Physical Sciences and Mathematics Commons^™

Machine Learning-Based Regression For Magnetic Field Prediction From Odmr Spectral Data, Jesse B. Hernandez

Electronic Theses, Projects, and Dissertations

Optically Detected Magnetic Resonance (ODMR) using nitrogen-vacancy (NV) centers in diamond enables sensitive, room-temperature magnetic field sensing, but real ODMR spectra are often noisy and difficult to analyze with traditional peak-fitting methods. This thesis investigates whether machine learning can reliably predict magnetic field strength directly from ODMR spectra, and compares four model families under a single regression task: a random forest, an artificial neural network (ANN), a one-dimensional convolutional neural network (1D-CNN), and a Transformer.

Training data were generated from an NV-ensemble simulation calibrated to real measurements provided by the Ulsan National Institute of Science and Technology (UNIST), spanning 0 …

Ai-Driven Collision Risk Prediction And Debris Optimization In Low Earth Orbit, Emad Alkhazraji, Mohamed E. Yahia, R. E. Tolba, N. S. Alharthi

All Works

Debris congestion and collision in low Earth orbit have become a major point of concern due to the rapid expansion of activities in that region. In this work, an AI-driven framework is developed and deployed to predict, analyze, and optimize collision risk across the altitude inclination space. Local debris object population, mass density distribution, and conjunction derived risk are computed. Then, an AI surrogate model, viz., gradient-boosted decision trees, was trained to predict collision conjunction relative probabilities and risk. Thereafter, data analysis and explain ability techniques are utilized to uncover underlying risk drivers and reveal how altitude, inclination, mass loading, …

Structured Data Preprocessing Techniques For A Multilingual Healthcare Dataset In Machine Learning Applications, Md. Abu Nishan, Choo-Yee Ting, Chih-Yang Pee, Helmi Zakariah, Thanh-Trung Nguyen

Journal of Informatics and Web Engineering

Data preprocessing is a foundational stage in any machine learning (ML) workflow, especially when dealing with complex, multilingual, and real-world healthcare datasets. The quality, consistency, and structure of input data strongly influence the accuracy, fairness, and interpretability of predictive models. This paper presents a comprehensive and structured preprocessing framework designed for a large multilingual healthcare dataset containing 19,536 patient records with 67 features encompassing demographic, clinical, and socioeconomic information. The framework systematically addresses data heterogeneity, linguistic diversity, and structural inconsistencies through multiple stages of cleaning and transformation. The preprocessing process includes translation of Malay text into English to ensure linguistic …

A Comparative Study Of Machine Learning Algorithms For Customer Churn Prediction In Ecommerce, Tan Yi Qi, Lew Sook Ling, Ram Avtar

Journal of Informatics and Web Engineering

Customer churn rate is one of the main challenges that e-Commerce businesses must address, as it may affect revenue and long-term growth. In this paper, predictive analysis was used to identify potential customers who would be lost. It uses two different types of data to evaluate and compare the performance of five Machine Learning (ML) models, namely logistic regression, decision tree, support vector machine, gradient boost and random forest. Accuracy, precision, recall rate and F1 score are used as indicators of model performance. Among them, random forest achieved the highest performance across both datasets, demonstrating superior predictive power and consistency. …

Empirical Evaluation Of Feature Selection Strategies For Interpretable And Robust Healthcare Machine Learning, Md. Abu Nishan, Choo-Yee Ting, Chih-Yang Pee, Helmi Zakariah, Thanh-Trung Nguyen

Journal of Informatics and Web Engineering

Feature Section (FS) is a fundamental step in developing accurate, robust, and interpretable Machine Learning (ML) models, especially when working with high-dimensional structured datasets commonly found in healthcare, finance, and other dataintensive domains. Selecting the most relevant subset of features not only improves predictive performance but also enhances computational efficiency and model transparency. This paper presents a comprehensive and systematic study of widely adopted feature selection strategies, including filter, wrapper, embedded, model-agnostic methods, and dimensionality reduction techniques. Each category is examined through experimental evaluations across multiple classifiers and benchmark datasets to understand how different feature selection mechanisms affect model performance, …

Benchmarking Hybrid Learning Models For Personalized Risk Classification And Prediction In Oncology, Tshikutu Bikengela Anaclet, Nkongolo Kenda Simon, Biduaya Symphorien, Mabela Matendo Rostin, Mbuyi Mukendi Eugène

Journal of Informatics and Web Engineering

In the field of oncology, and specifically regarding prostate cancer, recent breakthroughs in artificial intelligence have opened fascinating possibilities for risk classification and prediction. However, moving from theoretical success to actual clinical practice remains a significant challenge. In this study, we evaluated several architectures (generative, discriminant, and hybrid models) to assess their real-world relevance in the context of longitudinal medical data, which is often noisy or incomplete. Our analysis does not merely measure raw performance; it seeks to understand the critical balance between statistical precision and the interpretability that clinicians require for daily decision-making. By examining the inherent strengths and …

Designing A Predictive Expense Tracking Mobile Application: A Comparison Of Random Forest, Linear Regression, And Prophet-Based Models, Li Wei Tai, Li Zhe Poh, Md Ismail Hossen

Journal of Informatics and Web Engineering

In today’s fast-paced world, people engage in various forms of daily consumption, yet many lack the habit of tracking their expenses due to low financial awareness. Without proper expense recording and budgeting, individuals often struggle to understand their consumption habits and are at a disadvantage when it comes to financial planning, especially during emergencies. To address these issues, this project proposes the development of a user-friendly expense tracking mobile application designed to help adults build healthy financial habits and utilize predictive algorithms to forecast future expenses. The application enables users to record daily transactions, analyse their spending patterns, plan budgets, …

Predictive Test Case Prioritization In Agile Workflows: A Machine Learning Approach With Smote-Enn And Pca, Kavinraj Baskaran, Junaidi Abdullah, Sin-Ban Ho, Said Suleiman Naseer Al Harthy, Ian Chai

Journal of Informatics and Web Engineering

Test Case Prioritization (TCP) is an essential part of agile software development, allowing for the identification and execution of critical test cases early in the process to maximize fault detection efficiency. Traditional TCP techniques often depend on static metrics, like code complexity and historical pass/fail rates, that do not conform with the dynamic nature of Agile workflows. To overcome this, the proposed research presents a discriminative machine learning-based predictive prioritization model that incorporates historical defect data, execution history, as well as requirement criticality to improve auspiciousness of TCP. The study assesses a range of machine learning models like Logistic Regression, …

Intelligent Telemedicine Systems: Machine Learning For Remote Diagnosis And Patient Management, Oras Baker, Kasthuri Subaramaniam, Asiah Lokman

Journal of Informatics and Web Engineering

Telemedicine has experienced significant evolution in the past 10 years from a communication-driven health service to an intelligent, data-driven environment driven by AI (artificial intelligence), ML (machine learning), IoMT (Internet of Medical Things) and cloud–edge computing. This development has been further advanced through ongoing global health challenges that have seen an ageing population, rising burden of chronic, multi-morbid conditions, healthcare specialist shortage, soaring cost of healthcare and major disruptions like the COVID-19 pandemic. Modern telehealth services are now integrating more machine learning algorithms for remote diagnosis, real-time monitoring the patient, predictive risk stratification and proactive treatment. This paper offers a …

Fostering Public Appreciation For Science Through Online Communication, Carrie Craig-Barnes

Paul English Applied Artificial Intelligence (AI) Institute Publications

This presentation explores strategies for fostering public appreciation for science through online communication, highlighting initiatives developed by the NSF Center for Computer Assisted Synthesis (C-CAS). Carrie Craig-Barnes discusses the use of social media platforms, including Instagram, YouTube, and TikTok, to communicate scientific research, engage broader audiences, and make complex scientific concepts more accessible.

The presentation examines approaches to science communication through short-form videos, educational content, collaborations with science communicators, and audience engagement strategies. It also introduces an interactive video game project that combines chemistry education, machine learning, and crowdsourced scientific research, allowing participants to contribute to the classification of scientific …

Graph-Theoretic Analysis Of Function Call Graphs Using L-Moments For Malware Detection, Anthony J. Rose, Wayne C. Henry, Scott R. Graham, Christine M. Schubert Kabban, Christopher M. Rondeau

Faculty Publications

Most malware detection continues to rely on signature matching, which struggles with obfuscated or novel variants. This research presents a malware detector that instead relies on the static structure of function call graphs, summarized using L-moments of the degree, betweenness, closeness, and clustering measures into compact, interpretable descriptors that persist across malware variants. Evaluated on 175,633 binaries spanning many families under balanced, natural-prevalence, and prevalence-weighted training regimes, ensemble methods achieved Area Under the Curve (AUC) values up to 0.98 on the full-corpus random split, while a feed-forward neural network remained robust across regimes with AUC 0.92–0.95. Linear baselines were far …

Closing The Interpretability Gap: Explainable Ml-Based Malware Detection For Defensive Cyberspace Operations, Tashi Stirewalt, Sean Hodgson, Puumaaya Tahiru, Assefaw Gebremedhin

Military Cyber Affairs

This paper presents an end-to-end, explainable malware triage pipeline designed for defense-oriented cyber operations. It combines high-performance static detection methods with analyst-centered interpretability. Utilizing the EMBER 2024 Windows PE subset, we train and evaluate four classifiers and select LightGBM as the production model based on its predictive performance, inference efficiency, and compatibility with exact tree-based attribution. The deployed system consists of four sequential components: PE feature extraction, malware probability scoring, dual explainability (using SHAP and LIME), and large language model (LLM) report generation, all integrated within a Flask web interface. On a temporal test set of 1,080,000 samples, LightGBM achieves …

Mapping The Water Quality Of Jamaica Bay, New York (1996-2024): Principal Component Analysis And K-Means Clustering, Sneha Srivastava

Dissertations, Theses, and Capstone Projects

Jamaica Bay, located along the southeastern coast of New York City, acts as a biodiverse estuary of wetlands, meadows, and salt marsh islands. The purpose of this study is to analyze the water quality conditions of the region over time, comparing locations around the bay to identify hyperlocal features that influence larger trends in the hydrological system. Ten variables were used as water quality indicators, including total Kjeldahl nitrogen, salinity, pH, Secchi disk depth, and total phosphorus, among others, across five stations in the bay, between 1994 and 2024. After data cleaning and standardization methods were applied, principal component analysis …

Prune: A Patching Based Repair Framework For Certifiable And Privacy-Robust Unlearning Of Neural Networks, Xuran Li, Jingyi Wang, Xiaohan Yuan, Peixin Zhang

Research Collection School Of Computing and Information Systems

Machine unlearning has emerged as a key mechanism for enabling the “right to be forgotten” in neural network models, allowing the selective removal of specific training data upon request. Existing approaches typically rely on retraining models with the remaining data, which is computationally expensive and difficult to verify, especially when deployed models are distributed or resource-constrained. To address this challenge, our prior conference work introduced PRUNE, a patching-based framework that formulates unlearning as a neural network repair problem. PRUNE achieves targeted forgetting by learning lightweight patch networks that redirect model predictions on the data to be unlearned while preserving performance …

Machine Learning For Functional Outcome Prediction After Vestibular Schwannoma Surgery: A Systematic Review And Diagnostic Test Accuracy Meta-Analysis, Shiva Nischal, Shaan Patel, Musa China, Kush Kale, Yi Hein Chai, Santosh Guru, William Muirhead, Patrick Grover

Department of Neurosurgery Faculty Papers

PURPOSE: Machine learning (ML) models have been increasingly applied to predict postoperative facial nerve dysfunction and hearing preservation after vestibular schwannoma (VS) surgery. However, reported performance varies substantially, and the overall diagnostic accuracy and clinical reliability of these models remain uncertain. We conducted a systematic review and diagnostic test accuracy meta-analysis to characterise the current state and methodological readiness of ML-based prediction of these outcomes.

METHODS: PubMed, Embase, and CENTRAL were searched from inception to February 2026. Studies evaluating ML-based prediction of facial nerve function or hearing preservation following VS surgery were included. Diagnostic performance metrics were pooled using random-effects …

Set-Valued Conjugate Calculus And Duality In Optimization And Machine Learning Via Generalized Relative Interiors, Gary Lee Sandine

Dissertations and Theses

Convex analysis, optimization, and duality theory are broadly applicable to a multitude of real-world problems. Theoretical frameworks ensuring strong duality and optimality are fundamentally tied to convex separation under qualification conditions frequently involving topological or relative interiors. These can be empty in convex sets that appear naturally in infinite-dimensional models, yet guarantees of optimality and strong duality are often attainable. This dissertation presents frameworks for applying convex separation via generalized relative interiors to develop generalized calculus rules as well as conditions for strong duality and optimality for infinite-dimensional constrained convex optimization problems.

The first major contribution is the introduction of …

Applications Of Machine Learning To Gas Plume Analysis In Longwave Infrared Hyperspectral Images, Scout C. Jarman

All Graduate Theses and Dissertations, Fall 2023 to Present

Each pixel from a hyperspectral camera measures the intensity of light over a continuous range of wavelengths, which is in contrast to traditional color cameras, which just measure the intensity of red, green, and blue wavelengths of light. Longwave infrared hyperspectral images can be used to detect gases from a distance by measuring how different materials emit and absorb heat. This makes them useful for applications such as monitoring industrial emissions or locating hazardous gas leaks. In practice, however, gas signatures in these hyperspectral images are often weak and easily obscured by variations in the background scene, making reliable identification …

Understanding And Predicting Precipitation Characteristics In The United States Through Machine Learning, Numerical Modeling And Measurements, Cody Luther Ratterman

All Graduate Theses and Dissertations, Fall 2023 to Present

Precipitation is one of the most important yet uncertain variables in the climate system. It varies dramatically in terms of timing, accumulation, rate, and phase, depending on location, season, circulation patterns, and atmospheric conditions. Precipitation forecasts, especially snowfall, are essential to supporting drought mitigation and water management in the Intermountain West. Because rainfall and snowfall lead to opposite effects on snowpack, accurately partitioning rain and snow is important to estimate snowpack levels, winter recreation, mountain ecosystems and runoff. The research findings in this dissertation have advanced the understanding and prediction of precipitation and snowpack in the U.S. by addressing the …

Herd: A Policy-Driven Elastic Resource Distribution Framework For Hpc Deep Learning, Alejandro Guerrero Rodriguez

Open Access Theses & Dissertations

Modern deep learning workloads increasingly rely on distributed computation, and High Performance Computing systems can provide the necessary resources through large GPU allocations across interconnected nodes. Despite this, most distributed training frameworks operate under static resource assignments once a job is deployed. Research on NERSC Perlmutter has shown that 50% of GPU-enabled jobs use 25% or less of available GPU memory, and elastic training can reduce this underutilization by dynamically adjusting active workers. However, existing elastic systems have been developed mainly for cloud environments where fault tolerance and cost optimization are the primary concerns. Applying elastic training to HPC environments …

Evaluating Machine Learning Models On Classification Of Novel Cyber Attacks In The Healthcare Domain, Promise Ehimen

Dissertations, Theses, and Projects

The increasing adoption of the Internet of Medical Things (IoMT) has improved healthcare delivery through connected medical devices while simultaneously expanding the cybersecurity risks facing healthcare organizations. Although machine learning based intrusion detection systems have demonstrated high detection accuracy, their ability to respond reliably to previously unseen cyberattacks remains uncertain. This study investigated how a Neural Network model and a Logistic Regression model classified novel cyberattacks within the IoMT environment. The Neural Network and Logistic Regression models were both trained and tested using a subset of the CICIoMT2024 benchmark dataset. The Neural Network achieved 99.82% test accuracy and a 0.94 …

New Distance Distributions Of Asymptotic Giant Branch Stars And Their Role In Tracing Galactic Structure, Rajorshi Bhattacharya

Physics & Astronomy ETDs

Asymptotic giant branch (AGB) stars are among the final evolutionary stages of low- and intermediate-mass stars and among the most luminous cool stellar populations in the Milky Way (MW). Their strong infrared emission allows them to be observed through regions of high interstellar extinction, making them useful tracers of the inner MW. However, their use is limited by unreliable distances because many are dust-obscured and variable, while geometric parallaxes are often unavailable or uncertain. This thesis develops statistical distance-estimation methods for large samples of oxygen-rich AGB stars. The resulting distances broadly agree with literature estimates, supporting their statistical reliability for …

A Dynamics Viewpoint On The Approximation Capabilities Of Infinite-Depth Neural Networks, Andreus Brammer

Electronic Theses and Dissertations 2020 - Present

Neural Ordinary differential equations(Neural ODEs) provide a continuous-time framework for learning dynamical systems by representing the evolution of a state variable through a parameterized differential equation. While most existing methods rely on numerical time stepping methods during training such as RK4, this work investigates an alternate spectral framework where both the solution and the time-dependent network parameters are represented by global polynomial expressions.

Two methods are employed: the first uses Taylor series representations, and the second approach uses Chebyshev polynomial expansions together with fast spectral transforms and efficient polynomial multiplication techniques. In each formulation, the Neural ODE is transformed into …

Analysis Of Social Media Trends For Political Election Predictions, Wong Jing Hong, Lew Sook Ling, Tan Li Tao

Journal of Informatics and Web Engineering

The traditional opinion polls are losing the capability to forecast election results because of the biasness in the sampling and the slowness in updating the polls. Although social media has a lot of real-time data, it has a considerable number of drawbacks, such as noise and demographic bias. This paper shows a new end-to-end forecasting pipeline, which is evaluated on a corpus of 1.75 million tweets related to the 2020 election in the U.S. Our approach adopts a dual-path sentiment extracted (VADER & RoBERTa) for a better accuracy and a new state level feature engineering to fix data bias. This …

Synthetic Data Generation For Healthcare Machine Learning: A Case Study In Vital Signs And Diagnostic Predictions, Sellappan Palaniappan, Rajasvaran Logeswaran, Kasthuri Subaramaniam, Oras Baker, Bui Ngoc Dung

Journal of Informatics and Web Engineering

Healthcare Machine Learning (ML) applications face significant challenges in accessing high-quality training data due to stringent privacy regulations, institutional data silos, and concerns over patient confidentiality. This paper explores synthetic data generation as a viable and privacy-preserving alternative to real patient data for developing ML models in healthcare settings. We present techniques for generating realistic vital signs data including body temperature, blood pressure, heart rate, respiratory rate, and oxygen saturation according to appropriate statistical distributions. In addition, we demonstrate how synthetic datasets generated can be used to train diagnostic prediction models. The generated datasets were applied to multiple diagnostic prediction …

Analysis And Predictive Modelling Of Ev Charging Patterns And User Behaviour, Yi Xuan Law, Kah Ong Michael Goh, Check Yee Law, Connie Tee, Yong Wee Sek, S M Hasan Mahmud

Journal of Informatics and Web Engineering

As more Electric Vehicles (EVs) are released, the ability to predict energy consumption and charging duration becomes crucial in building optimal infrastructure and a proper system of managing energy. This paper proposes a machine learning model that predicts these two important parameters using a real-world dataset. The dataset consists of 1320 EV charging sessions made between January and February 2024 on Kaggle. The data set includes vehicle specifications, time stamps of sessions, environmental conditions, and user behaviour. Feature engineering tasks followed a thorough preprocessing procedure where missing values were imputed, outliers were removed, and the type of data was converted, …

Machine Learning For Employee Attrition Prediction: A Comparative Study, Kai Jia Low, Sook Ling Lew, Sri Winarno

Journal of Informatics and Web Engineering

Employee turnover remains a long-standing issue that can lead to significant economic losses and a decline in workplace productivity. Traditional methods for predicting natural attrition, such as surveys and rumour assessment, usually fail to capture the complexity and multi-factorial nature of natural attrition. To address this limitation, this paper proposes to develop an advanced prediction model using Machine Learning (ML) algorithms to enhance the accuracy and reliability of export prediction. These methods are applicable to a full set of data covering parameters such as demographics, workplace performance and survey scores. The objective of this model is to provide a data-driven …

An Ai-Based Framework For Heart–Brain–Body Coherence In Wellness Monitoring: A Longitudinal Simulation Study, Asiah Lokman, Akalpita Tendulkar, Yujiao Zhang, Mantena Sireesha

Journal of Informatics and Web Engineering

Present wellness monitoring systems primarily emphasize single-modality metrics, neglecting the intricate, interdependent interactions among cardiac, neural, and behavioral regulatory systems. This paper introduces a machine learning framework that implements heart–brain–body coherence as a dynamic, longitudinally evaluated wellness metric. In contrast to previous simulation-based studies that utilized independently generated, cross-sectional data categorized by deterministic IF-THEN rules, the current study adopts a longitudinal simulation design featuring 80 virtual subjects monitored across 30 consecutive daily profiles (N=2,400 records). This design incorporates physiologically realistic inter-variable correlations and probabilistic coherence labelling derived from a continuous risk-scoring function. The subject-level train/test split (56 training subjects, 1,680 …

Machine Learning-Based Prediction Of House Sale Prices In Hulu Langat, Kath Moon Yap Choo, Sew Lai Ng, Da An

Journal of Informatics and Web Engineering

House price prediction remains a complex task due to the interplay of structural, locational, and economic factors. This study proposes a machine learning-based predictive framework tailored to the residential real estate market in Hulu Langat, Malaysia, a district undergoing rapid urbanization. Using open-source datasets, three structured variations are developed: one containing only housing and locational attributes, another incorporating regional-level macroeconomic data, and a third combining both regional and national macroeconomic indicators. The proposed model (Ensemble Weighted Average) is trained and evaluated using evaluation metrics, then compared with models such as Random Forest, XGBoost, LightGBM, and Ensemble Stacking. The proposed model …

Ai-Powered Threat Hunting For Email Phishing Attack Detection Using Natural Language Processing (Nlp), Mohd Azriy Akmalhazim Mohd Nazariee, S Prabha Kumaresan, Alaa Haddad, Mohamed Uvaze Ahamed Ayoobkhan

Journal of Informatics and Web Engineering

Phishing attacks remain as a significant cybersecurity threat, aiming to steal sensitive information by exploiting human vulnerability. Traditional phishing email detection often struggles to keep up with the latest attack strategies developed by the attackers which results in high false positive rates and the limited contextual understanding on the email contents. Therefore, to address these challenges, this research proposes a solution via an AI-powered threat-hunting model integrating Natural Language Processing (NLP) techniques for phishing email detection in English through the development of PhishGuard AI application. The application is developed as a web-based software solution designed to be accessible to both …

Ai-Driven Intrusion Detection System For Network Security, Zhi Lin Sarah Teoh, Wee How Khoh, Hui Yen Yap, Pin Shen Teh

Journal of Informatics and Web Engineering

In the evolving landscape of cybersecurity, Intrusion Detection Systems (IDS) play a vital role in safeguarding computer networks against malicious activity. Traditional signature-based IDS approaches are increasingly ineffective in detecting novel, complex, or zero-day attacks due to their reliance on predefined rules. To overcome these limitations, this study proposes an AI-driven IDS that integrates both classical machine learning and modern deep learning techniques. The framework introduces and compares three models such as Support Vector Machine (SVM), Convolutional Neural Network (CNN), and a hybrid CNN-SVM model. The system is designed to analyze network traffic patterns and classify them as either benign …