Digital Commons Network^™

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 …

A Scientometric Study On Research Trends And Characteristics Of Kimura Disease, Zhongjing Lv, Yiming Luo, Wei Liu, Jian Yuan

Journal of Dental Sciences

Background/purpose: Kimura disease (KD) is an idiopathic condition that presents as a chronic, benign inflammatory disorder, typically affecting the head and neck region. The purpose of this study was to analyze the scientometric characteristics and research trends of KD.

Materials and methods: All the papers on KD were comprehensively retrieved from the Scopus database. The years of publication were divided into before 2012 and after 2012 in the analysis of research trends.

Results: There were 925 papers on KD, with total citations of 10,821 and the h index of 47. Eosinophilia, lymphadenopathy, nephrotic syndrome, angiofollicular lymph node hyperplasia, …

Artificial Intelligence In Dentistry: A Cross-Domain Bibliometric Analysis Of Technologies, Functional Applications, And Dental Specialties, Yinghui Yang, Cheng-Chia Yu, Min Yee Ng

Journal of Dental Sciences

Background/purpose: Artificial intelligence is increasingly applied in dentistry across diagnosis, prediction, treatment planning, education, and patient communication. This study aimed to provide a structured cross-domain overview of dental AI research by integrating AI technologies, functional applications, and dental specialties within one bibliometric framework.

Materials and methods: AI-related dental publications from 2016 to 2026 were retrieved from the Web of Science Core Collection. Original and review articles were screened and classified by AI technology, functional application, and dental specialty. Bibliometric mapping, collaboration analysis, keyword co-occurrence, and heatmap-based cross-domain visualization were performed.

Results: A total of 920 publications were included. Publication …

Ruptured Silicone Cheek Implant Mimicking Odontogenic Infection: A Diagnostic Pitfall, Kimiko Ohgi, Tomoko Shiraishi, Toyohiro Kagawa, Yasunori Yoshinaga

Journal of Dental Sciences

No abstract provided.

Long Short-Term Memory (Lstm) -Based Neural Network Model For Optimizing Composite Manufacturing Process Using Autoclave, Sourav Bolar, Steven Corns, Nayan Pundhir, Kumbla Chandrashekhara

Engineering Management and Systems Engineering Faculty Research & Creative Works

Producing high-quality fiber-reinforced composites requires precise temperature control during autoclave curing, as even small variations can lead to defects that compromise strength and reliability. At the same time, manufacturers aim to reduce energy use and shorten curing cycles without sacrificing material performance. To address these challenges, this study develops a data-driven Long Short-Term Memory (LSTM) neural network model capable of forecasting temperature evolution inside the autoclave throughout the curing cycle. The model is trained on time-series temperature data collected from multiple sensing locations, enabling it to learn the spatial and temporal trends that govern heat flow during curing. Data augmentation …

Work-In-Progress: Evaluating Feasibility Of Band Matrix Solvers For Scaling Up Extreme Learning Machine Method, Anton Akusok, Kaj Mikael Björk, Amaury Lendasse, Leonardo Espinosa Leal

Engineering Management and Systems Engineering Faculty Research & Creative Works

This work presents the results of the potential of band linear system solvers for improving the scalability of the Extreme Learning Machine (ELM) method at large model sizes. The model is tested on the standard MNIST dataset with a range of solvers provided by the SciPy Python library. The results are analyzed taking into consideration the overall performance and the performance impact of band solvers across different matrix bandwidths, as well as the performance versus runtime analysis. The findings show potential in applying the proposed method to very large ELM models with narrow band matrices.

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 …

Efficacy Of Cryotherapy For Oral Leukoplakia: A Systematic Review, Chuan-Hang Yu, Tzu-Chen Chan, Chun-Pin Chiang

Journal of Dental Sciences

Oral leukoplakia (OL) is the most common oral potentially malignant disorder and carries a risk of malignant transformation. Cryotherapy is a minimally invasive treatment option for OL, but its efficacy and optimal dose-response remain inconsistent among various studies. This systematic review evaluated the clinical efficacy and safety of cryotherapy for OL lesions and explored whether the characteristics of the lesions and treatment parameters influenced clinical outcomes. Electronic searches were performed in Embase, PubMed, and the Cochrane Central Register of Controlled Trials according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Seven studies reporting original clinical outcomes of …

Dental Treatment And Oral Care For Patients With Severe Mental Illness Receiving Psychiatric Home-Visit Care: A Narrative Review With An Illustrative Case, Takayuki Suga, Trang Thi Huyen Tu, Yuji Gamo, Takafumi Asakura, Shigeru Iida, Akira Toyofuku

Journal of Dental Sciences

Patients with severe mental illness (SMI) often have untreated caries, periodontal inflammation, tooth loss, xerostomia-related risk, dental anxiety, and delayed dental attendance. This narrative review aimed to synthesize evidence relevant to dental treatment planning for patients with SMI receiving psychiatric home-visit care and to clarify when domiciliary dental assessment and repeated professional oral care may be indicated. Targeted literature searches and citation tracking were used to identify reviews, epidemiological studies, intervention studies, qualitative syntheses, and special care dentistry guidance. The evidence indicates that oral disease in SMI reflects not only limited knowledge but also avolition, cognitive impairment, psychosis, sedation, medication-induced …

Evaluation Of Condylar Position Displacement Using Various Centric Relation Recording Techniques Based On Maximum Intercuspation Position: A Systematic Review And Meta-Analysis, Ling-Shiuan Huang, Yen-Chang Huang, I-Ting Wu, Shinn-Jyh Ding

Journal of Dental Sciences

Background/ purpose: Restoring tooth defects is a key clinical task for dentists, aimed at either maintaining or reconstructing a functional occlusal dentition. This study conducted a systematic review and meta-analysis of clinical trials comparing centric relation (CR) and maximum intercuspal position (MIP) condylar positions obtained using various CR techniques, and to verify the reproducibility of these methods.

Materials and methods: The PubMed, Embase, Google Scholar, and Cochrane Library databases were searched for articles published before January 2026. The single-arm meta-analysis used a random-effects model to calculate the overall effect size.

Results: This study included 12 articles published …

The Leeuwenhoek Paradox In Dental Artificial Intelligence: A Narrative Review Of Artificial Intelligence-Detected Subclinical Periapical Changes And Human-Labeled False Positives, Etyene Schnurr, Mario Parra, David M. Kim

Journal of Dental Sciences

This narrative review explores the “Leeuwenhoek Paradox,” a metaphorical and conceptual challenge that arises when artificial intelligence (AI) detects subtle periapical radiological changes that are not visible to human observers. Drawing on evidence from studies using two-dimensional and cone-beam computed tomography (CBCT) imaging, this review critically examined the limitations of human-centered reference standards and recurrent discrepancies in AI-based periapical detection. The literature shows that AI systems frequently detect more periapical alterations than human experts. These findings may reflect early bone changes, as indicated by CBCT-based analyses of bone density and longitudinal observations. The paradox arises because AI identifies subclinical radiographic …

Oral Pathogens Reprogram Endothelial Barrier And Angiotensin-Converting Enzyme2/Endothelial Nitric Oxide Synthase-Nitric Oxide Signaling To Promote Blood Pressure Dysregulation, Ming-Shou Hsieh, Tung-Nien Hsu, Chin-Sheng Huang, Ting-Yi Renn, Kuang-Tai Kuo, Kuo-Yao Lin, Wei Jen Chang

Journal of Dental Sciences

Background/purpose: Although periodontal disease is associated with an increased risk of hypertension, the endothelial mechanisms linking oral inflammation to vascular dysfunction remain unclear. We investigated whether Porphyromonas gingivalis lipopolysaccharide (Pg-LPS) can directly disturb endothelial homeostasis and whether macrophage–endothelial crosstalk further worsens endothelial injury.

Materials and methods: Human umbilical vein endothelial cells (HUVECs) were exposed to Pg-LPS alone or co-cultured (transwell system) with Pg-LPS-primed human monocytic cells -derived macrophages. Endothelial dysfunction was assessed through nitric oxide (NO) production, endothelial nitric oxide synthase (eNOS) phosphorylation, inflammatory and adhesion molecule expression, as well as junctional and cytoskeletal changes. Macrophage …

Cephalometric And Soft Tissue Determinants Of Esthetic Outcomes After Single-Jaw Mandibular Setback Surgery In Skeletal Class Iii Patients: A Retrospective Study, Chun-Te Ho, You-Ru Chen, Tsui-Hsien Huang, Jnug-Chun Yeh, Tzu-Yu Peng, Chia-Tze Kao

Journal of Dental Sciences

Background/purpose: Orthognathic surgery is an effective treatment for skeletal Class III malocclusion; however, the relative influence of skeletal and soft tissue variables on postoperative esthetic outcomes remains unclear. This study aimed to evaluate the relationships among cephalometric parameters, soft tissue changes, and esthetic outcomes following single-jaw mandibular setback surgery.

Materials and methods: A retrospective study was performed on 258 adult patients with skeletal Class III malocclusion subspinale-nasion-supramentale (ANB) angle < 0° who were treated between 2016 and 2021. Patients were divided into three groups: bilateral vertical ramus osteotomy (BVRO) group (n = 99), genioplasty alone group (n = 30), and BVRO plus genioplasty group. (n = 129). Cephalometric and …

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 …

Daisaikoto Restores Mitochondrial Function And Suppresses Inflammation Induced By Periodontal Bacteria-Derived Lipopolysaccharides, Suzuka Tozawa, Kazuo Tomita

Journal of Dental Sciences

No abstract provided.

Artificial Intelligence-Powered Chatbots’ Responses To Orthodontic Questions From The Dentistry Specialization Examination: Accuracy And Source Evaluation, Berrak Çakmak, Tevhide Sökmen, Burcu Balos‚ Tuncer

Journal of Dental Sciences

No abstract provided.

A Novel Method For The Precise Second Mesiobuccal Canal Orifice Location: A Combined Strategy For Enhanced Clinical Practice, Yuhan Wang, Lingyun Li,

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 …

Do Anatomy, Physiology And Biochemistry Subject Scores Predict Future Academic Performance? A Longitudinal Analysis Of Undergraduate Dental Students Across All Professional Years., Shahid Akhtar Akhund, Hassan Shaibah

Journal of Dental Sciences

Background/purpose: Basic sciences subjects including anatomy, physiology and biochemistry form the foundation of the Bachelor of Dental Surgery (BDS) programme. However, empirical evidence linking the basic science academic performance to sustained academic achievement across subsequent clinical years remains limited. This is true for low and medium sized economies like Pakistan.

Materials and methods: A retrospective, quantitative, and longitudinal cohort study was conducted.  The deidentified data from a representative dental college was used. Basic science examination scores from the 1^st professional year examination served as predictor variables. The examination scores across 14 subjects served as outcome variables. Pearson product-moment correlations …

Deer Antler Tip Cell Culture Supernatant Restores Endothelial Barrier Function And Angiotensin Converting Enzyme 2/Endothelial Nitric Oxide Synthase Nitric Oxide Signaling Impaired By Porphyromonas Gingivalis Lipopolysaccharide, Ming-Shou Hsieh, Ya-Ting Yang, Chin-Sheng Huang, Ting-Yi Renn, Chuen-Kai Wang, Chia-Chen Hsu, Wei Jen Chang, Yu-Sheng Chang

Journal of Dental Sciences

Background/purpose:

Periodontal inflammation contributes to endothelial dysfunction, but effective biologically active strategies for vascular protection remain limited. This study investigated whether deer antler tip cell culture supernatant could rescue Porphyromonas gingivalis lipopolysaccharide (Pg-LPS) induced endothelial injury and restore endothelial homeostasis.

Materials and methods:

Velvet antler tissues from the tip, shaft, and burr regions were examined histologically and used for primary cell isolation. Human umbilical vein endothelial cells were exposed to Pg-LPS or indirectly co-cultured with LPS-stimulated THP-1-derived macrophages. Deer antler tip cell culture supernatant was subsequently applied to these endothelial inflammatory models, and its protective effects were …

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 …