment. …

On-Device Artificial Intelligence Solutions With Applications To Smart Environments, Fabrizio De Vita, Dario Bruneo, Sajal K. Das

Computer Science Faculty Research & Creative Works

Recent advances in Artificial Intelligence (AI) and the increasing availability of computational power have accelerated the diffusion of Intelligent Cyber-Physical Systems (ICPSs), enabling smart applications with reasoning capabilities. However, the limited resources of embedded and Edge devices significantly constrain the complexity of deep learning models that can be effectively deployed. Traditional approaches rely on cloud-based training and edge-only inference, a paradigm that becomes inadequate when low latency, privacy, security, and high customization are required. In this context, On-device AI is emerging as a new paradigm in which both training and inference are performed directly on the device, avoiding data transfer …

Concerted Proton Transfer In Homogeneous And Heterogeneous Cyclic Hydrogen-Bonded Clusters Of H2o, Hf, And Hcl, Max R. Tucker, Yuan Xue, Nathan R. Speake, Eden Nickolson, Jeremy M. Carr, Gregory S. Tschumper

Chemistry Faculty Research & Creative Works

This work examines various homogeneous and heterogeneous clusters of hydrogen-bonded (HF)x(H₂O)y(HCl)z complexes, where x + y + z = 3 or 4. For each unique cyclic structure associated with the xyz permutations, the geometries of the reactant, product, and transition state (TS) for concerted proton transfer (CPT) were fully optimized using second-order Møller-Plesset perturbation theory (MP2) with a mixed basis set consisting of cc-pVTZ for H atoms and aug-cc-pVTZ for O, Cl, and F atoms (denoted haTZ). Harmonic vibrational frequencies were also computed at the same level of theory to verify the nature of the stationary points. Intrinsic …

Volatile Organic Compound Analysis Of Humboldt Penguin (Spheniscus Humboldti) Preen Oil: A Pilot Study, Dante E. Rojas, Mitchell M. Mccartney, Eva Borras, Michael O. Eze, Abigail Pietrow, Jennifer J. Valvo, Cristina E. Davis

Chemistry Faculty Research & Creative Works

Avian olfaction has gained prominence in recent decades for its roles in social communication and behavior. In penguins, the chemical characterization of preen oil remains limited. In this exploratory study, we characterized the volatile organic compound (VOC) profile of preen oil from Humboldt Penguins (Spheniscus humboldti). Preen oil from 12 captive individuals was analyzed using headspace sorptive extraction (HSSE) coupled to gas chromatography–mass spectrometry (GC–MS). Chemometric analyses examined variation in VOC profiles by sex, age class, and breeding activity. We detected 54 compounds (20 tentatively identified), including linear alcohols, methyl ketones, carboxylic acids, saturated hydrocarbons, oxygenated and nitrogen-containing organics, prenolipids, …

Synthesis Of The Naga(S1−Xsex)2 Solid Solution From Mechanically Activated Precursors, Louisiane Verger, Julien Trébosc, Santhoshkumar Sundaramoorthy, Amitava Choudhury, Olivier Hernandez, Eric Furet, Sébastien Chenu, David Le Coq, Laurent Calvez, Olivier Lafon

Chemistry Faculty Research & Creative Works

NaGaS₂ and NaGaSe₂ are two recently discovered compounds that crystallize in the same structure type. In this work, NaGa(S_1−xSe_x)₂ (x = 0.5, 0.75 and 1) are prepared using an alternative synthesis route, mechanochemistry followed by heat treatment. Na₂S, Na₂Se, Ga₂S₃ and Ga₂Se₃ are milled in stoichiometric proportions. Differential scanning calorimetry, X-ray diffraction and solid-state nuclear magnetic resonance (²³Na and ⁷¹Ga) show that the compounds after milling are composed of crystalline NaGa(S_1−xSe_x)₂ with an amorphous part. …

Soft-Chemical Scalable One-Pot Aqueous-Medium Synthesis Of Na3(Vo)2(Po4)2f-Based Cathodes: Compositional Tuning And Electrochemical Performance In Na- And Li-Ion Batteries, Prashanth Sandineni, Subal Chandra Manna, Sutapa Bhattacharya, Santhoshkumar Sundaramoorthy, Ramesh Deokate, Milad Aghayi-Anaraki, George E. Sterbinsky, Kartik Ghosh, Amitava Choudhury

Chemistry Faculty Research & Creative Works

One of the most important cathode materials for Na-ion batteries, Na₃(VO)₂(PO₄)₂F, and its compositional variants have been synthesized using four different and facile one-step soft chemical routes. The as-synthesized compounds, Na_2.95(VO)₂(PO₄)₂F (I), Na_2.93(VO)₂(PO₄)₂F (II), and Na_2.58(VO)₂(PO₄)₂F (IV), crystallize in the tetragonal crystal system in the P4₂/mnm space group, while Na₃(VO)₂(PO₄)₂F (III) crystallizes in the orthorhombic crystal system in …

Puppet Lab: Investigating Digital Technologies In Creative Learning, Harrison Lorenz-Daniel

Theses : Honours

This study interrogates the impact that digital technologies and digital mediation have on creative learning workshops run by arts organisations and delivered by teaching artists. It responds to a wave of new creative learning initiatives supported by arts organisations, state governments, and schools following the COVID-19 pandemic. Situating the research primarily in the investigation of Puppet Lab, a new digital workshop developed by Spare Parts Puppet Theatre in Walyalup (Fremantle), qualitative data was collected over a series of 5 semi-structured interviews with Western Australian teaching artists. The study found that digital technologies did not meaningfully impact the standard delivery of …

Transforming The Chemistry Classroom: Flipped Learning As A Scaffold For Inquiry, Hannah Alicia Nash

Graduate Research Papers

This action research study examines how the placement of flipped instruction within a 5E instructional model impacts student content understanding and perceptions of learning in a high school Chemistry II course. Research was conducted across three sections during a gas laws unit, with each section experiencing a different instructional approach. These approaches included flipped instruction in the Engage phase, flipped instruction in the Explain phase, or a non-flipped approach in which all parts of the 5E occurred in class. Pre and post tests were used to measure student understanding, while surveys and reflections were used to gather student perceptions of …