Engineering Commons^™

Development And Evaluation Of Machine Learning Models For Early Pediatric Sepsis Prediction, Ancita M. Andrade

Browse all Theses and Dissertations

Sepsis is a leading cause of pediatric mortality, claiming more lives in the United States annually than all childhood cancers combined. Early identification in Emergency Departments (EDs) remains challenging, as the current Phoenix criteria establishes an updated international consensus definition for sepsis, however is not designed for use as a screening tool. This study aimed to develop predictive models identifying pediatric patients at risk of sepsis within 24 hours of admission. Multiple tree-based and deep learning models were trained utilizing clinical and laboratory data from the initial four hours of presentation. Both the LightGBM and LSTM architectures demonstrated superior performance, …

Dataset Generation For Routing Policy Study In Ad Hoc Wireless Networks, Vishnu Vishnu Priya

Browse all Theses and Dissertations

Ad Hoc wireless networks, with their decentralized architecture and dynamic topology, present challenges in reliable and energy-efficient routing. While machine learning (ML) and reinforcement learning (RL) offer promising solutions, progress is limited by the lack of realistic, high-fidelity datasets. This research introduces a simulation-based framework for generating four diverse datasets representing combinations of node mobility (mobile vs. static) and spatial distribution (random vs. clustered). Each dataset captures critical metrics such as Signal-to-Interference-plus-Noise Ratio (SINR), bottleneck rate, and power consumption across multi-hop paths. A lookahead-based greedy routing algorithm with scenario-aware power control is implemented to emulate practical behavior. Supervised ML models, …

Precision Medicine Assessment Of The Radiographic Defect Angle Of The Intrabony Defect In Periodontal Lesions By Deep Learning Of Bitewing Radiographs, Patricia Angela R. Abu, Yi Cheng Mao, Yuan Jin Lin, Chien Kai Chao, Yi He Lin, Bo Siang Wang, Chiung An Chen, Shih Lun Chen, Tsung Yi Chen, Kuo Chen Li

Department of Information Systems & Computer Science Faculty Publications

In dental diagnosis, evaluating the severity of periodontal disease by analyzing the radiographic defect angle of the intrabony defect is essential for effective treatment planning. However, dentists often rely on clinical examinations and manual analysis, which can be time-consuming and labor-intensive. Due to the high recurrence rate of periodontal disease after treatment, accurately evaluating the radiographic defect angle of the intrabony defect is vital for implementing targeted interventions, which can improve treatment outcomes and reduce recurrence. This study aims to streamline clinical practices and enhance patient care in managing periodontal disease by determining its severity based on the analysis of …

A Secure Ml-Assisted Framework For Resilient And Efficient Prediction Of Physiotherapy Sequence In Bilateral Carpal Tunnel Syndrome, Pratik Pandurang Kharat

Browse all Theses and Dissertations

Bilateral idiopathic carpal tunnel syndrome (CTS) is a neuromuscular disorder characterized by compression of the median nerve at both wrists, leading to symptoms such as pain, numbness, tingling, and muscle weakness. Unlike unilateral cases, bilateral idiopathic CTS presents distinct therapeutic challenges due to the simultaneous involvement of both hands and the lack of an identifiable underlying cause. This study explores the application of machine learning techniques to predict the optimal sequence of physiotherapeutic interventions Stretching followed by Myofascial Mobilization (S/M) or the reverse (M/S) in female patients with bilateral idiopathic CTS and right hand dominance. Data were drawn from a …

Learning Under Data Scarcity: Reasoning And Negative Distillation For Texts And Graphs, Calvin T. Greenewald

Browse all Theses and Dissertations

Modern machine learning (ML) models rely on large amounts of high-quality labeled data to achieve optimal performance. However, in many real-world domains, such as cyber security, acquiring sufficient labeled data is often infeasible due to cost, privacy concerns, and the rapid evolution of underlying phenomena. This challenge underscores the importance of learning under data scarcity. This thesis addresses this challenge by proposing distinct, modality-specific techniques for text and graph domains, which allow models to generalize effectively with minimal data. For text classification task, we incorporate distilled rationales from large language models and adversarial perturbations into the input space to improve …

Machine Learning Guided Insights Into Phonon Scattering Mechanisms For Tunable Thermal Transport In Materials From First-Principles, Niraj Bhatt

Open Access Dissertations

As device dimensions shrink in the current era of miniaturization, effective thermal management at the material level has become critical. In ultrasmall device lengths, traditional electronic heat transport becomes severely limited as boundary scattering effects curtail the electronic transport because the electronic mean free paths substantially exceed those of phonons. The resulting high-power- density devices generate thermal hot spots that compromise both performance and long-term reliability. This challenge has intensified the search for materials with superior phonon-mediated heat transport, a key requirement for effective thermal management in next-generation nanoelectronics. Accurately predicting thermal transport properties with near-experimental accuracy is therefore essential. …

Development Of A Design Tool For Tow-Steered Composite Structures With Machine Learning-Assisted Modeling, Bangde Liu

Industrial, Manufacturing, and Systems Engineering Dissertations - Archive

Fiber-reinforced composites (FRCs) are widely used in aerospace, automotive, and other engineering applications due to their lightweight characteristics and superior mechanical properties. Traditional FRCs employ a fixed fiber orientation in each layer, and while different layup sequences can tailor performance, the mechanical properties remain spatially uniform. Tow-steered composites, which enable fibers to follow curvilinear paths, offer the potential for spatially varying stiffness and strength, improving structural performance.

This dissertation addresses key challenges in modeling and designing tow-steered composite structures, including the lack of commercial design tools, the high computational cost of design optimization, and the need to efficiently evaluate manufacturing …

Ion Hydration In Bulk And Nanoconfined Water: Insights From Machine Learning Force Fields, Zachary D. Baker

Theses and Dissertations--Chemical and Materials Engineering

Understanding ionic hydration remains a central challenge in physical chemistry and materials science, as the interactions between ions and water molecules govern diverse phenomena ranging from electrolyte transport to selective ion separation. While experimental techniques have provided invaluable insights into solvation energetics and coordination numbers, they often lack atomistic resolution, particularly under nanoscale confinement where direct measurement becomes infeasible. Molecular dynamics (MD) simulations can bridge this gap; however, conventional classical force fields are limited by their simplified, fixed functional forms and empirical parameterization, whereas ab initio molecular dynamics (AIMD) achieves higher accuracy at the expense of severe computational cost and …

The Role Of Artificial Intelligence In Boosting Cybersecurity And Trusted Embedded Systems Performance: A Systematic Review On Current And Future Trends, Xiangyi Cheng, Ahmed Oun, Kaden Wince

Mechanical Engineering Faculty Works

As technology becomes increasingly interconnected, ensuring the security of cyber and embedded systems is critical due to escalating vulnerabilities and sophisticated cyber threats. Researchers are exploring artificial intelligence (AI) to improve security mechanisms, yet there is a lack of a comprehensive technical, AI-focused analysis detailing the integration of AI into existing security hardware and frameworks. To address this gap, this article systematically reviews 63 articles on AI in cybersecurity and trusted embedded systems. The reviewed articles are categorized into four application domains: 1) Intrusion Detection and Prevention (IDPS), 2) Malware Detection, 3) Industrial Control and Cyber-Physical Systems (CPS) and 4) …

Ultrasound Shear Wave Elastography: Development Of Tissue Models And Investigation Of Shear Wave Variability, Emily J. Miller

Dissertations, Master's Theses and Master's Reports

Ultrasound shear wave elastography (USWE) is an evolving and promising clinical tool for noninvasively measuring in vivo soft tissue biomechanical properties. Assumptions incorporated into the clinical workflow and technical limitations have created gaps between theoretical and clinically derived solutions. The heterogeneity of the fibrotic liver tissue, composition of the background, such as the presence of fatty liver tissue, and the preferred local orientation of the scarred fibrotic liver tissues embedded into the liver parenchyma, may contribute to the uncertainty in USWE measurements. This study aims to systematically investigate four cofounding factors (i.e., size, volume fraction, orientation of the fibrotic inclusions, …

Multi-Objective Monitoring Of Cvd Diamond Micro-Grinding Tools Using Acoustic Emission And Force Signals With Neural Network Optimization, Ahmed Elkaseer, Jianfei Jia, Bianbian Meng, Bing Guo, Jun Qin, Guicheng Wu, Huan Zhao, Zhenfei Guo, Qingyu Meng, Qingliang Zhao, Honghui Yao, Amr Monier

Mechanical Engineering

Micro-grinding has been widely used in aerospace and other industry, and its application was mainly the asymmetric microstructure. Chemical Vapor Deposition (CVD) diamond has drawn attention for its good wear resistance. However, the small diameter and high spindle speed may cause difficulties on the monitoring of the micro-grinding processes. In order to solve the mentioned problem, a novel multi-objective monitoring method of structured CVD diamond micro-grinding tool based on acoustic emission (AE) and force signals is presented in this study to achieve the high efficiency of the tool condition and grinding quality. The relationship between the grinding quality, tool condition, …

A Hybrid Data Processing, Computational Intelligence, And Complex Systems Modeling Approach For Describing And Predicting The Bitcoin Market, Oluwadamilare Akinpelu Omole

Doctoral Dissertations

"The Bitcoin market, like traditional financial markets, is a complex system with intricate interdependencies and nonlinear interactions among various market elements. This, coupled with the inherent uncertainty and high volatility present, makes predicting Bitcoin price movements difficult. The lack of understanding of the underlying market dynamics often results in significant losses for investors and traders. Existing studies have focused on the use of predictive models, which have not sufficiently captured the complexities of the market and cannot forecast extreme market events. This research endeavors to bridge this gap by combining data processing techniques, computational intelligence, and complex systems theory to …

Insider Threat Agent: A Behavioral Based Zero Trust Access Control Using Machine Learning Agent, Michael Fojude

College of Graduate Studies: Theses & Dissertations

Hybrid work, cloud adoption, and freely available AI‑enabled attack tools have exposed critical weaknesses in perimeter‑centric security. Current breach reports attribute more than one‑third of incidents to insider misuse or credential compromise, yet many organizations still depend on static Role‑ or Attribute‑Based Access Control that neither verifies intent continuously nor adapts to subtle behavioral change. This research addresses that gap by designing and validating a behavioral based Zero Trust Access Control (ZTAC) Agent. A five‑year enterprise log Dataset was extracted and cleansed to establish a high‑fidelity baseline of normal user behavior. Feature engineering captured temporal regularity (login sequence, session duration), …

Temporal Analysis Of Construction Safety Incidents In Southeastern U.S. Using Machine Learning Techniques, Mayowa O. Oladele

College of Graduate Studies: Theses & Dissertations

Construction safety incidents remain a significant concern, particularly in the Southeastern U.S. due to the high-risk nature of the industry. Analyzing patterns in these incidents can help improve safety practices and reduce accidents. Machine learning (ML) techniques were employed in this study to identify temporal patterns in construction safety incidents, aiming to enhance proactive safety management. The machine learning methods used in this research included logistic regression, decision trees, random forest, support vector machine (SVM), and K nearest neighbors (KNN).

The objective of the study was to analyze temporal trends in safety incidents and identify the most effective machine learningtechnique …

Real-Time Intelligent Parking Management In Smart Cities Using Internet Of Things, Genetic Algorithms, And Machine Learning, Mohammed Abo-Zahhad, Mohammed M. Abo-Zahhad

Mansoura Engineering Journal

Smart city parking systems face significant challenges related to real-time availability updates, security vulnerabilities in RFID-based access, and connectivity issues. To address these limitations, this paper proposes a comprehensive two-stage intelligent parking system that integrates Internet of Things (IoT), Genetic Algorithms (GAs), and Machine Learning (ML) techniques. The system utilizes sensor technologies, such as infrared sensors and ESP8266 controllers, combined with a mobile application to monitor and manage parking space occupancy in real-time efficiently. In the first stage, real-time parking availability is detected through sensor data transmitted to a cloud infrastructure that updates the user interfaces. The second stage employs …

Movie Genre Classification Using Script Texts, Michael Roman Cuomo

Electronic Theses and Dissertations

Genres are used to classify movies so that they can be grouped with others that have similar themes and structures. These classifications are categories created by humans. In the process of creating a movie, a script is often the first creation to write and share ideas about a topic. The script contains large amounts of text that is used to describe the dialog, setting and direction of the film. Although the script contains important information for the film, the amount of text can present a challenge for machine learning algorithms. Often in studies on film classification, if text is used, …

Detecting Anomalous Srf Cavity Behavior With Unsupervised Learning, Hal Ferguson, Jiang Li, Adam Carpenter, Chris Tennant, Dillon Thomas, Dennis Turner

Electrical & Computer Engineering Faculty Publications

We present an unsupervised learning framework for detecting anomalous superconducting radio-frequency (SRF) cavity behavior at the Continuous Electron Beam Accelerator Facility (CEBAF), emphasizing its initial performance and effectiveness. Key to the system’s success was the development of data acquisition systems (DAQs) that capture fast-sampled, information-rich signals, essential for detecting transient effects. The approach involves creating daily cavity-specific models using principal component analysis to handle variations in rf signal behavior and mitigate performance degradation from data drift. This unsupervised method eliminates the need for expensive labeling by continuously updating models with recent data. Deployed and operational for 3 months before a …

A Fast Framework For Generating Radioactive Mixture Spectra And Its Application To Remote High-Performance Mixture Identification, Chiman Kwan, Bulent Ayhan, Adam Stavola, Kazi Aminul Islam, Hongfang Zhang, Jiang Li

Electrical & Computer Engineering Faculty Publications

Remote detection of radioactive materials in mixtures using handheld or portal detectors remains a challenge because of factors such as low concentration, environmental interference, sensor noise, and other complications. This work introduces a fast framework for generating realistic mixture spectra. Moreover, we present mixture isotope identification using data generated by the fast framework. Researchers have examined a range of conventional and recent algorithms within the fields of machine learning and deep learning. An application to uranium enrichment-level prediction has been included. Extensive simulation experiments validated the efficacy of the proposed framework.

Data-Driven Gradient Optimization For Field Emission Management In A Superconducting Radio-Frequency Linac, S. Goldenberg, K. Ahammed, A. Carpenter, J. Li, R. Suleiman, C. Tennant

Electrical & Computer Engineering Faculty Publications

Field emission can cause significant problems in superconducting radio-frequency linear accelerators (linacs). When cavity gradients are pushed higher, radiation levels within the linacs may rise exponentially, causing degradation of many nearby systems. This research aims to utilize machine learning with uncertainty quantification to predict radiation levels at multiple locations throughout the linacs and ultimately optimize cavity gradients to reduce field emission-induced radiation while maintaining the total linac energy gain necessary for the experimental physics program. The optimized solutions show over 40% reductions for both neutron and gamma radiation from the standard operational settings.

High-Fidelity Soh Prediction In Lithium-Ion Batteries Using Hybrid Ml Networks, Shafiyee Islam, Gon Namkoong

Electrical & Computer Engineering Faculty Publications

Accurate and efficient prediction of lithium-ion battery state of health (SOH) is critical for ensuring reliability in electric vehicles, grid storage, and aerospace systems. Traditional SOH estimation methods often struggle with nonlinear degradation behaviors and lack sensitivity to subtle electrochemical signals, limiting their real-world deployment. To address these challenges, this study examines hybrid deep learning models that integrate differential capacity (dQ/dV) analysis to enhance predictive accuracy. Four hybrid architectures - hybrid CNN-LSTM multihead, CNN extractor for LSTM, DNN-LSTM, and DNN Bi-LSTM - were developed and evaluated using the NASA randomized battery usage dataset, offering a realistic benchmark under diverse operational …

Advances In Battery Modeling And Management Systems: A Comprehensive Review Of Techniques, Challenges, And Future Perspectives, Seyed Saeed Madani, Yasmin Shabeer, Ananthu Shibu Nair, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, Shi Xue Dou, Khay See, Saad Mekhilef, Françios Allard

Electrical & Computer Engineering Faculty Publications

Energy storage systems (ESSs) and electric vehicle (EV) batteries depend on battery management systems (BMSs) for their longevity, safety, and effectiveness. Battery modeling is crucial to the operation of BMSs, as it enhances temperature control, fault detection, and state estimation, thereby maximizing efficiency and preventing malfunctions. This paper thoroughly examines the most recent advancements in battery and BMS modeling, including data-driven, thermal, and electrochemical methods. Advanced modeling approaches are explored, including physics-based models that incorporate mechanical stress and aging effects, as well as artificial intelligence (AI)-driven state estimation. New technologies that facilitate data-driven decision-making, real-time monitoring, and simplified systems include …

Ai-Based Steganography Method To Enhance The Information Security Of Hidden Messages In Digital Images, Nhi Do Ngoc Huynh, Jiajun Jiang, Chung-Hao Chen, Wen-Chao Yang

Electrical & Computer Engineering Faculty Publications

With the increasing sophistication of Artificial Intelligence (AI), traditional digital steganography methods face a growing risk of being detected and compromised. Adversarial attacks, in particular, pose a significant threat to the security and robustness of hidden information. To address these challenges, this paper proposes a novel AI-based steganography framework designed to enhance the security of concealed messages within digital images. Our approach introduces a multi-stage embedding process that utilizes a sequence of encoder models, including a base encoder, a residual encoder, and a dense encoder, to create a more complex and secure hiding environment. To further improve robustness, we integrate …

Land Target Detection Algorithm In Remote Sensing Images Based On Deep Learning, Wenyi Hu, Xiaomeng Jiang, Jiawei Tian, Shitong Ye, Shan Liu

Electrical & Computer Engineering Faculty Publications

Remote sensing technology plays a crucial role across various sectors, such as meteorological monitoring, city planning, and natural resource exploration. A critical aspect of remote sensing image analysis is land target detection, which involves identifying and classifying land-based objects within satellite or aerial imagery. However, despite advancements in both traditional detection methods and deep-learning-based approaches, detecting land targets remains challenging, especially when dealing with small and rotated objects that are difficult to distinguish. To address these challenges, this study introduces an enhanced model, YOLOv5s-CACSD, which builds upon the YOLOv5s framework. Our model integrates the channel attention (CA) mechanism, CARAFE, and …

Scoping Review Of Machine Learning Techniques In Marker-Based Clinical Gait Analysis, Kevin N. Dibbern, Maddalena G. Krzak, Alejandro Olivas, Mark V. Albert, Joseph J. Krzak, Karen M. Kruger

Biomedical Engineering Faculty Research and Publications

The recent proliferation of novel machine learning techniques in quantitative marker-based 3D gait analysis (3DGA) has shown promise for improving interpretations of clinical gait analysis. The objective of this study was to characterize the state of the literature on using machine learning in the analysis of marker-based 3D gait analysis to provide clinical insights that may be used to improve clinical analysis and care. Methods: A scoping review of the literature was conducted using the PubMed and Web of Science databases. Search terms from eight relevant articles were identified by the authors and added to by experts in clinical gait …

Delivery Of Medical Supplies To Remote Locations Via Unmanned Aerial Vehicles: Approaches, Challenges, And Solutions, Meshari Aljohani, Ravi Mukkamala, Stephanie Olariu

Computer Science Faculty Publications

Unmanned Aerial Vehicles (UAVs) are becoming more important in improving healthcare logistics, in particular due to their cost effectiveness, minimized risk, and versatile operational capabilities. This study explores the deployment of autonomous UAVs to deliver medical supplies to remote areas. Advances in ledger technology, smart contracts, and machine learning have transformed tasks previously managed by human teams or manually controlled UAVs into fully autonomous missions. We present a comprehensive analysis of the challenges and initial solutions vital for the effective use of autonomous UAVs in the delivery of medical supplies. In addition, we propose a machine-learning model to optimize UAV …

Human Perception Of Ai Capabilities At Classifying Perturbed Roadway Signs, Katherine R. Garcia, Jing Chen, Yanru Xiao, Scott Mishler, Cong Wang, Bin Hu

Computer Science Faculty Publications

Artificial Intelligence (AI) is crucial to numerous functions required for driving automation systems, including the computer vision techniques used to detect the roadway environment and make real-time decisions. However, the images used as inputs to the AI system may be maliciously perturbed, or manipulated, causing the AI system to make an incorrect classification. In this study, we examined humans’ perception of the AI’s computer vision capability of classifying various road sign images, including the original images, images with two different types of malicious attacks, and images that are scrambled randomly at the pixel level. Our results showed that participants rated …

Benchmarking Batch-Effect Correction Methods Towards The Construction Of A Triple-Negative Breast Cancer Cell Atlas, Peter Scheible, Amy H. Tang, Jing He, Jiangwen Sun

Computer Science Faculty Publications

Triple-negative breast cancer (TNBC) requires detailed cellular mapping given its aggressive nature, immense tumor heterogeneity and genetic diversity. We integrated 156,794 cells from six scRNA-seq datasets—including tumors, metastases, and cell lines—to build a TNBC scRNA cell atlas, focusing on batch effect mitigation while maintaining biological and molecular details. Preprocessing f ilters noise, normalizes data, and leverages PCA for integration readiness. We utilized scANVI, a semi-supervised tool, to align datasets, preserving TNBC’s complex tumor heterogeneity via marker annotations [1]. UMAPs demonstrate biological clustering in integrated data, contrasted with datasetdriven unintegrated patterns. Assessments verifying effective batch correction. This method aligns with NASA’s …

Coldstartcpi: Induced-Fit Theory-Guided Dti Predictive Model With Improved Generalization Performance, Qichang Zhao, Haochen Zhao, Linyuan Gao, Kai Zheng, Yajie Li, Qiao Ling, Jing Tang, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Predicting compound-protein interactions (CPIs) plays a crucial role in drug discovery. Traditional methods, based on the key-lock theory and rigid docking, often fail with novel compounds and proteins due to their inability to account for molecular flexibility and the high sparsity of CPI data. Here, we introduce ColdstartCPI, a framework inspired by induced-fit theory, which leverages unsupervised pre-training features and a Transformer module to learn both compound and protein characteristics. ColdstartCPI treats proteins and compounds as flexible molecules during inference, aligning with biological insights. It outperforms state-of-the-art sequence-based models, particularly for unseen compounds and proteins, and shows strong generalization capability …

High-Frequency Gold Price Forecasting: Optimizing Multi-Layer Perceptron With Genetic Algorithm, Vrtagic Sabahudin, Fatih Dogan

Materials Science and Engineering Faculty Research & Creative Works

Accurately forecasting gold price actions is critical in financial markets due to gold's role as a safe-haven asset. This paper addresses the challenge of forecasting gold prices by applying a Genetic Algorithm (GA) with a Multi-Layer Perceptron (MLP) model. The research exploits historical financial data from various instruments, including gold futures, Bitcoin, and key currency pairs, to improve prediction accuracy. By optimizing the MLP's hyper parameters through GA, the model efficiently captures complex relationships in high-frequency data, achieving a remarkable R² score of 0.9993. This level of precision demonstrates the model's potential for providing actionable insights for traders and investors. …

All-Solid-State Sodium-Ion Batteries: A Leading Contender In The Next-Generation Battery Race, Rui-Jie Zhu, Ze-Chen Li, Wei Zhang, Akira Nasu, Hiroaki Kobayashi, Masaki Matsui

Journal of Electrochemistry

All-solid-state lithium-ion batteries (LIBs) using ceramic electrolytes are considered the ideal form of rechargeable batteries due to their high energy density and safety. However, in the pursuit of all-solid-state LIBs, the issue of lithium resource availability is selectively overlooked. Considering that the amount of lithium required for all-solid-state LIBs is not sustainable with current lithium resources, another system that also offers the dual advantages of high energy density and safety— all-solid-state sodium-ion batteries (SIBs) —holds significant sustainable advantages and is likely to be the strong contender in the competition for developing next-generation high-energy-density batteries. This article briefly introduces the research …