Digital Commons Network^™

Explainable Physics-Based Constraints On Reinforcement Learning For Accelerator Optimization, Jonathan Colen, Malachi Schram, Kishansingh Rajput, Armen Kasparian

Data Science Faculty Publications

We present a reinforcement learning (RL) framework for optimizing particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator optimization environments designed to emulate the Continuous Electron Beam Accelerator Facility at …

Applying Transfer Learning For Street-Scale Nuisance Flood Forecasting In Coastal-Urban Environments, Binata Roy, Jonathan L. Goodall, Diana Mcspadden, Chetan Kumar, Steven Goldenberg, Yidi Wang, Malachi Schram

Data Science Faculty Publications

An important challenge with Machine Learning (ML) is its transferability; that is, whether an ML model trained on one set of data can be applied to a second set of data without requiring full retraining of the model. Transfer Learning (TL) addresses this challenge by transferring knowledge learned in the source domain (the data it was trained on) to the target domain (a second set of data that is statistically different but related, which the model was not trained on). This study investigates the use of TL for street-scale nuisance flood forecasting by exploring whether an ML model trained for …

Towards Developing A Career Technology Fit Framework And Analyzing Its Influence On Work-Related Outcomes Among It Professionals, Gunjan Tomer

Journal of International Technology and Information Management

With growing attrition rate and significant demand for skilled IT professionals, the importance of studying their behaviour has become important for both academia and industry. Despite ample amount of research, there is still a gap between theory and practice. Based on our qualitative study conducted on Indian IT professionals we propose that technology allocation might contribute in understanding the behaviour of IT professionals. We found that IT professionals evaluate the technology allocated to them based on their individual career motives. This evaluation, either positive or negative, influences their job outcomes. Further, we explored the factors that make a technology preferable …

High Technology And The Developing State: The Arrival Of Supercomputers In India, Ramesh Subramanian

Journal of International Technology and Information Management

While India has made vast strides in information technology in the last few decades, its success is mainly attributed to its software, rather than its hardware sector. In fact, India’s attempts at developing computer hardware that can match international standards have largely been unsuccessful. A notable exception is its development of a series of supercomputers that match and exceed many international standards. This paper looks at an interesting period in India’s computing history – namely the 1980s and 1990s – focusing on its development of an indigenous supercomputer. During that period, supercomputers were thought to be the sole privy of …

Responsible People Analytics For Remote-Work Decisions: A Machine-Learning Benchmark For Classifying Perceived Productivity, Ruth Menjivar, Nima Molavi, Narges Mashhadi Nejad

Journal of International Technology and Information Management

This study examines whether employee-perception survey data can support responsible people-analytics decisions about remote-work productivity. Using the public New South Wales (NSW) Remote Working Survey 2021 (N=1,512), the study benchmarks statistical and machine-learning classifiers for self-reported perceived productivity classes (same, less, or more productive when working remotely relative to onsite work), not objective output, under default, class-weighted, and resampling protocols. Main evidence comes from 5×5 repeated stratified cross-validation using macro F1 and balanced accuracy with fixed model specifications. Class-balanced separability is modest. Random Forest, CatBoost, and LightGBM form a leading cluster with overlapping confidence intervals (macro F1 ≈0.51–0.52). Affective/well-being items, …

The Value Of Personal Data Ecosystems: A Flemish Media Sector Case Study, Maarten De Mildt, Melanie Verstraete, Sofie Verbrugge, Didier Colle

Journal of International Technology and Information Management

Personal Data Stores (PDSs) have been proposed as a privacy-preserving approach to data sharing that increases individual control over personal data while enabling new forms of cross-organizational collaboration. This collaboration leads to the emergence of Personal Data Ecosystems (PDEs). Despite growing interest in PDEs, limited research has examined how the organizational and economic barriers identified in prior studies manifest in practice. This paper investigates these challenges through a case study of the Flemish media sector within the Solid4Media project, which explores the use of PDSs to support data sharing and personalization across media organizations. Using a qualitative research design, data …

Slm With Swarm Intelligence For Efficient Representation Of Medical Claims, Mohamed Ahmed Abo El-Enen, Ravi S. Sharma, Mustafa Abdulrazek, Amril Nazir, Reem Muhammad, Ahmed Talat Sahlol

All Works

Healthcare industry faces significant challenges due to fraudulent medical insurance claims, which result in substantial financial losses. We propose an automated system using domain-specific Small Language Models (SLMs) with a narrower scope and smaller parameter count than general-purpose Large Language Models (LLMs), combined with optimization algorithms to improve fraud detection. Our approach integrates numerical features, such as age and claim amount, with textual descriptions, including diagnoses and procedures, into a unified textual representation for each medical activity. This representation captures complex patterns, enhancing the model’s predictive ability. SLMs fine-tuned on medical corpora transform these textual inputs into fixed-dimensional numerical embeddings, …

Modelling Route-Level Interzonal Travel Time Using Gps Trajectories, Muhammad Faiq Ahmed, Tom Bellemans, Fatma Outay, Muhammad Ahmed, Afzal Ahmed, Feng Liu, Muhammad Adnan

All Works

Activity-based models (ABMs) require accurate travel-time estimates for accessibility calculations, yet many implementations rely on static routing outputs that fail to capture temporal congestion dynamics due to limited high-resolution data. This paper develops route-level travel-speed prediction models using GPS trajectory data from 48 vehicles in Flanders, Belgium. GPS trajectories are integrated with OpenStreetMap and land-use data through destination-based segmentation, in which trips from fixed origins are cumulatively segmented at zone crossings. To capture behavioural differences by trip length, separate Gamma regression models are estimated for short (≤5 km) and long (>5 km) trips using temporal, network, and spatial variables. …

A Design Science Research Architecture For Xr-Based Pre-Visit Cultural Heritage Learning Applications, Mousa Al-Kfairy, Omar Alfandi, Saed Alrabaee

All Works

Pre-Visit preparation plays a critical role in shaping visitors’ learning and engagement in cultural heritage sites; however, existing approaches largely rely on static and passive materials that fail to foster meaningful understanding before the physical visit. Extended Reality (XR) technologies offer new opportunities to address this gap by enabling immersive, narrative-driven pre-visit learning experiences. This paper proposes a conceptual architecture for XR-based pre-visit cultural heritage learning applications, grounded in Design Science Research (DSR). Drawing on museum pedagogy, experiential learning, and XR interaction design, the study identifies key educational and technical requirements and translates them into a layered, modular system architecture. …

Mapping Llm Misuse In Computing Education: A Survey-Based Risk Analysis Of Faculty And Student Contexts, Noura Alzaabi, Mohamed El-Attar, Sarah Kohail, Mahmood Niazi

All Works

Large Language Models (LLMs) have become deeply embedded in computing higher education, yet the misuse risks they introduce for faculty and students remain insufficiently understood from a cybersecurity and data privacy perspective. This paper presents an empirical study in which a structured survey of 105 participants at a computing college was used to identify and systematically risk-score thirteen LLM misuse cases across faculty and student contexts. Using a Likelihood × Impact scoring model, the resulting taxonomy classifies misuse cases as Critical, High, or Medium severity, with over-reliance and skill atrophy, academic integrity violations, and research integrity risks emerging as the …

Evaluating Chatgpt-5 For Misuse Case Diagram Generation: An Empirical Evaluation, Alia Alzarooni, Yasser Khan, Hassan Alsayegh, Mohamed El-Attar, Rima Grati

All Works

Misuse case diagrams are a widely adopted technique in security requirements engineering, enabling analysts to model adversarial threats and derive countermeasures early in the software development lifecycle. However, manual construction of these diagrams is prone to incompleteness and subjectivity, requiring significant security expertise. Large language models (LLMs) such as ChatGPT present a promising opportunity to automate this process, yet their effectiveness for generating structured security modeling artifacts remains largely unexplored. This paper presents an exploratory study evaluating ChatGPT-5's ability to generate misuse case diagrams directly from textual security requirements, using 12 case studies of varying complexity spanning small, medium, and …

Aoi-Aware Agentic Federated Mixture-Of-Digital-Twin Experts For 6g Vehicular Edge Intelligence, Asadullah Tariq, Mohamed Adel Serhani, Ikbal Taleb, Shayma Alkobaisi, Tariq Qayyum, Irfan Ud Din

All Works

Digital twin-enabled vehicular edge intelligence is expected to become a fundamental service paradigm for sixth-generation (6G) intelligent transportation systems. However, the performance of such systems depends not only on model accuracy, but also on the freshness of digital twin states, timeliness of inference, privacy-preserving model training, and efficient use of heterogeneous edge resources. Existing DT-assisted federated learning and edge mixture-of-experts solutions optimize digital twin synchronization, distributed learning, and sparse inference largely independently, without allowing digital twin states to actively govern expert specialization, expert refreshing, and distributed orchestration. Nevertheless, the joint problem of how digital twins should guide federated expert specialization, …

From Image To Insight: Evaluating Llm Accuracy In Understanding Uml Use Case Diagrams With Claude, Mohamed El-Attar, Yasser Khan, Mahmood Niazi, Sajjad Mahmood, Mohammad Alshayeb

All Works

UML use case diagrams are a prominent artefact of requirements engineering, capturing the functional scope of a software system in terms of actors, use cases, and their stereotyped relationships. The emergence of multimodal large language models with image understanding capabilities raises the question of whether such models can reliably extract structured construct-level information from use case diagram images. This paper reports an empirical evaluation of Claude on the task of counting 14 notational construct types from a corpus of 78 computer-generated UML use case diagrams, assessed against manually verified ground truth annotations. Results reveal a strongly differentiated accuracy profile: Claude …

Chronofy: A Temporal-Logical Decay Architecture For Information Validity In Time-Aware Retrieval-Augmented Generation, Muntaser Syed, Marius Silaghi, Sheikh Abujar, Sharun Akter

Electrical Engineering and Computer Science Student Publications

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make …

Epistemic Edge: Subjective Logic Guardrails For Llm-Driven Iot Actuation, Muntaser Syed, Marius Silaghi

Electrical Engineering and Computer Science Student Publications

Deploying large language models (LLMs) as decision-making agents in safety-critical Internet of Things (IoT) systems introduces risks that purely behavioral guardrails, such as action whitelists, cannot fully address. This paper presents Epistemic Edge, a four-tier neuro-symbolic pipeline that augments LLM-driven actuation with subjective logic (SL) uncertainty quantification, temporal decay, and dual guardrails combining epistemic threshold checks with behavioral whitelists. We evaluate seven locally-deployed models: three PrismML Bonsai 1-bit models (1.7B, 4B, 8B), three 4-bit quantized models (Qwen3-8B, Llama 3.2-3B, Phi-3.5-mini), and the DeepSeek-R18B reasoning model, across eight ablation conditions and five IoT actuation scenarios (2,800 controlled trials). We further validate …

A Virtual Model Of Data Centre Cooling, Younis Osama Abdelsalam, Tim Persoons, Sajad Alimohammadi

Research Outputs: 2025-Present

This study presents a calibrated, hybrid spreadsheet-based model developed to simulate the cooling energy consumption of a commercial-scale data centre in Dublin, Ireland. The model leverages five years of high-resolution, sub metered data, including chilled water flow rates, ambient conditions, and IT electrical load, offering a rare empirical foundation for system-level energy analysis. Existing modelling approaches often rely on simplified laboratory case studies, synthetic datasets, or isolated component analysis, limiting their relevance to operational facilities. This study introduces an innovative hybrid modelling framework that bridges the gap between black-box machine learning and rigid physics-only simulations. A key innovation is the …

Corporations’ First Amendment Rights And Algorithmic Cocoons, Sol Murgui Orsucci

Fordham Journal of Corporate & Financial Law

This Note examines how corporate First Amendment doctrine applies to algorithmic systems that curate commercial information and public discourse across online platforms. Courts have increasingly treated ranking, recommendation, and moderation practices as exercises of protected editorial judgment. At the same time, the Court has justified protection for corporate speech in part by reference to listener-centered interests in access to information and competitive comparison. This Note argues that the interaction between these doctrinal strands and contemporary algorithmic intermediation reveals a structural tension. Data-driven optimization can generate individualized informational environments—what this Note terms “algorithmic cocoons”—in which users encounter content, offers, and prices …

Predictive Analytics For Optimising Delivery Performance In Supply Chain Management, Vishwanath Sai Krishna Teja

ICT

Supply chain management has always been a challenging area where delivery delays stand as one of its main ongoing issues. Many companies continue to use outdated data collection systems despite the advancements in data collection tools. This study investigates how predictive analytics can help companies to prevent their operational problems from reaching their customers.

In this study, two datasets were used. The first is the Data Co Smart Supply Chain dataset which covers order level operations from 2015 to 2018, and the second is the World Bank Logistics Performance Index, which covers logistics quality across more than 160 countries. After …

Deep Learning Based Classification Of Retinal Oct Images Using Custom Cnn And Resnet50, Ahmed Afzal

ICT

Retinal diseases such as Choroidal Neovascularization, Diabetic Macular Edema and Drusen can affect vision if they are not detected and treated early. Optical Coherence Tomography images provide detailed cross sectional views of the retina, making them useful for identifying retinal abnormalities. This project investigates the use of deep learning for classifying retinal images from the OCT2017 dataset into four categories: CNV, DME, DRUSEN, and NORMAL. The project follows the CRISP-DM methodology, covering data understanding, data preparation, modelling, evaluation and deployment. During data preparation, duplicate images were removed, image dimensions were standardised and class imbalance was addressed using class weights during …

Pxaa: A Root-Cause Decision-Support System For Airline Passenger Complaints Using Sentiment Analysis And Complaint Classification, Adélia Acacio Da Silva, Stefani Rabelo De Campos Nunes

ICT

PXAA (Passenger Experience Analytics Assistant) is a machine learning and decision-support prototype developed to analyse airline passenger complaints using sentiment analysis and complaint classification techniques. The project follows the CRISP-DM methodology and uses airline passenger reviews collected from AirlineQuality.com through Python web scraping. Natural language processing (NLP) techniques were applied to clean and preprocess the textual data, while logistic Regression was used to classify passenger sentiment into positive, negative and neutral categories.

The project also implemented rule-based complaint classification to identify common complaint themes such as delays, baggage issues, customer service problems, comfort issues, payments/refund complaints and communication failures. These …

Design And Evaluation Of A Supervised Machine Learning-Based Intrusion Detection System., Tarquin Qazi

ICT

This project involves designing and evaluating a supervised machine-learning-based intrusion detection system (IDS) using the CIC-IDS2017 dataset. The project is structured around the cross-industry standard process for data mining (CRISP-DM) framework. The dataset comprises over 2.8 million labelled instances and was cleaned and reduced from 78 to 63 features via redundancy analysis. These data were used to train and tune three supervised classifiers: Logistic Regression algorithm as a linear baseline, a Decision Tree algorithm and a Random Forest algorithm. Hyperparameter optimisation was conducted using RandomizedSearchCV with 3-fold cross-validation, optimising for the F1-macro scoring metric.

While the random forest performed similarly …

Comparative Economic Impact Modelling Of Floods Vs Drought On A Global Scale, Diogo Lemos Aguiar, Paulo Henrique Oliveira Machado

ICT

Climate change is generating unprecedented economic losses through extreme weather events, yet comparative predictive analysis between different hazard types remains limited. This report presents a Machine Learning–Based Comparative Economic Impact Modelling System designed to predict and compare the economic damages caused by floods and droughts on a global scale. The system integrates historical disaster records from the EM-DAT International Disaster Database with country-level socioeconomic indicators from the World Bank's World Development Indicators, applying supervised regression modelling to a unified dataset of 1,301 disaster events across 133 countries from 2000 to 2025. XGBoost and a Multi-Layer Perceptron Neural Network were evaluated …

A Review On Biomass-Derived Hard Carbon Anodes For Sodium-Ion Batteries : From Carbon Precursors To Storage Mechanisms, Anqi Lu, Jiaqian Qin

Journal of Metals, Materials and Minerals

The rapid development of sustainable energy technologies has intensified the demand for cost-effective and high-performance energy storage systems. Sodium-ion batteries (SIBs) are regarded as one of the most promising alternatives to lithium-ion batteries (LIBs) owing to their low cost, abundant sodium resources, and similar electrochemical mechanisms to LIBs. Hard carbon (HC) has attracted significant attention as the predominant anode material for SIBs due to its low cost, structural tunability, and availability from diverse precursors. Nevertheless, challenges remain, including the unclear Na+ storage mechanism, limited rate capability, and strong dependence on precursor type. This review systematically summarizes recent advances in HC …

Mechanical Properties And Crystallization Of Polybutylene Terephthalate Reinforced With Glass Flakes And Aluminum Powder, Nattakarn Hongsriphan, Pajaera Patanathabutr

Journal of Metals, Materials and Minerals

This research investigated mechanical properties and crystallization of poly(butylene terephthalate) composites by adding glass flakes (GF) and aluminum particles (Al). The concentration of the GF was 3 wt% or 5 wt%, and the Al was 0.5 wt% or 1.0 wt%. The stress-strain curves of the PBT-based composites showed yielding and necking. The PBT/GF/Al composites with GF/Al ratios of 3/0.5 wt/wt%, 3/1.0 wt/wt%, 5/0.5 wt/wt%, and 5/1.0 wt/wt% had Young’s moduli of 11.44%, 11.70%, 16.81%, and 19.31% higher than that of neat PBT, respectively. In the presence of Al at 1.0 wt%, the flexural modulus of the PBT/GF/Al composites increased to …

Synthesis, Structure, And Electrochemical Properties Of The Ni(Oh)2/Nimoo4 Composite On The Rgo/Nf Template For Hybrid Battery-Supercapacitor Electrodes, Retno Asih, Haniffudin Nurdiansah, Rogabe Sianipar, Ida Ayu Gayatri, Lukman Noerochim, Diah Susanti, Isao Watanabe, Darminto Darminto

Journal of Metals, Materials and Minerals

The growing demand for renewable and sustainable energy has intensified research on advanced energy-storage systems that can deliver both high energy and power densities. In this study, a Ni(OH)2/ NiMoO4 composite on a reduced graphene oxide/nickel foam (rGO/NF) template was synthesized through a hydrothermal and electrodeposition route to construct a hybrid battery-supercapacitor electrode. The unique hierarchical design combines the pseudocapacitive activity of Ni(OH)2/NiMoO4 with the excellent conductivity of rGO and the high surface area of NF, enabling efficient electron and ion transport. Structural and morphological analyses confirm the successful formation of the Ni(OH)2/NiMoO4/rGO/NF architecture. The electrode exhibits a specific capacitance …

Development Of Poly(Lactic Acid)/Ethylene-Propylene-Diene Monomer/Cellulose Composites Using Cellulose Extracted From Hemp Biomass For Plastic Packaging Applications, Supanicha Alapon, Natthanich Thongmee, Wikoramet Teeka, Pattara Somnuake, Sirirat Wacharawichanant

Journal of Metals, Materials and Minerals

Poly(lactic acid)/ethylene-propylene-diene monomer (EPDM)/cellulose composites using cellulose derived from hemp biomass (CHB) were investigated in this research. Morphology, chemical structures, functional groups, and crystallinity of CHB were characterized, observing a size of 135 ± 32 μm from SEM images with high purity and crystallinity from FT-IR and XRD spectroscopy. The optimized CHB was incorporated at 1 phr, 3 phr, and 5 phr into PLA/EPDM blends at 90/10 w/w. The polymer composites were prepared using an internal mixer, and samples were produced by compression molding for mechanical and thermal testing. The results indicated that the EPDM phase dispersed as droplets in …

Effect Of Cu Content On Microstructure, Morphology, And Antibacterial Properties Of Ti-Cu Alloy Thin Films, Chittra Kedkaew, Phalakorn Khwansungnoen, Tanattha Rattana

Journal of Metals, Materials and Minerals

Ti-Cu alloy thin films exhibit considerable potential for the development of advanced antibacterial surfaces, particularly for biomedical applications. In this research, Ti-Cu binary alloy thin films with a wide range of Cu content from 25.8 at% to 77.8 at% were deposited using magnetron co-sputtering with pure Ti and Cu as the targets. The composition of Cu in the films can be controlled by the applied power of Cu targets. This study investigated the effect of Cu content on the microstructural, morphological, and antibacterial properties using X-ray diffraction (XRD), Field emission scanning electron microscopy (FESEM), Atomic force microscopy (AFM), X-ray photoelectron …

Contributions Of Carbon Content And Cooling Rate On Phase Transformations And Mechanical Properties Of Sintered Fe-1.5cr-0.2mo-Xc Alloys, Mantana Yaruan, Wantana Koetniyom, Thanyaporn Yotkaew, Nattaya Tosangthum, Ruangdaj Tongsri

Journal of Metals, Materials and Minerals

Microstructural development in sintered Fe-1.5Cr-0.2Mo-xC alloys, produced under different cooling rates of 0.1℃∙s‒1 and 5.4℃∙s‒1, was investigated. It was found that, in slowly sintered Fe-1.5Cr-0.2Mo-xC alloys, the microstructure changed from hypoeutectoid to eutectoid and to hypereutectoid steel microstructural features with increasing carbon content. Under the fast-cooling rate of 5.4℃∙s‒1, the microstructural change with respect to the increase of carbon content involved the competition between the formation of ferrite + carbide mixture and that of martensite-austenite constituent. The increase of tensile strength of slowly cooled sintered Fe-1.5Cr-0.2Mo-xC alloys with increasing carbon content was attributed to …

Effect Of Garnet Incorporation On The Functional Properties Of Sunscreens, Parinya Chakartnarodom, Kanyarat Munmani, Sureerat Polsilapa, Duangrudee Chaysuwan, Wichit Prakaypan, Passakorn Sonprasarn, Edward Laitila, Nuntaporn Kongkajun

Journal of Metals, Materials and Minerals

Garnet, a silicate mineral, was investigated as a replacement for the TiO2-based compound in sunscreen formulations. Samples containing garnet were evaluated for color shade, viscosity, sun protection factor (SPF), and water resistance. Substituting the TiO2-based compound with garnet reduced both viscosity and SPF but markedly enhanced water resistance. This improvement is attributed to the physical reinforcement provided by garnet particles, which strengthen the sunscreen film and reduce wash-off under water exposure. Garnet incorporation also altered the product’s appearance from white to a darker brownish-beige tone, improving visual compatibility with a wider range of skin tones.

Effects Of Welding Currents On Microstructure And Corrosion Behaviors Of Inconel 625 Cladding On 2.25cr-1mo Steel By Hot-Wire Tig, Supparat Saeheng, Hein Zaw Oo, Prapas Muangjunburee

Journal of Metals, Materials and Minerals

Hot-wire tungsten inert gas (HW-TIG) cladding has been applied to the steam turbine rotor welding repair. This study investigated the effects of welding currents on microstructure, hardness, and corrosion behavior. The experiments were conducted using four different welding currents applied to bead-on-plate Inconel 625 welds on a 2.25Cr-1Mo steel substrate as the steam turbine rotor material. The selected welding currents were 125 A, 150 A, 175 A, and 200 A. The percentages of weld dilution for different welding currents were also evaluated. Higher welding currents increased weld dilution, weld bead width, and HAZ size. As the welding current increased, the …