Search
Now showing items 1-20 of 31
Region based object detectors for recognizing birds in aerial images
(University of Missouri--Columbia, 2019)
This project explores different types of deep neural networks (DNNs) for recognizing birds in aerial images based on real data provided by the Missouri Department of Conservation. The pipeline to identify birds from an image consist of two phases...
Modeling the urban underground pallet tube system design
(University of Missouri--Columbia, 2017)
Cities are witnessing a rapid growth in population and vehicles, causing greater traffic congestion on roads. Therefore, a need for a better transportation system to avoid this swelling congestion. In this research, we examine an emerging technology...
Design of a single sided linear induction motor (SLIM) using a user interactive computer program
(University of Missouri--Columbia, 2005)
This project studies the design of SLIM, which can be used to power capsules in a pneumatic capsule pipeline (PCP) system. The design equations of the SLIM and the equivalent circuit model are studied and discussed in detail. A SLIM of specified...
Semantic segmentation of land use and land cover for mapping agricultural activities
(University of Missouri--Columbia, 2023)
and tasks. This project focused on the three research objectives. First, the author developed the preliminary semantic segmentation pipeline based on the fully convolutional neural network. The second objective is to test with the remote sensing images...
Neural modeling case studies at biophysical, machine learning, and automation levels
(University of Missouri--Columbia, 2023)
[EMBARGOED UNTIL 12/1/2024] This dissertation reports three case studies using machine learning, biophysical, and automation frameworks to study neural engineering challenges. The first study utilized machine learning with a clinical dataset...
Protein-ion binding site prediction using deep learning
(University of Missouri--Columbia, 2023)
More than 50 percent of proteins bind to ions and these interactions are essential for various biological functions such as enzymatic catalysis, structural stability, signal transduction, protein function modulation, and ...
Deep heterogeneous superpixel neural networks for image analysis and feature extraction
(University of Missouri--Columbia, 2021)
computer vision research where their efficient representation has superior effects. In contemporary computer vision research driven by deep neural networks, superpixel-based approaches mainly rely on oversegmentation to provide a more efficient...
Accelerating materials processing via machine learning : towards autonomous manufacturing
(University of Missouri--Columbia, 2020)
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT REQUEST OF AUTHOR.] "Given the advantages of ML, this research thesis focuses on developing appropriate methodologies to solve the problems that inherit in the three phases...
Accelerating data-driven discover in type 1 diabetes: an informatics-based approach
(University of Missouri--Columbia, 2022)
heterogeneity in T1D, and (3) development of a highly scalable pipeline to facilitate diabetes health outcomes research using multi-site EHR data. We also substantiate our commitment to openly disseminating our findings and tools to the research community...
Horticultural crop response to synthetic auxins
(University of Missouri--Columbia, 2019)
and 2018 at three locations in Missouri, research in production vineyards focused on the single-season effects of dicamba on hybrid grapes (Vidal blanc). During flowering and early fruit set, established grapes were exposed to low rates of dicamba...
Uncovering the genetic basis of seed amino acid composition in arabidopsis using a multi-omics integrative approach
(University of Missouri--Columbia, 2021)
, and how the content of Chapter Two through Chapter Four builds upon and adds value to the area of seed amino acid research as a whole. Chapter Two focuses on uncovering the genes and biological processes that underly the regulation of free Glutamine which...
Reliable and structural deep neural networks
(University of Missouri--Columbia, 2022)
Deep neural networks have dominated a wide range of computer vision research recently. However, recent studies have shown that deep neural networks are sensitive to adversarial perturbations. The limitations of deep networks cause reliability...
Interactive, multi-purpose traffic prediction platform using connected vehicles dataset
(University of Missouri--Columbia, 2022)
Traffic congestion is a perennial issue because of the increasing traffic demand yet limited budget for maintaining current transportation infrastructure; let alone expanding them. Many congestion management techniques ...
The progression of white matter abnormalities in individuals with early-treated phenylketonuria (PKU)
(University of Missouri--Columbia, 2020)
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Phenylketonuria (PKU) is a rare autosomal recessive disorder characterized by a disruption in the ability to metabolize phenylalanine (phe) into tyrosine, ...
Defeat data poisoning attacks on facial recognition applications
(University of Missouri--Columbia, 2021)
In the modern era, facial photos are used for a wide array of applications, from logging into a smartphone to bragging about a weekend getaway. With the vast amount of use cases for facial images, adversaries will attack ...
Deep learning for small object detection in images
(University of Missouri--Columbia, 2020)
, identified major challenges, and listed some future research directions. Existing techniques were categorized into using contextual information, combining multiple feature maps, creating sufficient positive examples, and balancing foreground and background...
The Bavarian model? : modernization, environment, and landscape planning in the Bavarian nuclear power industry, 1950-1980
(University of Missouri--Columbia, 2009)
Perhaps no state in the Federal Republic of Germany witnessed a more pronounced state sponsored modernization effort than Bavaria, 1950-1980. This vast transformation, particularly in the field of nuclear energy, required ...
Real-time visualization of massive imagery and volumetric datasets
(University of Missouri--Columbia, 2006)
The visualization of extremely large multi-dimensional datasets requires highly scalable geometric algorithms. We consider an algorithm to be scalable if its complexity remains constant independent of the size of the ...
Out-of-core image techniques with extensions for WAMI
(University of Missouri--Columbia, 2019)
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Out-of-core image techniques provide for interactive visualization, analysis, and processing of extremely large images exceeding primary memory. This ...
Development of Advanced Delivery Systems for Microbicides
(2016)
HIV/AIDS still continues to be a pandemic and global emergency and is a leading cause of
death among the women of reproductive age (15-49 yr). Women are more vulnerable for HIV infection
due to anatomical and physiological ...