Digital Commons Network^™

Cocm: Co-Occurrence-Based Consistency Matching In Domain-Adaptive Segmentation, Siyu Zhu, Yingjie Tian, Fenfen Zhou, Kunlong Bai, Xiaoyu Song

Electrical and Computer Engineering Faculty Publications and Presentations

This paper focuses on domain adaptation in a semantic segmentation task. Traditional methods regard the source domain and the target domain as a whole, and the image matching is determined by random seeds, leading to a low degree of consistency matching between domains and interfering with the reduction in the domain gap. Therefore, we designed a two-step, three-level cascaded domain consistency matching strategy—co-occurrence-based consistency matching (COCM)—in which the two steps are: Step 1, in which we design a matching strategy from the perspective of category existence and filter the sub-image set with the highest degree of matching from the image …

A Patient-Specific Algorithm For Lung Segmentation In Chest Radiographs, Manawaduge Supun De Silva, Barath Narayanan Narayanan, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

Lung segmentation plays an important role in computer-aided detection and diagnosis using chest radiographs (CRs). Currently, the U-Net and DeepLabv3+ convolutional neural network architectures are widely used to perform CR lung segmentation. To boost performance, ensemble methods are often used, whereby probability map outputs from several networks operating on the same input image are averaged. However, not all networks perform adequately for any specific patient image, even if the average network performance is good. To address this, we present a novel multi-network ensemble method that employs a selector network. The selector network evaluates the segmentation outputs from several networks; on …

Computer Engineering Education, Marilyn Wolf

School of Computing: Conference and Workshop Papers

Computer engineering is a rapidly evolving discipline. How should we teach it to our students?

This virtual roundtable on computer engineering education was conducted in summer 2022 over a combination of email and virtual meetings. The panel considered what topics are of importance to the computer engineering curriculum, what distinguishes computer engineering from related disciplines, and how computer engineering concepts should be taught.

Digitally Predicting Protein Localization And Manipulating Protein Activity In Fluorescence Images Using 4d Reslicing Gan, Yang Jiao, Lingkun Gu, Yingtao Jiang, Mo Weng, Mei Yang

Electrical & Computer Engineering Faculty Research

While multi-channel fluorescence microscopy is a vital imaging method in biological studies, the number of channels that can be imaged simultaneously is limited by technical and hardware limitations such as emission spectra cross-talk. One solution is using deep neural networks to model the localization relationship between two proteins so that the localization of one protein can be digitally predicted. Furthermore, the input and predicted localization implicitly reflect the modeled relationship. Accordingly, observing the response of the prediction via manipulating input localization could provide an informative way to analyze the modeled relationships between the input and the predicted proteins.

Transition-Metal Ions In Β-Ga2O3 Crystals: Identification Of Ni Acceptors, Timothy D. Gustafson, Nancy C. Giles, Brian C. Holloway, J. Jesenovec, B. L. Dutton, M. D. Mccluskey, Larry E. Halliburton

Faculty Publications

Excerpt: Transition-metal ions (Ni, Cu, and Zn) in β-Ga₂O₃ crystals form deep acceptor levels in the lower half of the bandgap. In the present study, we characterize the Ni acceptors in a Czochralski-grown crystal and find that their (0/−) level is approximately 1.40 eV above the maximum of the valence band.

Material Characterization And Comparison Of Sol-Gel Deposited And Rf Magnetron Deposited Lead Zirconate Titanate Thin Films, Katherine Lynne Miles

Mechanical Engineering ETDs

Lead zirconate titanate (PZT) has been a material of interest for sensor, actuator, and transducer applications in microelectromechanical systems (MEMS). This is due to their favorable piezoelectric, pyroelectric and ferroelectric properties. While various methods are available to deposit PZT thin films, radio frequency (RF) magnetron sputtering was selected to provide high quality PZT films with the added capability of batch processing. These sputter deposited PZT films were characterized to determine their internal film stress, Young’s modulus, composition, and structure. After characterization, the sputtered PZT samples were poled using corona poling and direct poling methods. As a means of comparison, commercially …

Rdlnn-Based Image Forgery Detection And Forged Region Detection Using Mot, Akram Hatem Saber, Mohd Ayyub Khan, Basim Galeb Mejbel

Karbala International Journal of Modern Science

Image forgery detection TEMPhas become an emerging research area due to the increasing number of forged images circulating on the internet and other social media, which leads to legal and social issues. Image forgery detection includes the classification of an image as forged or authentic and as well as localizing the forgery wifin the image. In this paper, we propose a Regression Deep Learning Neural Network (RDLNN) based image forgery detection followed by Modified Otsu Thresholding (MOT) algorithm to detect the forged region. The proposed model comprises five steps that are preprocessing, image decomposition, feature extraction, classification and block matching. …

Submillimeter-Wave Cornea Phantom Sensing Over An Extended Depth Of Field With An Axicon-Generated Bessel Beam, Mariangela Baggio, Aleksi Tamminen, Joel Lamberg, Roman Grigorev, Samu-Ville Pälli, Juha Ala-Laurinaho, Irina Nefedova, Jean-Louis Bourges, Sophie X. Deng, Elliott R. Brown, Vincent P. Wallace, Zachary D. Taylor

Electrical Engineering Faculty Publications

The feasibility of a 220 - 330 GHz zero order axicon generated Bessel beam for corneal water content was explored. Simulation and experimental data from the 25-degree cone angle hyperbolic-axicon lens illuminating metallic spherical targets demonstrate a monotonically decreasing, band integrated, backscatter intensity for increasing radius of curvature from 7 - 11 mm, when lens reflector and optical axis are aligned. Further, for radii >= 9.5 mm, maximum signal was obtained with a 1 mm transverse displacement between lens and reflector optical axes arising from spatial correlation between main lobe and out of phase side lobes. Thickness and permittivity parameter …

Development Of An Automated Platform For Sensing And Differentiating Vapor-Phase Btex Constituents, Jonathan Samuelson

USF Tampa Graduate Theses and Dissertations

Light aromatic hydrocarbons are an inevitable byproduct of fossil fuel extraction, refinement, distribution, and use. The four lightest and most prevalent of these are benzene, toluene, ethylbenzene, and xylene, which are known collectively as BTEX. In spite of their chemical similarity these species have markedly different effects on human health and substantially different concentrations are permitted by OSHA in workplaces and by the EPA in ambient air and groundwater. Real-time detection, identification, and quantification of these species is therefore of great importance wherever they see industrial use.This work represents the continuation and advancement of a line of research in which …

Deepdemod: Bpsk Demodulation Using Deep Learning Over Software-Defined Radio, Arhum Ahmad, Satyam Agarwal, Sam Darshi, Sumit Chakravarty

Open Access Publishing Fund Collection

In wireless communication, signal demodulation under non-ideal conditions is one of the important research topic. In this paper, a novel non-coherent binary phase shift keying demodulator based on deep neural network, namely DeepDeMod, is proposed. The proposed scheme makes use of neural network to decode the symbols from the received sampled signal. The proposed scheme is developed to demodulate signal under fading channel with additive white Gaussian noise along with hardware imperfections, such as phase and frequency offset. The time varying nature of hardware imperfections and channel poses a additional challenge in signal demodulation. In order to address this issue, …

Compilation Optimizations To Enhance Resilience Of Big Data Programs And Quantum Processors, Travis D. Lecompte

LSU Doctoral Dissertations

Modern computers can experience a variety of transient errors due to the surrounding environment, known as soft faults. Although the frequency of these faults is low enough to not be noticeable on personal computers, they become a considerable concern during large-scale distributed computations or systems in more vulnerable environments like satellites. These faults occur as a bit flip of some value in a register, operation, or memory during execution. They surface as either program crashes, hangs, or silent data corruption (SDC), each of which can waste time, money, and resources. Hardware methods, such as shielding or error correcting memory (ECM), …

Sers Platform For Single Fiber Endoscopic Probes, Debsmita Biswas

LSU Doctoral Dissertations

Molecular detection techniques have huge potential in clinical environments. In addition to many other molecular detection techniques, endoscopic Raman spectroscopy has great ability in terms of minimal invasiveness and real-time spectra acquisition. However, Raman Effect is low in sensitivity, limiting the application. Surface-Enhanced Raman Scattering (SERS), addresses this limitation. SERS brings rough nano-metallic surfaces in contact with specimen molecules which enormously enhances Raman signals. This provides Raman spectroscopy with immense capabilities for diverse fields of applications.

Generally, in clinical probe applications, the spectrometer is brought near the target molecules for detection. Typically, optical fibers are used to couple spectrometers to …

Gesture Controlled Collaborative Robot Arm And Lab Kit, Abel A. Reyes, Skylar Reinhardt, Tony Wise, Nathir Rawashdeh, Sidike Paheding

Michigan Tech Publications, Part 1

In this paper, a mechatronics system was designed and implemented to include the subjects of artificial intelligence, control algorithms, robot servo motor control, and human-machine interface (HMI). The goal was to create an inexpensive, multi-functional robotics lab kit to promote students’ interest in STEM fields including computing and mechtronics. Industrial robotic systems have become vastly popular in manufacturing and other industries, and the demand for individuals with related skills is rapidly increasing. Robots can complete jobs that are dangerous, dull, or dirty for humans to perform. Recently, more and more collaborative robotic systems have been developed and implemented in the …

Blockchain And Federated Learning-Based Security Solutions For Telesurgery System: A Comprehensive Review, Sachi Chaudjary, Riya Kakkar, Rajesh Gupta, Sudeep Tanwar, Smita Agrawal, Ravi Sharma

Turkish Journal of Electrical Engineering and Computer Sciences

The advent of telemedicine with its remote surgical procedures has effectively transformed the working of healthcare professionals. The evolution of telemedicine facilitates the remote monitoring of patients that lead to the advent of telesurgery systems, i.e. one of the most critical applications in telemedicine systems. Apart from gaining popularity, the telesurgery system may encounter security and trust issues of patients? data while communicating with the surgeon for their remote treatment. Motivated by this, we have presented a comprehensive survey on secure telesurgery systems comprising healthcare, surgical robots, traditional telesurgery systems, and the role of artificial intelligence to deal with the …

Skin Lesion Segmentation By Using Object Detection Networks, Deeplab3+, And Active Contours, Fatemeh Bagheri, Mohammad Jafar Tarokh, Majid Ziaratban

Turkish Journal of Electrical Engineering and Computer Sciences

Developing an automatic system for detection, segmentation, and classification of skin lesions is very useful to aid well-timed diagnosis of skin diseases. Lesion segmentation is a crucial task for automated diagnosis of skin cancers, as it affects significantly the accuracy of the subsequent steps. Varieties in sizes and locations of lesions, and the lesions with low-contrast boundaries make this task very challenging. In this paper, a three-stage CNN-based method is presented for accurate segmentation of lesions from dermoscopic images. At the first step, normalization, approximate locations and sizes of lesions are estimated. Due to the importance of the normalization stage, …

Mocmin: Convex Inferring Of Modular Low-Rank Contact Networks Over Covid Diffusion Data, Emre Sefer

Turkish Journal of Electrical Engineering and Computer Sciences

SEIR (which consists of susceptible, exposed, infected, and recovered states) is a common diffusion model which could model different disease propagation dynamics across various domains such as influenza and COVID diffusion. As a motivation, across these domains, observing the node states is relatively easier than observing the network edges over which the diffusion is taking place, or it may not even be possible to observe the underlying network. This paper focuses on the problem of predicting modular low-rank human contact network edges only if a SEIR diffusion dynamics spreading among the human on their contact network can be observed. Such …

Load2load: Day-Ahead Load Forecasting At Aggregated Level, Mustafa Berkay Yilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

A reliable and accurate short-term load forecasting (STLF) helps utilities and energy providers deal with the challenges posed by supply and demand balance, higher penetration of renewable energies and the development of electricity markets with increasingly complex pricing strategies in future smart grids. Recent advances in deep learning have been successively utilized to STLF. However, there is no certain study that evaluates the performances of different STLF methods at an aggregated level on different datasets with different numbers of daily measurements.In this study, a deep learning STLF architecture called Load2Load is proposed for day-ahead forecasting. Different forecasting methods have been …

Monte-Carlo Method Based Simulations For Photothermal Mucosa Coagulation With Accurate Depth Limits, Merve Türker Burhan, Serhat Tozburun

Turkish Journal of Electrical Engineering and Computer Sciences

The mucosa layer, the innermost layer of the gastrointestinal (GI) system, is of great importance in carcinogenesis since most cancerous tissues occur as superficial lesions. Although various treatment strategies exist, the main difficulty in eradicating lesions is unintentional damage to healthy tissues with the uncontrolled depth of treatment. This study proposes a computer modeling approach for simulating depth-resolved photothermal (laser) mucosal coagulation therapy. Computer modeling mimics the thermal dynamics of mucosal tissue to characterize the total heat energy required for successful superficial coagulation, which can be controlled by the scan rate, scan time, output power, and beam diameter of the …

Identification Of Initial Events Of Cascading Failures Using Graph Theory Methods, Mojtaba Fekri, Javad Nikoukar, Gevork Babamalek Gharehpetian

Turkish Journal of Electrical Engineering and Computer Sciences

In power systems, the unintentional outage of a grid element can lead to overload and outage of other equipment and, through a domino effect, all or a large part of a power system may collapse. The resulting events are called cascading, consecutive, or sequential failures. So far, various methods have been proposed to identify the initial events of cascading failures with different levels of accuracy and computational load. In this paper, an effective approach is employed which, by calculating the maximum flow of independent paths between generators and loads in the network graph, identifies the critical lines and transformers of …

Application Of Hierarchical Clustering On Electricity Demand Of Electric Vehicles For Gep Problems, Seyedkazem Afghah, Hati̇ce Teki̇ner Moğulkoç, Bi̇jan Bi̇bak

Turkish Journal of Electrical Engineering and Computer Sciences

Increasing fossil fuel consumption and consequently the effects of greenhouse gases (GHGs) on the environment and economy are a major concern for all nations and governments. Electric vehicles (EVs) with plug-in capabilities have the potential to ease such problems. However, the extracted power from the grid for charging the EVs' batteries will significantly impact daily power demand. To satisfy the increasing demand and ensure generation capacity adequacy, the generation expansion planning (GEP) problem is solved to determine the investment decisions for electricity generation sources. Even though there are no centralized utilities for generation planning in most markets, there is still …

Detection And Classification Of White Blood Cells With An Improved Deep Learning-Based Approach, Fatma Akalin, Nejat Yumuşak

Turkish Journal of Electrical Engineering and Computer Sciences

The analysis of white blood cells, which defend the body against deadly infections and disease-causing substances, is an important issue in the medical world. The concentrations of these cells in the blood, examined in 5 classes, i.e. monocytes, eosinophils, basophils, lymphocytes, and neutrophils, vary according to the types of diseases in the body. The peripheral blood smear is widely used to analyze blood cells. Manual evaluation of this method is laborious and time-consuming. At the same time, many environmental and humanistic parameters affect the method's performance. Therefore, in the presented study, a real-time detection process is realized. Firstly, YOLOv5s, YOLOv5x, …

Affective States Classification Performance Of Audio-Visual Stimuli From Eeg Signals With Multiple-Instance Learning, Yaşar Daşdemi̇r, Rüstem Özakar

Turkish Journal of Electrical Engineering and Computer Sciences

Throughout various disciplines, emotion recognition continues to be an essential subject of study. With the advancement of machine learning methods, accurate emotion recognition from different data modalities (facial images, brain EEG signals) has become possible. Success of EEG-based emotion recognition systems depends on efficient feature extraction and pre/postprocessing of signals. Main objective of this study is to analyze the efficacy of multiple-instance learning (MIL) on postprocessing features of EEG signals using three different domains (time, frequency, time-frequency) for human emotion classification. Methods and results are presented for single-trial classification of valence (V), arousal (A), and dominance (D) ratings from EEG …

Design Of Arbitrary Planar Optical Devices With Full Phase Control Using Nanoimprinting Of Refractive Index, Matthew Panipinto

All Theses

Planar optical devices offer a lightweight solution to the constraints found in traditional optical devices. While subwavelength patterning of optics offers attractive performance and size, traditional fabrication methods demand a trade-off between resolution and throughput that presents a significant hurdle for the widespread use of subwavelength devices. Nanoimprinting of refractive index (NIRI) is a novel fabrication method pioneered in previous work that offers promise in mitigating the throughput issues that hamstring traditional fabrication methods. However, NIRI has not been shown to impart full $2\pi$ phase control in planar optical devices, nor has a method for fabricating arbitrary designs using the …

Selected Topics Of The Past Thirty Years In Ocean Acoustics, Michael D. Collins, Altan Turgut, Michael J. Buckingham, Peter Gerstoft, Martin Siderius

Electrical and Computer Engineering Faculty Publications and Presentations

This paper reviews some of the highlights of selected topics in ocean acoustics during the thirty years that have passed since the founding of the Journal of Theoretical and Computational Acoustics. Advances in computational methods and computers helped to make computational ocean acoustics a vibrant area of research during that period. The parabolic equation method provides an unrivaled combination of accuracy and efficiency for propagation problems in which the bathymetry, sound speed, and other environmental parameters vary in the horizontal directions. The extension of this approach to cases involving layers that support shear waves has been an active area …

Iris Detection Authenticator, Nathan D. Tang, Bryan K. Chau

Electrical Engineering

The development of iris biometric identification recognition is presented. Iris recognition differs from other methods because data acquisition is non-physical and is more accessible. It has been proven that the iris does not change as an individual ages and is well protected from external damages due to the eyelid and cornea, acting as a shield to the iris. In addition, the iris is almost impossible to forge due to its complex patterns and the current limitations in technology. Using Canny Edge Detection, Hough Transform, rubber-sheet normalization, Histogram of Gradient feature extraction, and the MultiMedia University iris database as our subjects, …

Modeling And Validation Of The Thermoelectric Generator With Considering The Change Of The Seebeck Effect And Internal Resistance, Mehmet Ali̇ Üstüner, Hayati̇ Mamur, Sezai̇ Taşkin

Turkish Journal of Electrical Engineering and Computer Sciences

Thermoelectric generators (TEGs) produce power in direct proportion to the temperature difference between their surfaces. The Seebeck coefficient and internal resistance of the thermoelements (TEs) that make up the TEGs change depending on the temperature change. In simulation studies, it is seen that these two values are kept constant. However, this situation prevents approaching the data of TEG in real applications. In this study, a TEG Simulink/MATLAB ® model has been developed to capture real TEG module data, which considers changing of both the Seebeck coefficient and the internal resistance depending on the temperature difference change. To achieve this aim, …

Asking The Right Questions To Solve Algebraic Word Problems, Ege Yi̇ği̇t Çeli̇k, Zeynel Orulluoğlu, Ridvan Mertoğlu, Selma Teki̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Word algebra problems are among challenging AI tasks as they combine natural language understanding with a formal equation system. Traditional approaches to the problem work with equation templates and frame the task as a template selection and number assignment to the selected template. The recent deep learning-based solutions exploit contextual language models like BERT and encode the natural language text to decode the corresponding equation system. The proposed approach is similar to the template-based methods as it works with a template and fills in the number slots. Nevertheless, it has contextual understanding because it adopts a question generation and answering …

Multi-Robot Symbolic Task And Motion Planning Leveraging Human Trust Models: Theory And Applications, Huanfei Zheng

All Dissertations

Multi-robot systems (MRS) can accomplish more complex tasks with two or more robots and have produced a broad set of applications. The presence of a human operator in an MRS can guarantee the safety of the task performing, but the human operators can be subject to heavier stress and cognitive workload in collaboration with the MRS than the single robot. It is significant for the MRS to have the provable correct task and motion planning solution for a complex task. That can reduce the human workload during supervising the task and improve the reliability of human-MRS collaboration. This dissertation relies …

Disturbance-Observer Based Control For Pwm Rectifiers Without Dc Voltage Oscillations Under Unbalanced Grid Conditions, Mohammed Samer Al-Razehi

Theses

A three-phase controlled rectifier is a power electronic converter that employs the grid voltages as an input to produce a constant dc voltage at its output through the use of a capacitor, known as dc-link capacitor. However, the switching devices of power converters can create harmonics in the grid current, which mandates the need for filters to ensure high-quality grid current. This explains why the power converter is normally connected to the grid using passive filters such as L filter or LCL filter. The L filter is normally preferred over LCL filter to reduce harmonic distortions in grid currents as …

Piezoelectric Enhanced Noninvasive Laser-Based Detection Of Multiple Vital Signs, Ahmed Saeed Dabi

Theses

In this study, a method for concurrent measurement of heart rate (HR) respiration rate (RR) and blood pressure (BP) using movements of the chest wall is proposed. Unlike conventional approaches that use only laser, in this approach a laser source is used to collect the piezoelectric sensor output without the need for probing. The chest wall movements are transduced using an optical ODSL 8 sensor and a piezoelectric taped to the patient’s chest. Measurement data is used for development of algorithms for estimation of HR, RR and BP. Next measurements are taken while the subjects are breathing and holding their …