Biomedical Informatics Commons^™

Ai-Driven Biomarker Discovery & Progression Modeling For Precision Diagnosis Of Glaucoma, Cheng Huang

Computer Science and Engineering Theses and Dissertations

This dissertation presents a comprehensive study on the integration of artificial intelligence (AI) for glaucoma diagnosis and retinal image analysis. Leveraging multimodal imaging data including fundus photography, Optical Coherence Tomography Optical Coherence Tomography (OCT) and Optical Coherence Tomography Angiography (OCTA), the research develops a suite of deep learning frameworks designed to detect early glaucomatous changes with high precision, robustness, and interpretability. A series of novel architectures are introduced, spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models, all designed to enhance diagnostic accuracy and generalizability across diverse populations. To facilitate reproducible and scalable ophthalmic AI research, this work …

A Unified Pipeline For Network-Based Gene Pattern Discovery, Siddhartha Reddy Pullannagari, Sharlee Climer

Undergraduate Research Symposium

Large-scale genetic datasets from diverse diseases, including cancer and neurodegenerative disorders such as Alzheimer’s disease, provide unprecedented opportunities to study disease pathogenesis and generate hypotheses for drug discovery. However, identifying meaningful genetic interaction patterns within these datasets remains challenging due to combinatorial relationships amongst genes and heterogeneous biological underpinnings across subtypes. This project systematically analyzes a diverse collection of omics datasets (e.g., GSE44076, GSE97810, GSE127711, GSE112679) obtained from the NCBI Gene Expression Omnibus (GEO), spanning multiple biological conditions and data types. We use a unified computational pipeline designed to handle variation in dataset size, structure, and context. The steps in …

Agentic Scientific Machine Learning For Autonomous Model Discovery In Systems Pharmacology, Nazanin Ahmadi, George Karniadakis

Biology and Medicine Through Mathematics Conference

No abstract provided.

Robust Non-Invasive Cardiac Index Prediction Via Feature Integration And Data-Augmented Neural Networks, Chih-Hao Chang, Mei-Ling Chan, Yu-Hung Fang, Po-Lin Huang, Tsung-Yi Chen, Tsun-Kuang Chi, I Elizabeth Cha, Tzong-Rong Ger, Kuo-Chen Li, Shih-Lun Chen, Liang-Hung Wang, Jia-Ching Wang, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Concurrent with the rising consumption of ultra-processed, high-calorie diets and the decline in physical activity, obesity and related cardiovascular conditions among young adults have continued to increase, becoming an important global public health concern. This study integrates non-invasive Internet of Things (IoT) sensing devices, including the TERUMO ES-P2000 blood pressure monitor (Terumo Corp., Tokyo, Japan) and the PhysioFlow PF07 Enduro cardiac hemodynamic analyzer (Manatec Biomedical, Poissy, France), with an artificial neural network (ANN) for cardiac index (CI) prediction. Through appropriate data preprocessing and model training strategies, the generalization ability and stability of the proposed CI prediction model were significantly enhanced. …

Re-Purposing Pre-Existing Tilapia Aquaculture Open-Design System For Zebrafish Biomedical Research Purposes, Luke Cantu, David Sierra, Skyleigh Curtis, Maya Avila

ATU Scholars Symposium

Title: Re-purposing pre-existing tilapia open-design aquaculture systems for zebrafish biomedical research purposes.

Background: Zebrafish (Danio rerio) models are gaining popularity in biomedical research; however, the high infrastructure cost, at approximately $20,000 per unit, is a significant hurdle for primary undergraduate institutions (PUIs) establishing zebrafish facilities. This study assesses if repurposing existing tilapia open-design aquaculture systems could be a cost-effective method for zebrafish facility establishment.

Methods: Between November-2025 to February-2026, the study used a pre-existing tilapia aquaculture open-design system with personnel modified outlet filters. The water quality of this system was monitored and recorded. The study compared the stabilization phase or …

A Specification-Driven Framework For Self-Supervised Learning In Specialized Vision Domains, Mahmut S. Gokmen

Theses and Dissertations--Computer Science

Self-supervised learning (SSL) has emerged as a principled approach to visual representation learning that derives supervisory signal directly from unlabeled data, enabling foundation models to be trained at scale without manual annotation. Deployments in medical imaging and biometric recognition have demonstrated the potential of this paradigm, yet the assumptions that make SSL effective on natural image benchmarks fail systematically in specialized domains. Generic SSL pipelines encode a tacit assumption that the most informative correspondence is spatial proximity within a single acquisition. In specialized domains this assumption breaks at the level of the data-generating process: the signal that carries domain-specific information …

Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari

Bioengineering Theses

This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …

Hyperglycemia Detection From Sigle - Lead Ecg Using A Hybrid Cnn & Transformer Model, Adam Ayomikun Ogunjembola

Graduate Theses, Dissertations, and Problem Reports (ETD)

Abstract
Hyperglycemia Detection from Single-Lead ECG using a Hybrid CNN & Transformer Model
Adam Ogunjembola

Diabetes Mellitus is known as high blood glucose. This high blood glucose level happens when the body has a problem with producing or using insulin. Insulin is a very important hormone that the pancreas makes to control how much glucose gets into the bloodstream and cells. Diabetes Mellitus has an effect on the body if it is not treated, such as damaging the blood vessels and nerves which can lead to stroke, kidney failure, heart attack and permanent loss of vision. Since people with diabetes …

Towards The Performance Characterization Of A Robotic Multimodal Diagnostic Imaging System, George Papaioannou, Christos Mitrogiannis, Mark Schweitzer, Nikolaos Michailidis, Maria Pappa, Pegah Khosravi, Apostolos Karantanas, Sean Starling, Christian Ruberg

Publications and Research

Characterizing imaging performance requires a multidisciplinary approach that evaluates various interconnected parameters, including dosage optimization and dynamic accuracy. Radiation dose and dynamic accuracy are challenged by patient motion that results in poor image quality. These challenges are more prevalent in the brain/cardiac pediatric patient imaging, as they relate to excess radiation dose that may be associated with various complications. Scanning vulnerable pediatric patients ought to eliminate anesthesia due to critical risks associated in some cases with intracranial hemorrhages, brain strokes, and congenital heart disease. Some pediatric imaging, however, requires prolonged scanning under anesthesia. It can often be a laborious, suboptimal …

Toward The Application Of Natural Language Processing In Electronic Health Record Analysis For Taxonomy Development, Latoya Mcdonald

All Dissertations

Electronic health records (EHRs) are pivotal resources for nurse practice because they increase the timeliness and reliability of patient information at the point of care and support access by multiple healthcare providers and the individual patients themselves. However, it is widely recognized that data extraction from EHRs is challenging due to the variability in the language used in clinical care notes and the lack of standardized terminology across healthcare systems. The broad objective of this dissertation is to develop taxonomy-based classification models for nursing care by applying feature engineering approaches to EHRs that include nursing care of ostomy patients following …

Enhanced And Interpretable Prediction Of Multiple Cancer Types Using A Stacking Ensemble Approach With Shap Analysis, Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Zhongming Zhao

Faculty, Staff and Student Publications

Background: Cancer is a leading cause of death worldwide, and its early detection is crucial for improving patient outcomes. This study aimed to develop and evaluate ensemble learning models, specifically stacking, for the accurate prediction of lung, breast, and cervical cancers using lifestyle and clinical data.

Methods: 12 base learners were trained on datasets for lung, breast, and cervical cancer. Stacking ensemble models were then developed using these base learners. The models were evaluated for accuracy, precision, recall, F1-score, AUC-ROC, MCC, and kappa. An explainable AI technique, SHAP, was used to interpret model predictions.

Results: The stacking …

Securing Biometric Data, Alyssa F. Carroll

Cybersecurity Undergraduate Research Showcase

Biometric data has been widely adopted across various sectors, including digital identity, artificial intelligence (AI), border control, digital wallets, and national identification systems. While biometric identifiers—such as fingerprints, retina scans, and facial recognition—offer reliable and convenient authentication, they also raise significant concerns regarding privacy and security. This paper examines how biometric data is stored, the vulnerabilities it faces, and the most effective methods for safeguarding it. By highlighting the critical importance of biometric data protection, this study reviews current research on approaches, strategies, and policies that enhance security while preserving the functionality and efficiency of biometric systems.

Development And Analysis Of The Kinematic-Dynamic Model Of The Rehabilitation Exoskeleton System, Umidjon Abdumutalipovich Takabaev, Zafar Botirovich Juraev

Technical science and innovation

Designing modern rehabilitation exoskeleton systems requires a comprehensive study of human-machine interactions. In this process, creating kinematic and dynamic mathematical models of the system is extremely important. In this paper, we develop mathematical models that describe rehabilitation exoskeleton systems' kinematic and dynamic properties. Based on the Denavit-Hartenberg method we construct kinematic model of the exoskeleton system. The method gave us to determine the coordinate system for each joint. Furthermore, we also study the motion range of joints of the exoskeleton. Modeling the dynamic properties of the system performed with the second-order Lagrange equation. The exoskeleton construction consisting of knee, thigh, …

Evaluating Lidar Technology In Iphone Mobiles For 2d Mapping Applications, Nasr Mohammady Saba, Salem Salama Saleh

Journal of Engineering Research

Abstract- LiDAR (Light Detection and Ranging) technology has revolutionized mapping applications, offering enhanced precision and accuracy in spatial data collection. The integration of LiDAR technology in the latest iPhone models, beginning with the iPhone 12 Pro, has introduced new capabilities for 2D data measurement and plan creation directly on the mobile device. The iPhone 12 Pro and 12 Pro Max models support LiDAR techniques within their mobile phone cameras, enhancing the performance of various applications such as Measurements and Photos. LiDAR operates by emitting pulsed light waves into the surrounding space, which bounce off nearby objects and return to the …

Experimental And Numerical Investigation For Optimum Design Of Hydraulic Steel Gates, Basma Hassan Mohamed Eng, Ahmed Mohamed Anwer Dr, Hanan Eltobgy Prof., Gamal Helmy El-Saeed Prof

Journal of Engineering Research

Conventionally, steel gates are widely used in hydraulic structures for their superior mechanical properties in sustaining hydrostatic pressure. Maintenance and operational costs should be considered while studying the feasibility of these gates. In the current research, three prototype steel gates with different configurations were prepared and examined experimentally. The three gates have the same surface dimensions of (width x height) equal to (1.0 x 1.25 m). The first steel gate represents a typical traditional gate made of skin plate and stiffened laterally using standard steel channels and will be kept for comparison. The second gate represents a standard thicker plate …

Performance And Emissions Characteristics Of Multi-Cylinder Direct Injection Diesel Engine Fuelled With Diesel/Biodiesel And Toluene Additives, Hagar Alm-Eldin Bastawissi, Medhat Elkelawy Prof. Dr. Eng., Mohammed Osama Elsamadony Dr. Eng., Moustafa Ghazaly Eng.

Journal of Engineering Research

This study explores the impact of using a diesel, biodiesel, and toluene additive fuel blend in a multi-cylinder direct injection diesel engine, focusing on both performance and emissions characteristics. Biodiesel, made from renewable sources like vegetable oils, is often added to diesel to reduce reliance on fossil fuels and improve combustion due to its higher oxygen content. In this work, a 45% biodiesel blend (B45) led to significant reductions in particulate matter (PM) emissions by up to 40% compared to conventional diesel. Additionally, carbon monoxide (CO) and hydrocarbon (HC) emissions decreased by up to 30% and 25%, respectively, due to …

Effect Of Dual-Fuelled Cng And Gasoline On Spark Ignition Engine Performance And Emissions Behaviors At Different Loads, Medhat Elkelawy Prof. Dr, Eng., M.M. Bassuoni Prof. Dr., Hagar Alm-Eldin Bastawissi, Saied I. Haiba Eng.

Journal of Engineering Research

Engine emissions are one of numerous factors that have detrimentally affected the environment, such as global warming, which is the result of growing exhaust gases, practically carbon dioxide (CO2). These emissions have substantially influenced researchers to develop strategic initiatives to minimize the carbon contents of fuels. The purpose of this research is to investigate the characteristics of internal combustion (SI) engines fueled by gasoline and compressed natural gas (CNG) blends. The experiments are performed using a HONDA 4-stroke, single-cylinder, and air-cooled SI engine. Five CNG concentrations are evaluated, the concentrations range from 0.5 to 2.5 L/min with a 0.5 L/min …

A Quantitative Analysis Of The Commercial-Additive Effects On Diesel Engine Combustion And Emissions Characteristics, Medhat Elkelawy Prof. Dr. Eng., Hagar Alm-Eldin Bastawissi Prof. Dr. Eng., E. A. El Shenawy Prof. Dr., Mahmoud Mohamed Soliman Mahmoud Mohamed Mahmoud Soliman

Journal of Engineering Research

Petroleum fuel prices fluctuate in response to global political and economic issues. Government regulations should be followed when it comes to engine emissions, as these dangerous pollutants have a negative impact on the environment. One such effect is global warming, which raises global temperatures. The purpose of this study is to develop the additives for use as a fuel mix with diesel fuel, which will be used to feed the diesel engine of a single cylinder, four strokes. The engine will be tested experimentally with varying loads at fixed speed of 1500 rpm, using blends of [(5% PRETSONE additive + …

Design And Implementation Of A Low-Cost Educa-Tional Robot For Engineering Curriculums, Diana Refaat Henry Jacob, Ashraf Mohamed Hafez, Mohamed Tarek Elawa

Journal of Engineering Research

The role of educational robots is becoming increasingly important. Many commercial educational robots differ in their abilities and price. In general, the cost of these robots presents the main cause of their limited use in the teaching process, especially in countries with limited financial resources. This work attempts to solve this problem by designing and implementing an educational robot with a limited budget. The robot was initially intended to serve higher education students' needs, especially in engineering curriculums but can be extended to other application areas. This work presents robot hardware functional blocks, mechanical struc-ture design, and 3D printing implementation. …

A Greening The Diesel: Vegetable Oil Biodiesel Blends For Cleaner Emissions And Improved Direct Injection Diesel Engine Performance, Medhat Elkelawy Prof. Dr, Eng., Hagar Alm-Eldin Bastawissi, E. A. El Shenawy Prof. Dr., Mustafa Mohamed Ouda

Journal of Engineering Research

In this study, we conducted comprehensive experiments to assess and compare the performance of pure diesel fuel against biodiesel produced from corn oil in various blend ratios (15/85, 30/70, 45/55, and 60/40) in a conventional four-stroke, direct-injection diesel engine, fuel is injected directly into the combustion chamber at the end of the compression stroke, allowing for efficient combustion and power generation over four distinct phases: intake, compression, power, and exhaust. Each fuel blend was tested at an engine speed of 16,000 rpm across different load conditions (low, medium, and high). Key performance metrics, including volumetric fuel consumption, exhaust smoke, and …

Novel Electrophysiological Biomarkers In Pediatric Drug Resistant Epilepsy And Genetic Epilepsy Syndromes, Sakar Rijal

Bioengineering Dissertations - Archive

Pediatric epilepsies, particularly those that are drug-resistant or genetically driven, represent some of the most complex neurological disorders encountered in childhood. Central to their pathophysiology is a disruption in the delicate balance between cortical excitation and inhibition (E/I), often resulting from impaired GABAergic interneuron function. This imbalance manifests as aberrant network dynamics and altered neural oscillations, giving rise to seizures and long-term cognitive impairments. In this thesis, we developed a translational framework to identify electrophysiological biomarkers that (i) assess cortical E/I imbalance and (ii) map epileptogenic zones, with the aim of enhancing diagnosis, guiding surgical planning, and informing therapeutic monitoring …

Neurotensin Regulates Primate Ovulation Via Multiple Neurotensin Receptors, Andrew C. Pearson, Jessica S. Miller, Hannah J. Jensen, Ketan Shrestha, Thomas E. Curry Jr., Diane M. Duffy

Department of Biomedical and Translational Sciences Faculty Publications

Neurotensin (NTS), a small neuropeptide, was recently established as a key paracrine mediator of ovulation. NTS mRNA is highly expressed by granulosa cells in response to the luteinizing hormone (LH) surge, and multiple NTS receptors are expressed by cells of the ovulatory follicle. To identify the role of NTS receptors NTSR1 and SORT1 in ovulation in vivo, the dominant follicle of cynomolgus macaques (Macaca fascicularis) was injected with either vehicle control, the general NTS receptor antagonist SR142948, the NTSR1-selective antagonist SR48692, or the SORT1-selective antagonist AF38469. Human chorionic gonadotropin (hCG) was then administered to initiate ovulatory events. …

Enhancing Human Aging Proteins Detection Based On Bio-Structural Deep Clustering Network, Sondos M. Hammad, Mohamed Talaat Saidahmed, Elsayed A. Sallam, Reda Elbasiony

Journal of Engineering Research

Aging is a major risk factor for numerous chronic diseases and declines in physical and cognitive functions, making it a critical focus of research. Identifying biomarkers that signify biological aging is crucial for developing interventions that can potentially delay age-related diseases. Among these biomarkers, human aging proteins are of significant interest. However, laboratory experiments to discover aging proteins are complex, costly, and time-consuming. Often focusing on single proteins at a time. To address this challenge, we used a clustering algorithm to detect potential human aging proteins. This approach aims to aid biologists in their experimental efforts. Deep clustering, particularly simultaneous …

Evaluation Of Virtual Distance Learning And Teaching In The Architectural Design Studio Experience Of Professors And Students Of The College Of Architecture And Planning - Qassim University - Kingdom Of Saudi Arabia., Abdulaziz Ibrahim Alhrabi

Journal of Engineering Research

The paper deals with the evaluation of distance learning of the architectural design studio during the Corona pandemic, and the extent to which distance learning and teaching were achieved between the professor and the student. The paper aims to share and evaluate the experience of distance learning and teaching of the architectural design studio, in the College of Architecture and Planning at Qassim University. The research problem is that the Corona virus crisis generates many ideas for educational programs and media, but there is a deficiency in knowledge of many programs that achieve the continuity of the educational process remotely, …

Optimal Site Layout Planning For Construction Projects Over Waterways, Rana M. Azzam, Nashwa Mohamed Yossef Prof, Adel I. Eldosouky Prof

Journal of Engineering Research

Construction site layout planning is an important part of a project's success. An effective construction layout plan can enhance the performance of the construction process by improving productivity, ensuring safety, and reducing costs. Given the importance of bridges over a waterway and the lack of interest in previous research for planning a construction site over a waterway. This paper concentrates on the problems of site planning for such projects, including the problem of limited site space. The study indicated that constructing an offshore terminal is one of the primary requirements for projects with limited space being carried out on a …

Decision-Making In Diagnosing Heart Failure Problems Using Dual Hesitant Fuzzy Sets, Manar Mohamed Omran, Reham Abdel-Aziz Abo-Khadra

Journal of Engineering Research

In recent decades, several types of sets, such as fuzzy sets, interval-valued fuzzy sets, intuitionistic fuzzy sets, interval-valued intuitionistic fuzzy sets, type 2 fuzzy sets, type n fuzzy sets, and hesitant fuzzy sets, have been introduced and investigated widely. In this paper, we propose dual hesitant fuzzy sets (DHFSs), which encompass fuzzy sets, intuitionistic fuzzy sets, hesitant fuzzy sets, and fuzzy multi-sets as special cases. Then we investigate the basic operations and properties of DHFSs. We also discuss the relationships among the sets mentioned above, and then propose an extension principle of DHFSs. Additionally, we give an example to illustrate …

Developing Paths In Areas Of Distinguished Value Between Preservation And Extinction (A Case Study Of The Railway Axis In The Maadi Area), Kamal Mahmoud Elgabalawy

Journal of Engineering Research

Abstract: proportion of the place, and thus the loss of the distinctive general character of the area, which leads to its extinction. These areas are of distinguished value, with all the thought and culture they carry of society over time. Among the areas classified as having distinguished value is the Maadi suburb, which is located in the south of Cairo Governorate, where boundaries and foundations for preserving them have been set through the Central Administration for Studies, Research, and Policies of the National Coordination Organization. The Ministry of Culture, approved by the Supreme Council for Planning and Urban Development by …

Review Of Wood Drying Technologies, Mohamed Salah Elmetwaly, Lotfy Hassan Rabie Saker, Mohamed Sameh Salem

Journal of Engineering Research

Abstract- This article provides a comprehensive review of drying optimization in data centers by examining the limitations of drying methods and discussing advances proposed by scientists through whom we can provide a comparison between different drying systems with an emphasis on improving energy efficiency and thermal performance. Wood drying under atmospheric pressure has many advantages, including the ability to dry at lower temperatures (by reducing the likelihood of some drying defects), significantly reduced drying times, color preservation, increased energy efficiency, better control of volatile organic compound emissions, and the ability to dry very large cross sections. Previous studies have achieved …

"Towards A Methodology For Studying The Impact Of Integrating Motion Systems In The External Envelope Of A Building On Natural Lighting Inside The Building– (An Applied Study On A Government School In Greater Cairo)", Nashwa Youssif

Journal of Engineering Research

يدرك المصمم ما للعناصر البيئية ولا سيما الإضاءة الطبيعية من دور فاعل في الوصول إلى تصميم ناجح يحقق أفضل أداء إستخدامي، فالإضاءة الطبيعية تذهب إلى صميم عمل المعماري فيستعين بها للإيحاء بشكل الفراغات ولونها وملمس سطوحها.

وهناك العديد من الأساليب الحديثة التي تساعد المعماري علي إتخاذ قراراته التصميمية الخاصة بتصميم المبنى وكيفية الإستفادة من الإضاءة الطبيعية داخل المباني، وهذه الأساليب تهدف إلى زيادة إحترام البيئة وتفترض تحسينات في النظم البيئية من العزل الحراري وإستغلال مصادر الطاقة الطبيعية والإهتمام بنظم الإضاءة الطبيعية والمواد البنائية.

وتعد تقنية دمج الأنظمة الحركية بالغلاف الخارجي للمبنى مع الإستفادة من الإضاءة الطبيعية داخل هذا …

The Bioremediation Effect Of Microalgae On Wastewater: A Green Technology Approach, Mohamed Ahmed Reda Hamed Dr, Marwa Abdelfattah Abdallah Dr

Journal of Engineering Research

The present study lays an emphasis on the microalgae-based for simultaneous wastewater bioremediation using Chlorella vulgaris and Micrococcus luteus mixed algal cultures to remove its constituent pollutants, amazing green technology guarantees benefits with the decrease in the formation of dangerous solid sludge. Ten days of fully monitoring laboratory experimental program were performed in batch cultures to investigate the effect of various dominant mixing ratios for attaining wastewater concentrations and different governing temperature ranges on the performance of microalgae treatment. The results revealed that there is a significant impact of both wastewater concentrations and temperature treatment conditions on the capability of …