Computational Engineering Commons^™

Automated Brain Tumor Classifier With Deep Learning, Venkata Sai Krishna Chaitanya Kandula

Electronic Theses, Projects, and Dissertations

Brain Tumors are abnormal growth of cells within the brain that can be categorized as benign (non-cancerous) or malignant (cancerous). Accurate and timely classification of brain tumors is crucial for effective treatment planning and patient care. Medical imaging techniques like Magnetic Resonance Imaging (MRI) provide detailed visualizations of brain structures, aiding in diagnosis and tumor classification^[8].

In this project, we propose a brain tumor classifier applying deep learning methodologies to automatically classify brain tumor images without any manual intervention. The classifier uses deep learning architectures to extract and classify brain MRI images. Specifically, a Convolutional Neural Network (CNN) …

Generative Language Models For Personalized Information Understanding, Pengshan Cai

Doctoral Dissertations

A major challenge in information understanding stems from the diverse nature of the audience, where individuals possess varying preferences, experiences, educational and cultural backgrounds. Consequently, adopting a one-size-fits-all approach to provide information may prove suboptimal. While prior research has predominantly focused on delivering pre-existing content to users with potential interests, this thesis explores generative language models for personalized information understanding. By harnessing the potential of generative language models, our objective is to generate novel personalize content for individual users. As a result, users from diverse backgrounds can be provided with content that are tailored for their need and better aligns …

Comparison Of Conventional And Adaptive Acoustic Beamforming Algorithms Using A Tetrahedral Microphone Array In Noisy Environments, Megan Brittany Ewers

Dissertations and Theses

In situ acoustic measurements are often plagued by interfering sound sources that occur within the measurement environment. Both adaptive and conventional beamforming algorithms, when applied to the outputs of a microphone array arranged in a tetrahedral geometry, are able to capture sound sources in desired directions and reject sound from unwanted directions. Adaptive algorithms may be able to measure a desired sound source with greater spatial precision, but require more calculations and, therefore, computational power. A conventional frequency-domain phase-shift algorithm and a modified adaptive frequency-domain Minimum Variance Distortionless Response (MVDR) algorithm were applied to simulated and recorded signals from a …

The Integration Of Neuromorphic Computing In Autonomous Robotic Systems, Md Abu Bakr Siddique

Dissertations, Master's Theses and Master's Reports

Deep Neural Networks (DNNs) have come a long way in many cognitive tasks by training on large, labeled datasets. However, this method has problems in places with limited data and energy, like when planetary robots are used or when edge computing is used [1]. In contrast to this data-heavy approach, animals demonstrate an innate ability to learn by communicating with their environment and forming associative memories among events and entities, a process known as associative learning [2-4]. For instance, rats in a T-maze learn to associate different stimuli with outcomes through exploration without needing labeled data [5]. This learning paradigm …

Adaptable And Trustworthy Machine Learning For Human Activity Recognition From Bioelectric Signals, Morgan S. Stuart

Theses and Dissertations

Enabling machines to learn measures of human activity from bioelectric signals has many applications in human-machine interaction and healthcare. However, labeled activity recognition datasets are costly to collect and highly varied, which challenges machine learning techniques that rely on large datasets. Furthermore, activity recognition in practice needs to account for user trust - models are motivated to enable interpretability, usability, and information privacy. The objective of this dissertation is to improve adaptability and trustworthiness of machine learning models for human activity recognition from bioelectric signals. We improve adaptability by developing pretraining techniques that initialize models for later specialization to unseen …

Simulation Of Wave Propagation In Granular Particles Using A Discrete Element Model, Syed Tahmid Hussan

Electronic Theses and Dissertations

The understanding of Bender Element mechanism and utilization of Particle Flow Code (PFC) to simulate the seismic wave behavior is important to test the dynamic behavior of soil particles. Both discrete and finite element methods can be used to simulate wave behavior. However, Discrete Element Method (DEM) is mostly suitable, as the micro scaled soil particle cannot be fully considered as continuous specimen like a piece of rod or aluminum. Recently DEM has been widely used to study mechanical properties of soils at particle level considering the particles as balls. This study represents a comparative analysis of Voigt and Best …

Joint Learning Of Unknown Safety Constraints And Control Policies In Reinforcement Learning, Lunet Abiye Yifru

Graduate Theses, Dissertations, and Problem Reports

Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe RL approaches have predominantly focused on incorporating predefined safety constraints into the policy learning process. However, this reliance on predefined safety constraints poses limitations in dynamic and unpredictable real-world settings where such constraints may not be available or sufficiently adaptable. Bridging this gap, we propose a novel approach that concurrently learns a safe RL control policy and identifies the unknown safety constraint parameters of a given environment. …

Early-Age Strength And Failure Characteristics Of 3d Printable Polymer Concrete: Numerical Modelling And Experimental Testing, Mohammad Amin Dehghani Najvani

Civil Engineering ETDs

The time-dependent rheological and early-age strength parameters of Polymer concrete (PC) were investigated. PC flow decreased, and the static yield stress and thixotropy increased as the specimen aged, while the dynamic yield stress remained unchanged. The study found that the Herschel-Bulkley model can accurately describe the PC’s rheological behavior over time. The change in cohesion strength and internal friction angle over time was observed using uniaxial unconfined compression and direct shear tests of fresh PC. A time-dependent MohrCoulomb failure criterion was established. Temperature analysis was used to determine the gel time and explain the evolution of the time-dependent early-age strength …

Numerical Investigation Of Subglottal Stenosis Effects On Human Voice Production, Dariush Bodaghi

Electronic Theses and Dissertations

This dissertation aimed to advance knowledge of how subglottal stenosis impacts voice production physiology. An in-house fluid-structure-acoustic interaction approach based on the hydrodynamic/acoustic splitting technique was employed. This technique was rigorously verified for simulating phonation by matching the acoustic behavior to a compressible flow solver for phonation-relevant geometries. Simulations of an idealized 2D vocal tract model demonstrated the effects of supraglottal acoustic resonance on vocal fold kinematics and glottal flow waveform. Results showed that the acoustic coupling between higher harmonics and formats generated pressure oscillations, modifying vocal fold dynamics and glottal flow rate.

A major novelty was the incorporation and …

An Investigation Into Applications Of Canonical Polyadic Decomposition & Ensemble Learning In Forecasting Thermal Data Streams In Direct Laser Deposition Processes, Jonathan Storey

Theses and Dissertations

Additive manufacturing (AM) is a process of creating objects from 3D model data by adding layers of material. AM technologies present several advantages compared to traditional manufacturing technologies, such as producing less material waste and being capable of producing parts with greater geometric complexity. However, deficiencies in the printing process due to high process uncertainty can affect the microstructural properties of a fabricated part leading to defects. In metal AM, previous studies have linked defects in parts with melt pool temperature fluctuations, with the size of the melt pool and the scan pattern being key factors associated with part defects. …

Convolution And Autoencoders Applied To Nonlinear Differential Equations, Noah Borquaye

Electronic Theses and Dissertations

Autoencoders, a type of artificial neural network, have gained recognition by researchers in various fields, especially machine learning due to their vast applications in data representations from inputs. Recently researchers have explored the possibility to extend the application of autoencoders to solve nonlinear differential equations. Algorithms and methods employed in an autoencoder framework include sparse identification of nonlinear dynamics (SINDy), dynamic mode decomposition (DMD), Koopman operator theory and singular value decomposition (SVD). These approaches use matrix multiplication to represent linear transformation. However, machine learning algorithms often use convolution to represent linear transformations. In our work, we modify these approaches to …

Machine Learning For Kalman Filter Tuning Prediction In Gps/Ins Trajectory Estimation, Peter Wright

Electronic Theses, Projects, and Dissertations

This project is an exploration and implementation of an application using Machine Learning (ML) and Artificial Intelligence (AI) techniques which would be capable of automatically tuning Kalman-Filter parameters used in post-flight trajectory estimation software at Edwards Air Force Base (EAFB), CA. The scope of the work in this paper is to design and develop a skeleton application with modular design, where various AI/ML modules could be developed to plug-in to the application for tuning-switch prediction.

Automated Usability Evaluation Utilizing Log Files And Data Mining Techniques., Sima Shafaei

Electronic Theses and Dissertations

Usability evaluation is one of the essential aspects of software production. This evaluation should be done during the entire life cycle of a software application, from pre-production to production and post-production. However, the collection and evaluation of usability data can be a very challenging, time-consuming, and expensive task to be conducted manually, particularly for certain types of products and working conditions. These challenges may include the need to recruit participants fully engage and motivate them during evaluation, and factor in environmental conditions. Other challenges may include collecting data in real-world environments, especially when the users are geographically dispersed, minimizing evaluator …

Digital Twins Of The Living Knee: From Measurements To Model, Thor Erik Andreassen

Electronic Theses and Dissertations

Modern medicine has dramatically improved the lives of many. In orthopaedics, robotic surgery has given clinicians superior accuracy when performing interventions over conventional methods. Nevertheless, while these and many other methods are available to ensure treatments are performed successfully, far fewer methods exist to predict the proper treatment option for a given person. Clinicians are forced to categorize individuals, choosing the best treatment on “average.” However, many individuals differ significantly from the “average” person, for which many of these treatments are designed. Going forward, a method of testing, evaluating, and predicting different treatment options' short- and long-term effects on an …

Automatic Cardiac Mri Image Segmentation And Mesh Generation, Ziyuan Li

McKelvey School of Engineering Theses & Dissertations

Segmenting and reconstructing cardiac anatomical structures from magnetic resonance (MR) images is essential for the quantitative measurement and automatic diagnosis of cardiovascular diseases [1]. However, manual evaluation of the time-series cardiac MRI (CMRI) obtained during routine clinical care are laborious, inefficient, and tends to produce biased and non-reproducible results [2]. This thesis proposes an end-to-end pipeline for automatically segmenting short-axis (SAX) CMRI images and generating high-quality 2D and 3D meshes suitable for finite element analysis. The main advantage of our approach is that it can not only work as a stand-alone pipeline for the automatic CMR image segmentation and mesh …

Using Dynamic Task Allocation To Evaluate Driving Performance, Situation Awareness, And Cognitive Load At Different Levels Of Partial Autonomy, Viraj R. Patel

Theses and Dissertations

The state of the art of autonomous vehicles requires operators to remain vigilant while performing secondary tasks. The goal of this research was to investigate how dynamically allocated secondary tasks affected driving performance, cognitive load, and situation awareness. Secondary tasks were presented at rates based on the autonomy level present and whether the autonomous system was engaged. A rapid secondary task rate was also presented for two short periods regardless of whether autonomy was engaged. There was a three-minute familiarization phase followed by a data collection phase where participants responded to secondary tasks while preventing the vehicle from colliding into …

Singular Integration By Interpolation For Integral Equations, Ioannis Kyriakou

Doctoral Dissertations

Maxwell’s equations and the laws of Electromagnetics (EM) govern a plethora of electrical, optical phenomena with applications on wireless, cellular, communications, medical and computer hardware technologies to name a few. A major contributor to the technological progress in these areas has been due to the development of simulation and design tools that enable engineers and scientists to model, analyze and predict the EM interactions in their systems of interest. At the core of such tools is the field of Computational Electromagnetics (CEM), which studies the solution of Maxwell’s equations with the aid of computers. The advances in these applications technologies, …

Deep Cnn-Based Automated Optical Inspection For Aerospace Components, Shashi Bhushan Jha

Doctoral Dissertations and Master's Theses

ABSTRACT

The defect detection problem is of outmost importance in high-tech industries such as aerospace manufacturing and is widely employed using automated industrial quality control systems. In the aerospace manufacturing industry, composite materials are extensively applied as structural components in civilian and military aircraft. To ensure the quality of the product and high reliability, manual inspection and traditional automatic optical inspection have been employed to identify the defects throughout production and maintenance. These inspection techniques have several limitations such as tedious, time- consuming, inconsistent, subjective, labor intensive, expensive, etc. To make the operation effective and efficient, modern automated optical inspection …

Resilience Model For Teams Of Autonomous Unmanned Aerial Vehicles (Uav) Executing Surveillance Missions, Robert Koeneke

Doctoral Dissertations and Master's Theses

Teams of low-cost Unmanned Aerial Vehicles (UAVs) have gained acceptance as an alternative for cooperatively searching and surveilling terrains. These UAVs are assembled with low-reliability components, so unit failures are possible. Losing UAVs to failures decreases the team's coverage efficiency and impacts communication, given that UAVs are also communication nodes. Such is the case of a Flying Ad Hoc Network (FANET), where the failure of a communication node may isolate segments of the network covering several nodes. The main goal of this study is to develop a resilience model that would allow us to analyze the effects of individual UAV …

Resources Based Planning Framework For Infrastructure Maintenance And Rehabilitation Projects, Heba Gad

Theses and Dissertations

Infrastructure maintenance and rehabilitation projects involve activities scattered over a large geographical area (e.g., scattered road segments maintenance, telecom towers maintenance program, etc.). Planning such projects require a resource-based approach that accounts for the implications of resource mobility between activities’ locations in terms of time & cost. Existing scheduling techniques fall short of addressing the unique challenges of the scattered nature of these projects in combination with organization's limited resources availability. To address this need, this research presents a resources-based planning framework for infrastructure maintenance and rehabilitation scattered projects with the objective of enhancing resources utilization achieving time and cost …

Vi Energy-Efficient Memristor-Based Neuromorphic Computing Circuits And Systems For Radiation Detection Applications, Jorge Iván Canales Verdial

Electrical and Computer Engineering ETDs

Radionuclide spectroscopic sensor data is analyzed with minimal power consumption through the use of neuromorphic computing architectures. Memristor crossbars are harnessed as the computational substrate in this non-conventional computing platform and integrated with CMOS-based neurons to mimic the computational dynamics observed in the mammalian brain’s visual cortex. Functional prototypes using spiking sparse locally competitive approximations are presented. The architectures are evaluated for classification accuracy and energy efficiency. The proposed systems achieve a 90% true positive accuracy with a high-resolution detector and 86% with a low-resolution detector.

The Influence Of Heat And Mass Transfer On The Setting Rate Of Adhesives Between Porous Substrates, Mubarak Mohammed Khlewee

Electronic Theses and Dissertations

The dynamic penetration of fluid into a porous media where other changes are occurring such as temperature or concentration is of interest to a number of situations. However, little experimental and theoretical analysis of this situation is found in the literature where most of the previously published works have studied the penetration with constant physical properties, where there is no change of the fluid as it enters the pores. This situation is important in the setting of adhesives in porous medium such as in the setting of hot melt and water-based adhesives in the production of paper based packaging. The …

Explainable Physics-Informed Deep Learning For Rainfall-Runoff Modeling And Uncertainty Assessment Across The Continental United States, Sadegh Sadeghi Tabas

All Dissertations

Hydrologic models provide a comprehensive tool to calibrate streamflow response to environmental variables. Various hydrologic modeling approaches, ranging from physically based to conceptual to entirely data-driven models, have been widely used for hydrologic simulation. During the recent years, however, Deep Learning (DL), a new generation of Machine Learning (ML), has transformed hydrologic simulation research to a new direction. DL methods have recently proposed for rainfall-runoff modeling that complement both distributed and conceptual hydrologic models, particularly in a catchment where data to support a process-based model is scared and limited.

This dissertation investigated the applicability of two advanced probabilistic physics-informed DL …

Smart-Insect Monitoring System Integration And Interaction Via Ai Cloud Deployment And Gpt, Ahmed Moustafa

Computer Science and Computer Engineering Undergraduate Honors Theses

The Insect Detection Server was developed to explore the deployment and integration of an Artificial Intelligence model for Computer Vision in the context of insect detection. The model was developed to accurately identify insects from images taken by camera systems installed on farms. The goal is to integrate the model into an easily accessible, cloud-based application that allows farmers to analyze automatically uploaded images containing groups of insects found on their farms. The application returns the bounding boxes and the detected classes of insects whenever an image is captured on-site, enabling farmers to take appropriate actions to address the issue …

Machine Learning-Based Data And Model Driven Bayesian Uncertanity Quantification Of Inverse Problems For Suspended Non-Structural System, Zhiyuan Qin

All Dissertations

Inverse problems involve extracting the internal structure of a physical system from noisy measurement data. In many fields, the Bayesian inference is used to address the ill-conditioned nature of the inverse problem by incorporating prior information through an initial distribution. In the nonparametric Bayesian framework, surrogate models such as Gaussian Processes or Deep Neural Networks are used as flexible and effective probabilistic modeling tools to overcome the high-dimensional curse and reduce computational costs. In practical systems and computer models, uncertainties can be addressed through parameter calibration, sensitivity analysis, and uncertainty quantification, leading to improved reliability and robustness of decision and …

Achieving Causal Fairness In Recommendation, Wen Huang

Graduate Theses and Dissertations

Recommender systems provide personalized services for users seeking information and play an increasingly important role in online applications. While most research papers focus on inventing machine learning algorithms to fit user behavior data and maximizing predictive performance in recommendation, it is also very important to develop fairness-aware machine learning algorithms such that the decisions made by them are not only accurate but also meet desired fairness requirements. In personalized recommendation, although there are many works focusing on fairness and discrimination, how to achieve user-side fairness in bandit recommendation from a causal perspective still remains a challenging task. Besides, the deployed …

Detecting Pathobiomes Using Machine Learning, Valerie Jackson, Valerie Jackson

Industrial Engineering Undergraduate Honors Theses

Machine learning is a field with high growth potential due to the overall continuous progressions, developments, advancements, and improvements caused by the way it is used to help interpret and use large amounts of data [1]. One type of data that can be collected and analyzed by these machine learning models is data that is associated with DNA and information that the DNA gives. The research will be focusing specifically on using machine learning technology to detect pathobiomes indicative of salmonella pork. The pathobiome associated with salmonella is very similar to others, and this causes a problem for classification/detection with …

Development Of A Computational Model To Investigate Pathways And The Effects Of Treatment In Fanconi Anemia, Sabrina Kellett

Biological Sciences Undergraduate Honors Theses

Fanconi Anemia (FA) is a rare type of anemia that is not easily studied and can have very detrimental effects. This disease compromises the bone marrow, resulting in decreased hemopoiesis. Symptoms of FA also include abnormalities in the brain and spinal cord, incorrect formation of the kidneys, abnormal formation of the heart and lungs, and a dramatically increased risk of developing cancer. FA can be caused by various mutations in any of the 22 genes that encode for proteins involved in what is called the FA DNA repair pathway. In healthy individuals, this pathway specifically repairs interstrand cross-links (ICLs) recognized …

Preserving User Data Privacy Through The Development Of An Android Solid Library, Alexandria Lim

Computer Science and Computer Engineering Undergraduate Honors Theses

In today’s world where any and all activity on the internet produces data, user data privacy and autonomy are not prioritized. Companies called data brokers are able to gather data elements of personal information numbering in the billions. This data can be anything from purchase history, credit card history, downloaded applications, and service subscriptions. This information can be analyzed and inferences can be drawn from analysis, categorizing people into groups that range in sensitivity — from hobbies to race and income classes. Not only do these data brokers constantly overlook data privacy, this mass amount of data makes them extremely …

Implementation Of A Pre-Assessment Module To Improve The Initial Player Experience Using Previous Gaming Information, Rafael David Segistan Canizales

Electronic Thesis and Dissertation Repository

The gaming industry has become one of the largest and most profitable industries today. According to market research, the industry revenues will pass $200 Billion and are expected to reach another $20 Billion in 2024. With the industry growing rapidly, players have become more demanding, expecting better content and quality. This means that game studios need new and innovative ways to make their games more enjoyable. One technique used to improve the player experience is DDA (Dynamic Difficulty Adjustment). It leverages the current player state to perform different adjustments during the game to tune the difficulty delivered to the player …