Digital Commons Network^™

Robust Hybrid Tree-Based Machine Learning-Assisted Optimization Of Well Parameters To Reduce Asphaltene Precipitation Risk In Oil Fields, Malek Jalilian, Madani, Alireza Keshavarz, Stefan Iglauer, Abbas Khaksar Manshad, Amir H. Mohammadi

Research outputs 2022 to 2026

Asphaltene precipitation is a persistent flow-assurance issue in carbonate oil wells, leading to increased intervention frequency and production losses. This study utilizes multi-decade surveillance and operational data from a mature carbonate field (1983–2023) to train and optimize five tree-based models: Decision Tree, Random Forest, Extra Trees, Gradient-Boosting Decision Tree, and CatBoost, employing a Tree-Structured Parzen Estimator. These models, constrained by operational parameters, were integrated to identify optimal settings that can minimize the frequency of asphaltene precipitation and the subsequent cleanups. The novelty of this research lies in the direct integration of interpretable tree ensembles with an optimizer that adheres to …

Suicide Ideation Detection Using Social Media Data And Ensemble Machine Learning Model, Erol Kina, Jin Ghoo Choi, Abid Ishaq, Rahman Shafique, Monica Gracia Villar, Eduardo Silva Alvarado, Isabel De La Torre Diez, Imran Ashraf

Research outputs 2022 to 2026

Identifying the emotional state of individuals has useful applications, particularly to reduce the risk of suicide. Users’ thoughts on social media platforms can be used to find cues on the emotional state of individuals. Clinical approaches to suicide ideation detection primarily rely on evaluation by psychologists, medical experts, etc., which is time-consuming and requires medical expertise. Machine learning approaches have shown potential in automating suicide detection. In this regard, this study presents a soft voting ensemble model (SVEM) by leveraging random forest, logistic regression, and stochastic gradient descent classifiers using soft voting. In addition, for the robust training of SVEM, …

A Systematic Review Of Audio Deepfake Detection Techniques For Digital Investigation, Mahra Alnaqbi, Richard Adeyemi Ikuesan

All Works

Deepfake technology has been driven by advanced machine learning and revolutionized multimedia creation by synthesizing hyper-realistic content. It includes images, videos, and audio. While its creative applications in entertainment and accessibility are significant, the technology also poses critical risks, especially in fraud, disinformation, and identity theft. Audio deepfakes are a subset of this phenomenon that replicate human voices with enhanced precision, mimicking tone, accent, and subtle vocal nuances. This has raised concerns in security-sensitive domains like voice authentication and forensic investigations. This systematic literature review (SLR) adopts PRISMA guidelines to explore the state-of-the-art in audio deepfake detection. It examines existing …

Dataset For Integrity Attacks On Time Synchronized Synchrophasor Data, Taylah Griffiths, Mohiuddin Ahmed, Chadni Islam

Research outputs 2022 to 2026

Phasor measurement units, also known as synchrophasors, are a vital component within smart grids to determine the stability of the grid. These devices send synchrophasor data to phasor data concentrators that collate and analyse the data. Recently, synchrophasor communication data has become beneficial for the research community. However, datasets covering cyberattacks on synchrophasor data are not public. Having access to this data would aid in investigating mitigations against cyberattacks. This paper describes a public specialized dataset, known as ECU-PMU-FDI/TSA. The dataset contains synchrophasor communication data for cybersecurity mitigation testing. Three hours of communication data was captured, from a simulated testbed. …

Machine Learning Models For Estimating The Consumed And Remaining Useful Life Of Haul Trucks In An Open-Pit Mine In Peru, Marco Cotrina, Jairo Marquina, Mario Sandoval, Jose Mamani, Johnny Ccatamayo

Journal of Sustainable Mining

The purpose of this study was to develop a machine learning-based model to predict the consumed useful life and estimate the remaining useful life of haul trucks in an open-pit mining operation in Peru. A comparative analysis of multiple machine learning models was conducted, including multiple linear regression (MLR), random forest + PSO, support vector regression (SVR), gradient boosting machine (GBM), decision tree + PSO, and artificial neural networks (ANN-MLP). The models were evaluated using performance metrics such as R², RMSE, and MAE, selecting the optimal model to estimate the remaining useful life based on a theoretical lifespan …

Energy-Efficient Routing Protocols In Wireless Sensor Networks For Iot Applications: A Machine Learning Approach Using Xgbm And Color Harmony Algorithm, Subhieh El-Salhi, Bashar Igried, Sari Awwad

Mesopotamian Journal of CyberSecurity

Energy efficiency is a central constraint in wireless sensor networks (WSNs) used for Internet of Things (IoT) applications because sensor nodes have limited batteries, processing capacity, and communication bandwidth. This study combines eXtreme Gradient Boosting (XGBM) with the Color Harmony Algorithm (CHA) to predict energy-efficient paths and optimize model and routing parameters. The analysis uses 58,847 validated network-event records generated with NS-3 and a custom Python simulator; the Intel Berkeley Research Lab sensor trace was used only as an external range check. In a 50-run simulated evaluation, the proposed configuration showed an 18% reduction in energy consumption, a 22% increase …

Beyond Electromyography: A Systematic Review And Meta-Analysis Of Ai Enabled Wearables For Neuromuscular Assessment In Sports Medicine And Rehabilitation, Dariusz T. Skalski, Michał Spieszny, Łukasz Jaworski, Marcin Żak, Artur Terbalyan, Marlena Stawiarska, Wirginia Likus, Adam Maszczyk

Baltic Journal of Health and Physical Activity

Background: Conventional laboratory based EMG systems constrain neuromuscular assessment to controlled environments, limiting ecological validity in sport and rehabilitation. While AI enabled wearable sensor systems, including surface EMG (sEMG), high density EMG (HD-EMG), inertial measurement units (IMUs), and multimodal configurations, have expanded ambulatory monitoring capabilities, no prior meta-analysis has quantitatively synthesized their agreement with laboratory grade comparators or examined the moderating roles of sensor class and task domain. Objective: To determine the overall agreement between AI enabled wearable neuromuscular systems and laboratory benchmarks; to examine sensor class and task domain as moderators of measurement fidelity; to evaluate multimodal gain over …

Understanding The Role Of Data Science Applications In Soil And Water Health, Payton Davis, Debabrata Sahoo, Dara Park, Brook Russell

Forestry and Natural Resources

Data science is an emerging field that can be incorporated into many disciplines, including environmental science. Data science can provide valuable information from data, enhancing the understanding of systems and environments. This publication is intended to give an overview of the different aspects of data science and how data science can be leveraged into and applied to soil and water health.

Investigating The Characteristics Of Ch4 Adsorption In Coal Reservoirs Based On Interpretable Machine Learning, Chen Ruibin, Zhou Sandong, Zhang Weixin, Yan Detian, Wang Hua

Coal Geology & Exploration

Objective Accurately predicting methane (CH₄) adsorption capacity in coal reservoirs is critical to the efficient exploration and exploitation of coalbed methane (CBM). Existing studies largely rely on experimental data from a small number of samples and theoretical adsorption models such as Langmuir. However, these studies exhibit time-consuming and laborious processes, as well as conclusions with limited generalizability, posing challenges to their widespread applications across different basins. Methods Based on 1150 sets of experimental data on CH₄ adsorption in coals, this study investigated five machine learning models, namely artificial neural network (ANN), support vector machine (SVM), K-nearest neighbor …

Intelligent Identification Of Deep Coal Macrolithotypes Based On Weighted Ensemble In Machine Learning: A Case Study Of The Shenmu Area, Ordos Basin, Yao Yuhao, Yang Zhaobiao, Huang Daojun, Wang Jianan, Dong Guodong, Chen Yilin, He Jinxian, Zhang Shang

Coal Geology & Exploration

Objective Coal macrolithotype represents a key geological property in the exploration and recovery of deep coalbed methane (CBM) resources, and its accurate identification is of great significance for selecting the optimal geological and engineering sweet-spot intervals. However, conventional coal macrolithotype identification relies heavily on core observation, suffering from prohibitively high costs since core data are extremely valuable and thus feature a small sample size. Meanwhile, conventional log-based threshold methods face challenges in effectively characterizing the complex boundaries between coal macrolithotypes.Methods This study investigated the No. 8 coal seam of the Benxi Formation, Shenmu area, eastern Ordos Basin. Based on …

Hybrid Deep-Machine Learning For Butterfly Species Image Classification, Maha A. Rajab, Wisal Hashim Abdulsalam, Firas A. Abdullatif, Tole Sutikno

Baghdad Science Journal

Classifying butterfly species is crucial in biodiversity studies and environmental monitoring. However, manual classification is often a laborious process that requires specialized expertise and is prone to error, especially when species have similar visual characteristics. To address these drawbacks, this paper presents a hybrid approach that combines machine learning with deep learning for feature extraction. To enhance the visibility of important features, preprocessing techniques such as background removal and binarization are applied to butterfly images. Feature extraction was performed using the SqueezeNet convolutional neural network, pretrained on the ImageNet dataset. By discarding the final classification layer, the network produced discriminative …

Quantum-Enhanced And Machine Learning Framework For High-Accuracy Fatigue Life Prediction And Structural Analysis Of Connecting Rod, P. H. J. Venkatesh, P. Seema Rani

Babylonian Journal of Mechanical Engineering

The connecting rod is a critical mechanical component that transmits reciprocating motion from the piston to rotational motion in the crankshaft. Although connecting rods are traditionally manufactured from aluminum alloys, titanium alloys, or alloy steels, the demand for higher power-to-weight ratios has motivated the exploration of alternative materials supported by advanced computational validation methods. This study proposes a multilayer optimization framework for identifying the most suitable material for the connecting rod of a 110 cc four-stroke petrol engine. The component was modelled in Pro/ENGINEER, and high-fidelity Finite Element Analysis (FEA) was performed in ANSYS to evaluate the von Mises stress, …

Leakage-Safe Boosting Ensembles With Shap Explainability For Alzheimer's Disease Risk Prediction: A Rigorous Multi-Classifier Benchmark On Global Structured Clinical Data, Hadeer Mahmoud, Fady Salama

Sustainable Machine Intelligence Journal

Alzheimer's disease (AD) is a major public health challenge, and scalable non-invasive risk-stratification tools are needed. We benchmarked 11 machine-learning classifiers on a publicly available global structured Alzheimer's prediction dataset (N = 74,283; 24 predictors) using leakage-safe sklearn/imblearn pipelines. Four resampling strategies were assessed with stratified cross-validation; preprocessing included imputation, IQR-based outlier capping, feature engineering, one-hot encoding, and standardization. The leading models underwent HalvingRandomSearchCV optimization, followed by soft-voting and stacking ensembles. Performance was evaluated on a held-out 20% test set and interpreted with SHAP, permutation importance, and built-in feature importance. No resampling was selected in Stage A (composite score = …

From Data To Victory: The Race For Analytic Superiority In Warfare, Robert Grossman, Emily Goldman

Joint Force Quarterly

Artificial intelligence technologies have reached a tipping point after decades of development. They are diffusing widely across defense and national security applications. Twenty-first century warfighters rely on analytic models in all systems, at all echelons, and in all domains. As more powerful models built on ever larger data sets become ubiquitous, militaries are in a new competition to deploy artificial intelligence. Operational art must embrace “analytic superiority.” This is the operational advantage from collecting and ingesting data, building robust models and computing infrastructure, deploying the models into operational systems, and denying adversaries' ability to do the same

This article explains …

An Intelligent Approach For Mobile Traffic Forecasting And Optimal Positioning Of New Radio Access Sites In Emerging Mobile Networks, Bavoua Kenfack Patrick Dany, Binele Abana Alphonse, Tonye Emmanuel, Ngohe-Ekam Paul-Salomon, Heuna Njeumi Susy Anne-Lucie

Engineering and Technology Journal

The exponential growth of mobile data traffic in Sub-Saharan Africa is placing increasing pressure on cellular operators to modernise their radio access network (RAN) planning. Traditional approaches, namely Excel-based linear extrapolation and manual congestion-map analysis, are inadequate for the non-linear, seasonally driven traffic dynamics observed in heterogeneous environments such as Cameroon. This paper presents RAN-OptimForecast, an artificial intelligence (AI)-based decision-support framework that jointly addresses two problems: (1) accurate long-term evolution (LTE) mobile traffic forecasting using machine learning, and (2) optimal geographical positioning of new radio base stations. Because proprietary operator traffic measurements were not available for release, the framework is …

Artificial Intelligence In Food Engineering For Food Safety, Quality Assurance, And Human Health, Ayad Abbood Abdulhasan, A. M. Mustafa, F. F. Sayyid, Marwan B. Hussein, Mohanad Muzahem Khalaf

AUIQ Technical Engineering Science

Artificial intelligence (AI) is increasingly reshaping food engineering by providing data-driven tools for safeguarding food safety, ensuring quality assurance, and improving human health outcomes. This review synthesizes current evidence on the application of machine learning, deep learning, computer vision, and the Internet of Things (IoT) across the food production continuum, from raw material inspection to consumer-facing nutrition guidance. We examine how convolutional neural networks, hyperspectral imaging, and sensor-fusion approaches enable rapid, non-destructive detection of contaminants and pathogens, and how predictive models support shelf-life estimation and quality grading. We further discuss AI-enabled traceability systems, including blockchain-integrated supply chains, and the growing …

The Application Of Machine Learning And Deep Learning On Demand Forecasting Across Time-Critical Industries: A Systematic Review, Asmaa Seyam, Sujith Samuel Mathew, May El Barachi, Cheng Zhang, Jun Shen

All Works

The applications of machine learning and deep learning in demand forecasting have attracted increasing attention, as they offer remarkable predictive capabilities that help automate forecasting processes and achieve higher accuracy. While numerous review studies have examined solutions within specific industries, there is a lack of comprehensive literature review investigating these solutions across different sectors. Therefore, this study overviews machine learning and deep learning applications in demand forecasting across time-critical industries, including power, tourism, water, transportation, and food. A two-tier classification framework is proposed to categorize demand forecasting studies by both application industry and methodological architecture. In addition, the most popular …

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

Dissertations

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

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

Cmsi Translations #35: How To Leverage The "Butterfly Effect" To Cause The Collapse Of "Taiwan Independence" Elements?, Su Ming

CMSI Translations

Intelligent Tools for Designing Operational Concepts: Intelligent Agents Innovating Mechanisms for Victory

If a large model is likened to a machine, interacting via conversation is akin to a worker manually operating that machine. Although machine tools have significantly reduced human workloads, “manual operation” still entails challenges: demanding skill requirements for operators; difficulty in resolving complex, specialized tasks through conversation alone; difficulty in standardizing and reusing repetitive workflows; susceptibility to hallucinations; and the time- and labor-intensive nature of verifying results. To this end, the Department of Theoretical Innovation Research has proposed a technical roadmap for programming large models. The underlying concept …

A Web-Based Machine Learning Application For Classifying Post-Covid Risk Among Middle-Aged Adults, Himasha Amarathunga, Dhishan Dhammearatchi, Nimesh Pollwaththage

Journal of Innovation in Science, Engineering and Technology

Post-COVID syndrome (Long-COVID) represents a significant public health challenge, yet accessible tools for individual risk assessment among middle-aged adults remain limited. This study describes the development and evaluation of a web-based machine learning application for the classification of post-COVID risk in adults aged 30–60 years. A publicly available secondary dataset comprising 9,637 patient records was used, of which 5,871 (61%) were classified as high-risk and 3,766 (39%) as standard recovery, reflecting an imbalanced class distribution. The web application incorporates key demographic and clinical features including age, sex, vaccination status and comorbidities to produce a binary risk classification (High/Low). Five machine …

Semantic-Guided Diffusion Autoencoder For Medical Image Synthesis And Representation Learning, Neda Yousefi, Abbas Koochari, Azadeh Zamanifar

Makara Journal of Technology

The development of robust machine learning models for medical diagnostics is constrained by the scarcity of large, annotated imaging datasets, a challenge rooted in high acquisition costs and stringent privacy regulations. To address this, generative approaches for data synthesis have emerged as an essential tool, and this study explores the use of diffusion models to generate medical images. This study introduces a novel Diffusion Autoencoder Model (DAM) integrated with a semantic encoder framework to generate interpretable and decodable image representations. Our DAM learns disentangled latent features via its encoder, which then conditions a diffusion probabilistic model acting as the decoder, …

Probe Cytotoxic And Oxidative Stress Effects Of Nanoplastics On Caco-2 Cells: Insights From Raman Spectroscopy And Machine Learning, Bryan Gustafson, Negar Kosari, Emily Brothersen, Morgan Mosher, Anhong Zhou

Biological Engineering Student Research

Nanoplastics and microplastics have become an increasing ecological and health concern due to their widespread presence in the environment and food chain. In this study, Caco-2 cells were used as an in vitro model of the human intestinal epithelium to investigate the cytotoxic effects of polystyrene nanoparticles and microparticles of varying sizes, concentrations, and surface modification. Oxidative stress and apoptosis were evaluated following particle exposure. Raman spectroscopy, combined with machine learning analysis, was employed to detect and characterize biochemical alterations in the cells. Several peak ratios were selected to cluster data depending on size. A correlation between apoptosis and both …

Harnessing Artificial Intelligence For Real-Time Innovation In Upstream Oil And Gas: A Data-Driven Framework For Early Detection Of Lost Circulation Incidents, Gnana Allan Whinney Gnanapragasam

Journal of Global Management Research

Artificial intelligence (AI) and machine learning are reshaping upstream oil and gas operations, yet their value depends less on algorithmic sophistication than on converting heterogeneous sensor streams into timely operational decisions. This study develops and evaluates an AI-enabled framework for early detection of lost circulation incidents (LCIs) during drilling, positioning this safety-critical use case within the broader innovation architecture of upstream operations. Uncontrolled drilling-fluid losses generate non-productive time, well-control risk, and substantial cost. The empirical component uses historical surface drilling data from approximately 200 wells that experienced severe or total losses, recorded at an average frequency of 0.2 Hz (one …

Data-Driven Staging Of Neurodegenerative Pathology Related To Alzheimer’S Disease, Thomas Earnest

McKelvey School of Engineering Graduate Student Theses & Dissertations

Alzheimer’s Disease (AD), the most common cause of dementia, is a dual proteinopathy exhibiting deposits of extracellular amyloid-beta (Aβ) and intracellular tau in brain tissue. Models which describe the spatial and temporal trajectories of these pathologies have been invaluable for understanding AD and have the potential to support diagnosis, disease monitoring, and treatment development. Disease staging systems, which provide protocols for assessing individual disease severity based on their extent of brain pathology, have been crucial for explaining and diagnosing AD. However, these systems have been primarily informed by post-mortem histological assessments and are not directly applicable to disease assessment in …

Research Status And Prospects Of Monitoring Technology For Large-Span Cable-Stayed Bridges Based On Machine Learning, Liu Guoliang, Liu Guokun, Yan Donghuang, Wang Wenxi, Wang Qishun

Journal of China & Foreign Highway

Machine learning and intelligent optimization algorithms have been increasingly applied to construction and health monitoring of long-span cable-stayed bridges. Based on the construction history of cable-stayed bridges both domestically and internationally, an overview of the origin and development process of cable-stayed bridges was provided. Firstly, from the perspective of the entire life cycle of bridges, bridge monitoring was divided into construction period monitoring and operation period monitoring. The applications of mainstream construction monitoring methods in large cable-stayed bridge projects were elaborated, and the specific composition of bridge health monitoring systems was clarified. Secondly, the basic principles of several machine learning …

Real-Time Two-Stage Machine Sound Monitoring For Wire-Edm State Recognition, Yuseop Sim, Yonghyun Lee, Edgar James Yother, Duju Lee, Hojun Lee, Byoungkwon Yoon, Asif Tanveer, Martin Byung-Guk Jun

MMRL-XMO Industrial Seminar

Operational state monitoring is critical for assessing machine utilization and reducing downtime in smart manufacturing. However, many Wire Electrical Discharge Machining (Wire EDM) systems remain legacy machines with limited access to controller-level data, making non-invasive sensing approaches necessary. This study proposes a lightweight two-stage sound-based operational state monitoring framework using an Internal Sound Sensor (ISS) and a 1D convolutional neural network (CNN). The ISS, built around a stethoscope-inspired bell structure, captures machine-specific acoustic signatures while suppressing ambient machine-shop noise and spark-related acoustic interference. The proposed framework classifies machine states in two stages: Stage 1 identifies coarse states such as beep, …

Machine Learning-Driven Prediction And Design Guidance For Asphalt Concrete Using Marshall Stability And Indirect Tensile Strength, Jianglei Xing, Xiao Tan, Mu Guo, Pengwei Guo, Yuhuan Wang, Dongzhao Jin

Michigan Tech Publications

This work addresses the simultaneous prediction of Marshall Stability (MS) and Indirect Tensile Strength (ITS) by integrating machine learning models with multi-objective optimization for the preliminary design of asphalt concrete. Based on 389 experimental samples, 15 variables were selected to describe asphalt properties, aggregate gradation, volumetric parameters and fiber characteristics, and four dual-output prediction models were developed. The models were evaluated using 50 Monte Carlo splits. TabICLv2 performed slightly better for MS prediction, with an RMSE of 1.49 ± 0.22 kN and an R of 0.85 ± 0.04, whereas TabPFN showed a slight advantage for ITS prediction, achieving an RMSE …

Reducing Mr Acquisition Times Using Artificial Intelligence: A Systematic Review, Fatin M. Arief

Radiologic Sciences

Purpose To synthesize existing evidence on artificial intelligence (AI) applications for reducing magnetic resonance (MR) imaging acquisition time, evaluate their impact on image quality, and identify challenges in clinical implementation.

Method A systematic literature review was conducted using PubMed, CINAHL, and Scopus including peer reviewed, English-language articles published between 2020 and 2026. Both qualitative and quantitative primary research were eligible and had to be on AI use in MR processes. Findings were analyzed through thematic synthesis, and the quality of each study was appraised using relevant critical appraisal tools.

Results Three major themes emerged: AI methods in MR procedures, perceived …

Archaeal Signal Peptide Prediction Through Integration Of Proteomics And Machine Learning, Anjali Kaur

Theses

Signal peptides are short N-terminal amino acid sequences that direct proteins through cellular secretion pathways and play an essential role in protein localization and function. Computational tools such as SignalP are widely used to predict signal peptides. However, prediction accuracy for archaeal proteins remains lower than for bacterial and eukaryotic proteins, likely because relatively few archaeal proteins were available for model training. The goal of this study was to determine whether expanding the archaeal training data used by SignalP 6.0 could improve archaeal signal peptide prediction. Archaeal proteomics datasets from five archaeal species were analyzed to identify proteins with experimentally …

Ucf Libraries 2026 Faculty Research Showcase, Thomas R. Caswell, Patrick D. Green, Rae Mair, Yuqing Li, Athena Hoeppner, Sai Deng, Jeanne Piascik, Nokimul Hasan Arif, Peter Spyers-Duran, Tina Buck

Faculty Scholarship and Creative Works

The University of Central Florida (UCF) Libraries’ Faculty Research Showcase is an annual tradition that celebrates the scholarly achievements, research, and creative work of library faculty.

The 2026 Showcase took place on August 4, 2026, and features six engaging presentations covering a diverse range of topics:

• Thomas Caswell – UCF Libraries Faculty Scholarship: Growth & Impact

• Patrick Green – Making Moves: A Cross-Institutional Presentation on Library Skill Transference

• Rae Mair & Yuqing Li – Generative AI as Peer Tutor: Designing & Evaluating a Prompt to Support Source Identification & Evaluation

• Athena Hoeppner – Have you ever …