Imnets: Deep Learning Using An Incremental Modular Network Synthesis Approach For Medical Imaging Applications, 2022 University of Dayton
Imnets: Deep Learning Using An Incremental Modular Network Synthesis Approach For Medical Imaging Applications, Redha A. Ali, Russell C. Hardie, Barath Narayanan Narayanan, Temesguen Messay
Electrical and Computer Engineering Faculty Publications
Deep learning approaches play a crucial role in computer-aided diagnosis systems to support clinical decision-making. However, developing such automated solutions is challenging due to the limited availability of annotated medical data. In this study, we proposed a novel and computationally efficient deep learning approach to leverage small data for learning generalizable and domain invariant representations in different medical imaging applications such as malaria, diabetic retinopathy, and tuberculosis. We refer to our approach as Incremental Modular Network Synthesis (IMNS), and the resulting CNNs as Incremental Modular Networks (IMNets). Our IMNS approach is to use small network modules that we call SubNets …
Private Information Retrieval And Function Computation For Noncolluding Coded Databases, 2022 New Jersey Institute of Technology
Private Information Retrieval And Function Computation For Noncolluding Coded Databases, Sarah A. Obead
Dissertations
The rapid development of information and communication technologies has motivated many data-centric paradigms such as big data and cloud computing. The resulting paradigmatic shift to cloud/network-centric applications and the accessibility of information over public networking platforms has brought information privacy to the focal point of current research challenges. Motivated by the emerging privacy concerns, the problem of private information retrieval (PIR), a standard problem of information privacy that originated in theoretical computer science, has recently attracted much attention in the information theory and coding communities. The goal of PIR is to allow a user to download a message from a …
Project Metamorphosis: Designing A Dynamic Framework For Converting Musical Compositions Into Paintings, 2022 Chapman University
Project Metamorphosis: Designing A Dynamic Framework For Converting Musical Compositions Into Paintings, Rao Hamza Ali, Grace Fong, Erik Linstead
Engineering Faculty Articles and Research
The authors present an automated, rule-based system for converting piano compositions into paintings. Using a color-note association scale presented by Edward Maryon in 1919, which correlates 12-tone scale with 12 hues of the color circle, the authors present a simple approach for extracting colors associated with each note played in a piano composition. The authors also describe the color extraction and art generation process in detail, as well as the process for creating “moving art,” which imitates the progression of a musical piece in real time. They share and discuss artworks generated for four well-known piano compositions.
Development And Optimization Of Classification Neural Networks For Disaster-Assessment Using Unmanned Aerial Vehicle Systems, 2022 Georgia Southern University
Development And Optimization Of Classification Neural Networks For Disaster-Assessment Using Unmanned Aerial Vehicle Systems, Maria Isabel Gonzalez Bocanegra
Honors College Theses
This research focuses on increasing the classification accuracy of convolutional neural networks in an autonomous network of unmanned aerial vehicles for transportation disaster management. The autonomous network of UAVs will allow first responders to optimize their rescue plans by providing relevant information on inaccessible roads. The research seeks to explore different methods to optimize the architecture of convolutional networks for the multiclass classification of disaster-damaged roads.
Optical Microresonator-Based Flow-Speed Sensor, 2022 Southern Methodist University
Optical Microresonator-Based Flow-Speed Sensor, Elie Ramon Salameh
Mechanical Engineering Research Theses and Dissertations
Optical sensors have become more prominent in atmospheric measurement systems, with LiDAR instruments deployed on a variety of earth-bound, air-borne, and space-based platforms. In recent years, the interest in the human exploration of Mars has created a substantial push towards reliable and compact sensing elements for Mars exploration missions, particularly during a spacecraft’s entry, descent, and landing stages. Real-time sensors able to reliably measure the craft’s speed relative to the surrounding atmosphere during these stages are thus of great interest. In this dissertation, a proof-of-concept for an optical microfabricated sensor, which leverages the whispering-gallery-mode (WGM) and Doppler shift principles, is …
Worksheet 02 - Meshing, 2022 University of Southern Maine
Worksheet 02 - Meshing, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet is designed to oberserve the variations in results when the mesh is varied from coarse to fine, hence how to find the optimum mesh size such that we can get accurate results while not compromising computational power.
Worksheet 07 - Bicone, 2022 University of Southern Maine
Worksheet 07 - Bicone, Ashanthi Maxworth Phd
Antenna Design With HFSS
In this worksheet, setps are given to design a full-wavelength biconical antenna. This is a broadband antenna. The worksheet also shows how to observe surface currents.
Worksheet 10 - Patch, 2022 University of Southern Maine
Worksheet 10 - Patch, Ashanthi Maxworth Phd
Antenna Design With HFSS
In this worksheet, steps are given to create a slotted rectangular microstrip patch antenna with an inset feed using a stripline. The patch antenna is operating in the TM10 mode.
Worksheet 05 - Loop, 2022 University of Southern Maine
Worksheet 05 - Loop, Ashanthi Maxworth Phd
Antenna Design With HFSS
In this worksheet, the users can design a small loop. The small loop shows low directivity, hence at the end of the worksheet, the users can chanage the design parameters and increase the directivity.
Worksheet 06 - Arrays, 2022 University of Southern Maine
Worksheet 06 - Arrays, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet designs an antenna array with three identical dipole elemetns. The antenna is operating as a broadside array. By changing the parameters the users can view the grating lobes in addition to the main lobe.
Worksheet 09 Horn, 2022 University of Southern Maine
Worksheet 09 Horn, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet designs a pyramidal horn antenna fed by a waveport.
Worksheet 03 - Near Field, 2022 University of Southern Maine
Worksheet 03 - Near Field, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet guides students to change the observational region between, reactive near field, radiating near field, and far-field.
Worksheet 08 - Helix, 2022 University of Southern Maine
Worksheet 08 - Helix, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet creates a helical antenna operating in the axial mode. The antenna is mounted on a ground plane. The users can change the circumference of the helix and change the operating mode to broadside or conical if they wish.
Worksheet 04 - Dipole, 2022 University of Southern Maine
Worksheet 04 - Dipole, Ashanthi Maxworth Phd
Antenna Design With HFSS
This worksheet shows how to create a half-wavelength dipole, set the feeder through a port, observe directivity, half-power beamwidth, etc.
Integrating Fire Responses To Combat Wildfires, 2022 California Polytechnic State University, San Luis Obispo
Integrating Fire Responses To Combat Wildfires, Jonathan Leonard Badal
Electrical Engineering
Each year wildfires cause significant loss of property, worsen people’s health, and destroy multiple ecosystems. On average, a wildfire season costs anywhere from 7.6-62.8 billion dollars due to fire containment, repair, and restoration [1]. It can take decades to recover from the crippling loss of land and take even longer to fully restore it. However, with the implementation of a robust early detection system, these losses can be significantly reduced. The current process for identifying wildfires involves visual identification, phone call alerts, and media tools primarily driven by park rangers and public reporting. Unfortunately, this system is not preventative and …
Soft Web-Based Continuum Robot Grippers, 2022 Clemson University
Soft Web-Based Continuum Robot Grippers, Anthony Carambia
All Theses
We discuss the potential of soft webs to enhance robotic grasping. Specifically, we explore a novel combination of compliant continuum digits interspersed with a flexible material. The resulting webbed structure offers the potential for new modes of robust and adaptive object grasping. We introduce and describe two webbed grippers featuring alternate modes of actuation: pneumatic muscles and remotely actuated tendons. Experiments with the grippers demonstrate their ability to gently capture small, fragile, and non-cooperative objects.
Measuring The Electrical Properties Of 3d Printed Plastics In The W-Band, 2022 University of Arkansas, Fayetteville
Measuring The Electrical Properties Of 3d Printed Plastics In The W-Band, Noah Gregory
Electrical Engineering Undergraduate Honors Theses
3D printers are a method of additive manufacturing that consists of layering material to produce a 3D structure. There are many types of 3D printers as well as many types of materials that are capable of being printed with. The most cost-effective and well documented method of 3D printing is called Fused Deposition Modeling (FDM). FDM printers work by feeding a thin strand of plastic filament through a heated extruder nozzle. This plastic is then deposited on a flat, typically heated, surface called a print bed. The part is then built by depositing thin layers of plastic in the shape …
Signal Analysis Of Photovoltaic Systems For Multilevel Cybersecurity, 2022 University of Arkansas, Fayetteville
Signal Analysis Of Photovoltaic Systems For Multilevel Cybersecurity, Wesley G. Schwartz
Electrical Engineering Undergraduate Honors Theses
The cybersecurity of grid-connected power electronics is a rapidly developing field as more and more of these devices become a part of the Internet of Things. The objective of this thesis to analyze the current control signals of a photovoltaic (PV) inverter and develop an interface board for the implementation of a new cyber-secure controller.
In this thesis, the testing and in-depth analysis of the current PV inverter control system will be conducted. Using the data collected, an interface board will be developed to allow the use of the Unified Control Board (UCB), developed by Chris Farnell, in the PV …
Co-Planar Waveguides For Microwave Atom Chips, 2022 William & Mary
Co-Planar Waveguides For Microwave Atom Chips, Morgan Logsdon
Undergraduate Honors Theses
This thesis describes research to develop co-planar waveguides (CPW) for coupling microwaves from mm-scale coaxial cables into 50 μm-scale microstrip transmission lines of a microwave atom chip. This new atom chip confines and manipulates atoms using spin-specific microwave AC Zeeman potentials and is particularly well suited for trapped atom interferometry. The coaxial-to-microstrip coupler scheme uses a focused CPW (FCPW) that shrinks the microwave field mode while maintaining a constant 50 Ω impedance for optimal power coupling. The FCPW development includes the simulation, design, fabrication, and testing of multiple CPW and microstrip prototypes using aluminum nitride substrates. Notably, the FCPW approach …
Identification Of Orthologous Gene Groups Using Machine Learning, 2022 University of Nebraska-Lincoln
Identification Of Orthologous Gene Groups Using Machine Learning, Dillon Burgess
Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research
Identification of genes that show similarity between different organisms, a.k.a orthologous genes, is an open problem in computational biology. The purpose of this thesis is to create an algorithm to group orthologous genes using machine learning. Following an optimization step to find the best characterization based on training data, we represented sequences of genes or proteins with kmer vectors. These kmer vectors were then clustered into orthologous groups using hierarchical clustering. We optimized the clustering phase with the same training data for the method and parameter selection. Our results indicated that use of protein sequences with k=2 and scaling the …