Engineering Commons^™

A Joint Geometric Topological Analysis Network (Jgta-Net) For Detecting And Segmenting Intracranial Aneurysms, Xinyue Zhang, Zonghan Lyu, Yang Wang, Bo Peng, Jingfeng Jiang

Michigan Tech Publications

Objective: The rupture of intracranial aneurysms leads to subarachnoid hemorrhage. Detecting intracranial aneurysms before rupture and stratifying their risk is critical in guiding preventive measures. Point-based aneurysm segmentation provides a plausible pathway for automatic aneurysm detection. However, challenges in existing segmentation methods motivate the proposed work. Methods: We propose a dual-branch network model (JGTANet) for accurately detecting aneurysms. JGTA-Net employs a hierarchical geometric feature learning framework to extract local contextual geometric information from the point cloud representing intracranial vessels. Building on this, we integrated a topological analysis module that leverages persistent homology to capture complex structural details of 3D objects, …

Predicting Seizure Onset Zones From Interictal Intracranial Eeg Using Functional Connectivity And Machine Learning, Jared Pilet, Scott A. Beardsley, Chad Carlson, Christopher T. Anderson, Candida Ustine, Sean Lew, Wade Mueller, Manoj Raghavan

Biomedical Engineering Faculty Research and Publications

Functional connectivity (FC) analyses of intracranial EEG (iEEG) signals can potentially improve the mapping of epileptic networks in drug-resistant focal epilepsy. However, it remains unclear whether FC-based metrics provide additional value beyond established epilepsy biomarkers such as epileptic spikes and high-frequency oscillations (HFOs). Using interictal iEEG data from 26 patients, we estimated FC across eight frequency bands (4–290 Hz) using amplitude envelope correlation (AEC) and phase locking value (PLV). From the resulting FC-matrices, we estimated two graph metrics each to derive 32 FC-based features. We also extracted features related to spikes, HFOs, and power spectral densities (PSD). A trained support …

Developments On Abbreviations Towards Machine Reading Comprehension, Sing Choi

UNLV Theses, Dissertations, Professional Papers, and Capstones

Machine reading comprehension is a critical step in development of applications that require the semantic understanding of human speech-to-text driven work. Many devices such as smart home appliances like the Amazon Echo Dot, Google Home, or smart assistants like Apple Siri or Microsoft Cortana are examples of these applications. The comprehension task involves a deeper understanding and recognition of named entities such as person names, locations, medicals codes, quantities, abbreviations, and acronyms in speech or text data. In this dissertation, we explore and extend the different approaches and techniques in modern research that tackles the problem of recognition and definition …

A Framework For Establishing An Automated Traffic Violation Detection System In New Assiut City Using Ordinary Cctv Units, Mahmoud Owais, Ali Shehata, Abdou Shaband, Ghada S. Moussa

Mansoura Engineering Journal

Violating traffic rules in transport networks is a genuine concern for operators as it is one of the most important causes of fatal accidents. With the increasing number of residents in the new cities in the Arab Republic of Egypt, and the incompleteness of the transportation system in those cities, including traffic signs, light signals, and control points, the possibility of committing such violations increases. The study aims to propose the framework for establishing an intelligent monitoring system in the new city of Assiut consisting of high-resolution cameras optimally distributed on the traffic network points in the city. They will …

Fff Process Parameter Identification With Machine Learning Models, Owen Davis Smith

Honors Theses

Additive manufacturing (AM) has seen increasing popularity in recent times, owing to its efficiency and high speeds, particularly with processes such as Fused Filament Fabrication (FFF). Input process parameters have large impacts on the final part. Incomplete process parameters, which can occur for a variety of reasons, make tasks such as replicating AM studies difficult. A machine learning model can be trained on in-situ layer-wise images collected during a print to combat this issue, predicting process parameters with sufficient data. In this study, two parameters were tested: infill pattern orientation and extrusion width. Twelve parts were produced per parameter and …

Improvement Of Hanford Waste Vitrification Algorithms With Machine Learning, Uncertainty Quantification, And Gradient-Based Optimization, Lagrande L. Gunnell

Theses and Dissertations

Over 200 million liters of nuclear waste is stored in tank farms in Hanford, Washington, USA. An ongoing effort to immobilize non-solid nuclear waste is through waste vitrification, where waste is mixed and melted with glass-forming chemicals (GFCs) to form a waste glass. Algorithms to determine the ideal mixing recipes are formalized as constrained optimization problems to maximize waste loading in the glass product, with constraints on several properties of the glass melt and final product. These properties are on the glass melt, such as viscosity, electrical conductivity, and corrosion rates, as well as the final glass product, such as …

Computer Vision In Soccer: Yolov11 Analytics Engine For Quantifying Game Strategy, Connor S. Maurer

Data Science Undergraduate Honors Theses

Single-shot object detection capabilities significantly reduce computational overhead for real-time computer vision in sports analytics at 60 FPS. YOLO11’s lightweight CNN gives promising accuracy while meeting the low-latency demand of dynamic soccer matches. As data-driven approaches take over the sport of soccer, efficient player tracking systems become critical for informing coach’s strategies. I prototype the ETL (Extract, Transform, Load) process of data collected from a single- shot detection program and evaluate its viability for estimating player fatigue. YOLO11 detects players, the ball, and other characteristics, with the output transformed by homography to estimate the positions in the real world. These …

Expressive And Interpretable User Engagement Prediction Using Multivariate Survival Processes, Akshay Aravamudan

Theses and Dissertations

The ability to characterize how information diffuses online is of paramount importance to stakeholders that are interested in tasks such as proposing solutions for mitigating and countering dis/misinformation, predicting user engagement of content in social media, planning marketing campaigns to roll-out products and planning dissemination of political campaign messaging among others. One such facet of learning the dynamics of information diffusion is the ability to predict user engagement or the popularity of a single piece of information as it spreads through an online medium. Existing works in this regard mainly either obfuscate user level information or utilize frameworks that are …

Inference Per Joule: A Performance Metric For Artificial Intelligence In Space Applications, Eduardo Macias Zugasti

Open Access Theses & Dissertations

The use of artificial intelligence (AI) has grown exponentially in recent years. This growth is driven in part by the significant advancements in computing capabilities, which have also increased exponentially. Computers have not only become more powerful but also smaller in size, thanks to the evolution of transistor technology. These developments have enabled AI to become a widely accessible tool, even in recreational activities such as image creation and entertainment videos.

More recently, the use of AI has extended to space applications, where it can enhance and optimize various tasks. However, space conditions pose significant challenges for conventional computers due …

Car Damage Detection Using Deep Learning, Rahul Varma Indukuri Sr.

Electronic Theses, Projects, and Dissertations

Growing vehicle usage has resulted in a notable increase in road accidents, so it is imperative to have effective systems for identifying and evaluating vehicle damage. This work aims to create a computer vision and deep learning-based automated car damage detection system. This project's main goal is to develop a model that, using visual cues, can categorize car photos as either damaged or undamaged.

The algorithm operates in two steps: first, determining whether the picture features an automobile; then, it classifies the state of the car—damaged or undamaged. We thus employ the InceptionV3 model for damage classification and the MobileNet …

Virtual Makeup And Technology Integration, Vishwa Bhatt

Electronic Theses, Projects, and Dissertations

The Virtual Makeup Streamlit application presents an advanced approach to digital cosmetic try-on by allowing users to apply makeup to their facial images in real time. This project uses computer vision and web technologies to create an interactive and user-friendly platform that capitalizes on the increasing popularity of virtual try-on solutions in the cosmetics industry.

At its core, the system uses effective facial detection and semantic segmentation techniques to recognize and separate facial areas such as lips and hair. Techniques such as U-Net and Resnet, and Midepipe are used to create accurate segmentation masks, which are essential for accurate makeup …

Real Time Adaptive Control Of A Pid Via Genetic Algorithm Machine Learning Systems, Cemre Tas

Graduate Theses and Dissertations

The most common control method that is utilized by all industries across the world is the proportional-integrative-derivative controller (PID) due the relatively low cost and complexity of the system. However, there are draw-backs with PIDs, it is not adaptative to a changing system, so it works on nominal systems, and it starts breaking down when a system begins to have a non-linear response. The method chosen to overcome both is the utilization of machine learning with the use of genetic algorithms.

This method allows any PID system to be capable of adapting in real-time, while not adding significant additional cost …

Detection Of Http Flood Attacks Based On Machine Learning Algorithms, Norbek Karimov, Furkat Rakhmatov, Oybek Xolmuminov

Chemical Technology, Control and Management

This paper analyzes the effectiveness of Random Forest and SVM models for detecting HTTP Flood attacks. Experimental results demonstrate that both models achieve high accuracy. Evaluation was conducted using Precision, Recall, and F1 Score metrics. Additionally, key features of network traffic were extracted through correlation analysis to enable real-time application of the models in attack detection. The findings provide important insights into detecting DDoS attacks using machine learning and improving model performance.

Investigating The Role Of Blood Models In Predicting Rupture Status Of Intracranial Aneurysms, Zonghan Lyu, Mostafa Rezaeitaleshmahalleh, Nan Mu, Jingfeng Jiang

Michigan Tech Publications

Purpose. Selecting patients with high-risk intracranial aneurysms (IAs) is of clinical importance. Recent work in machine learning-based (ML) predictive modeling has demonstrated that lesion-specific hemodynamics within IAs can be combined with other information to provide critical insights for assessing rupture risk. However, how the adoption of blood rheology models (i.e., Newtonian and Non-Newtonian blood models) may influence ML-based predictive modeling of IA rupture risk has not been investigated.Methods and Materials.In this study, we conducted transient CFD simulations using Newtonian and non-Newtonian rheology (Carreau-Yasuda [CY]) models on a large cohort of 'patient-specific' IA geometries (>100) under pulsatile flow conditions to …

Bayesian Belief Networks Approach To Prioritize Road Safety Mitigation Measures For Eco-Mobility Modes, Fatmah Mohamed Alyammahi

Thesis/ Dissertation Defenses

This study presents a novel approach to prioritizing road safety mitigation measures for eco-mobility modes in Abu Dhabi, employing a sophisticated Bayesian methodology integrated with cost-benefit analysis. The research addresses the pressing need for enhanced safety in sustainable urban transportation, focusing on pedestrians, cyclists, and users of micro-mobility devices. A comprehensive Bayesian Belief Network (BBN) model was developed, incorporating key variables influencing eco-mobility safety, including visibility, predictability, road curvature, obstructions, and lighting conditions. The model was constructed using a combination of historical accident data and Probabilistic reasoning. This approach allowed for the quantification of complex relationships between various risk factors …

Utilizing Machine Learning To Predict The Charge Storage Capability Of Lithium-Ion Battery Materials, Manoj Chhetri, Karen S. Martirosyan

Physics & Astronomy Faculty Publications

With the increasing demand for high-performance batteries in applications such as electric vehicles and portable electronics, accurately predicting the charge storage capacity of battery materials is crucial for developing more efficient and reliable energy storage systems. Machine Learning (ML) and data-driven approaches, plays a vital role in enhancing our understanding of Li-ion battery performance, guiding materials design, optimizing system efficiency, and accelerating innovation in energy storage technologies. In this study, an ML-based approach was applied to a dataset of 2345 rechargeable Li-ion battery materials, obtained from the Materials Project online portal, to predict gravimetric charge storage capacity ─ a key …

Ai Diagnostic Tool For Covid-19 Severity, Hunter Lau, Ryan Lang, Aidan Furuhashi

Bioengineering Senior Theses

With the advent of COVID-19 pandemic global, healthcare systems were challenged with resource constraints plaguing hospital environments around the world with consequences that presented weaknesses in our healthcare system. This demonstrated the importance of triage in unprecedented scenarios. This project presents an integrated AI-driven diagnostic tool to predict the severity of COVID-19 cases using length of stay as an analog. By using clinical data and radiographic chest images, this project integrates a XGBoost clinical data model with a Convolutional Neural Network (CNN) model utilizing chest CT images to create a comprehensive assessment of patient case severity through predicted length of …

A Bayesian Belief Networks Approach To Prioritize Road Safety Mitigation Measures For Eco-Mobility Modes, Fatmah Mohamed Alyammahi

Theses

This study presents an innovative decision-making approach that enables the prioritization of road safety measures for eco-mobility users—pedestrians, cyclists and light-electric micromobility riders—in Abu Dhabi. The analysis uses 2032 eco-mobility crash records (1016 pedestrian, 567 bicycle, 449 e-scooter) from 2020-2023 supplied by Abu Dhabi Police and the Department of Municipalities and Transport. A supervised Bayesian Belief Network (BBN) was constructed around six empirically estimated variables: visibility, predictability, road curvature, obstructions, lighting and speed limit. Maximum-likelihood conditional-probability tables were derived from the cleaned dataset; Beta priors were applied only where cell counts were sparse. Ten conventional machine-learning models—including Random Forest, Gradient …

Explainable And Reduced-Feature Machine Learning Models For Shape And Drag Prediction Of A Freely Moving Drop In The Sub-Critical Weber Number Regime, Md Amanullah Kabir Tonmoy

Theses and Dissertations

Accurately predicting the shape and drag of a moving drop is crucial in many spray applications. However, due to the complex interaction between the drag force and drop shape deformation, accurate prediction of drop shape and drag from Computational Fluid Dynamics (CFD) simulation requires large computational resources and time. A novel data-driven approach using NARXNN (Non-linear Auto Regressive eXogenous input Neural Network) is proposed in this study, which recurrently predicts the drop shape and drag for a given Weber number (We) and Reynolds number (Re), in the sub-critical We regime where there is no drop breakup. The average error in …

Towards The Advancement Of Violence Recognition In Security Footage With Explainable Neural Networks, Paris Her

Dissertations (1934 -)

This dissertation investigates the problem of violence recognition in surveillance footage using computer vision and machine learning techniques. More specifically, our goal is to achieve interpretable and explainable deep learning models because violence recognition is a sensitive task. We first propose to perform violence recognition using a 3D convolutional neural network through intuitive hyperparameter tuning and transfer learning. We utilize a state-of-the-art 3D model used for general activity recognition that is lightweight and adjustable. Along with that, we introduce a data augmentation technique called "resize-within" which uses interpolation, rather than cropping, to resize the original input video to a new …

Evaluating And Improving U.S. National Water Model Evapotranspiration Estimates Through Eddy-Covariance Flux Tower Observations And Machine Learning Post-Processing, Abin Raj Chapagain

Theses and Dissertations

Despite ET's critical importance in the hydrological cycle, very little has been done to provide ET forecasts at a national level. This study comprises two research chapters examining the National Water Model's (NWM) evapotranspiration (ET) simulations. In Chapter II, we conducted the first comprehensive NWM ET model performance assessment by comparing simulations to eddy-covariance flux tower measurements across the Continental United States (CONUS) on a high-resolution, 1 KM square grid. We clustered results by National Weather Service (NWS) River Forecast Centers (RFCs), land cover classifications, elevation bands, and Köppen-Geiger Climate Zones. The NWM performs best in the Northeast and Ohio …

Automated Data Analysis For Concussion Patient Records: A Flutter-Based Desktop Application, Fhaheem Tadamarry

USF Tampa Graduate Theses and Dissertations

Concussions are a prevalent and complex medical condition requiring careful clinical assessment and data-driven insights for effective management. This thesis presents the development of an automated data analysis system for concussion patient records, integrating Flutter-based desktop application development with SQL-driven data processing. The system provides a streamlined, interactive interface for clincians and researchers to upload, visualize, and analyze patient data efficiently.

The proposed solution automates data cleaning, preprocessing, and statistical analysis, ensuring robust and reliable insights into demographic, clinical, and recovery-related factors. Key analyses include sex-based differences injury mechanisms, prior head injury impact, mood disorder correlations, and time-to-treatment variations. The …

Multimodal Ai-Driven Biomarker For Early Detection Of Cancer Cachexia, Sabeen Ahmed

USF Tampa Graduate Theses and Dissertations

Cancer cachexia is a metabolic syndrome characterized by substantial skeletal muscle loss, impacting cancer patients' survival and quality of life. Despite its clinical significance, early detection remains a challenge due to the lack of standardized diagnostic criteria and the reliance on indirect markers. This work presents an AI-driven approach to enhance cachexia detection and monitoring by integrating multiple deep learning methodologies. We explore transformer architectures for time-series analysis to model sequential medical data, enabling disease prediction and progression modeling. To ensure robust and reliable decision-making in clinical settings, we explore Bayesian deep neural networks for uncertainty estimation. Additionally, we introduce …

War Strategy Algorithm- Based Hybrid Optimization For Accurate And Rapid Speech Recognition, Shahad Thamear Abd Al-Latief, Salman Yussof, Azhana Ahmad, Saif Mohanad Khadim, Ahmed Alkhayyat

Iraqi Journal for Computer Science and Mathematics

Speech recognition-based applications increased and developed as a result of artificial intelligence's rapid growth, particularly Machine Learning, which play a crucial role in many aspects of daily life, such as applications related to human-computer interaction, and natural language processing. The complexity and diversity of speech signals provides challenges in maximizing the rate of accuracy and efficiency of speech recognition systems. Hyperparameter tuning is a crucial step in machine learning that has a significant role in optimizing the performance and generalization by determining the optimal values for the model's hyperparameters. This paper employed the recently developed WAR Strategy optimization algorithm for …

Feature Manifold Transformer For Detection Of Differential Item Functioning: Visual Detection Of Categorical Feature Nonconformity Through Attention-Based Analysis, Derrick A. Cox, Tanvi Banerjee, William L. Romine

Computer Science and Engineering Faculty Publications

Methods for interpreting complex feature interactions in educational assessment data remain a critical challenge, with traditional statistical approaches often creating barriers to accessibility and interpretability. We introduce the Feature Manifold Transformer (FMT), a novel machine learning approach that leverages dimensionality reduction, representation learning, and transformer architectures to visualize and interpret feature relationships in categorical data. Using the Concept Inventory of Natural Selection (CINS) and Concept Assessment of Natural Selection (CANS) datasets as testbeds, we demonstrate the FMT’s ability to capture subtle relationships between student demographics and response patterns. Our methodology enables both global and local pattern analysis, providing interpretable visualizations …

Methods For Detecting Anomalies In Network Traffic Based On One-Class Svm Technology, Komil Kerimov, Sardor Kurbanov, Zarina Azizova

Chemical Technology, Control and Management

This article is dedicated to the research and application of the One-Class Support Vector Machines method for detecting anomalies in network traffic. It examines the problems of detecting anomalies in network traffic and proposes a methodology for using One-Class SVM, including an overview of the main concepts and formulas of the algorithm. A discussion of the results of One-Class SVM is presented, including interpretation, advantages, limitations and possible directions for development of the proposed technique, as well as the practical significance of using the proposed method for detecting anomalies in network traffic.

A Novel Preprocessing Model For Multi Modal Brain Mri Image Classification For Stroke Prognosis, Alwin Joseph, Chandra J

Northeast Journal of Complex Systems (NEJCS)

Magnetic Resonance Imaging (MRI) is an imaging technique used for the diagnosis and observing the progression in various neurological disorders. Stroke is one of the prominent neurological disorders that creates significant impacts in the patients. It occurs when the blood supply to part of the brain is interrupted or reduced, preventing brain tissues from getting oxygen and nutrients. Multimodal data from various modalities help clinicians in proper prognosis of stroke. Ischemic Stroke Lesion Segmentation Challenge (ISLES22) provides data of stroke data for various stroke patients, the dataset consists of three modalities of data – Fluid Attenuated Inversion Recovery (FLAIR), Apparent …

Utilizing Ai For Improved Credit Risk Assessment, Emel Baglarbasi

Harrisburg University Dissertations and Theses

As the finance sector continues to evolve, traditional risk assessment methods struggle to calculate default risk and identify nonlinear relationships accurately. This research examines an alternative risk assessment model designed to estimate credit risk more accurately and efficiently in the credit processes of individual customers, which are one of the primary sources of income for the banking sector. It presents the theoretical design of an AI-based model. The use of this AI model can reduce human error in processes, improve risk assessment accuracy, and expedite procedures. The study adopts a postpositivist worldview and employs a quantitative research design. Algorithms including …

Fault Diagnosis And Fault Tolerant Structure For Multilevel Inverters Using Machine Learning Techniques, Sudha V

Theses and Dissertations

A paradigm shift towards electric drives in domestic and industrial sectors has significantly increased the use of multilevel inverters (MLI). MLIs are constructed using more semiconductor devices, which hinders safety and reliability. Literature states 31.2% of failures in MLIs are due to semiconductor devices. Hence, there is a need for fault detection and tolerant mechanisms to ensure the safety and reliability of MLIs.

MLIs like Cascaded H-bridge(CHB) and Packed U cell(PUC) are mostly preferred due to low harmonic distortion, which is considered in this work. The complexity associated with fault diagnosis with more components in MLIs is addressed by machine …

Rapid Prediction Of Coastal Flooding With Deep Neural Networks, Ali Shahabi, Navid Tahvildari

Graduate Student Government Association Research Conference

With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from extreme storm tides and recurrent nuisance flooding. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, enormous efforts have been made to utilize machine learning (ML) based data-driven models for the emulation and prediction of storm tides. However, flood advisory systems still rely on running computationally demanding real-time hydrodynamic models. because developing highly reliable ML-based models suitable for real-time forecasting and capable of capturing any surge levels is challenging. …