Other Electrical and Computer Engineering Commons^™

Characterization Of High Temperature Optocoupler For Power Electronic Systems, David Gonzalez

Electrical Engineering Undergraduate Honors Theses

High-temperature devices have been rapidly increas due to the implementation of new technologies like silicon carbide, high-temperature ceramic, and others. Functionality under elevated temperatures can reduce signal integrity reducing the reliability of power electronic systems. This study presents an ongoing research effort to develop a high-temperature package for optocouplers to operate at higher temperature compared with commercial devices. Low temperature co-fired ceramic (LTCC) was used as the substrate. Bare die commercial LED and photodetectors were attached to the substrate and tested for functionality. Preliminary results show enhanced performance at elevated temperatures compared to a commercial optocoupler device.

Counterfeit Detection With Multispectral Imaging, Ian Spatz

Electrical Engineering Undergraduate Honors Theses

Multispectral imaging is becoming more practical for a variety of applications due to its ability to provide hyper specific information through a non-destructive analysis. Multispectral imaging cameras can detect light reflectance from different spectral bands of visible and nonvisible wavelengths. Based on the different amount of band reflectance, information can be deduced on the subject. Counterfeit detection applications of multispectral imaging will be decomposed and analyzed in this thesis. Relations between light reflectance and objects’ features will be addressed. The process of the analysis will be broken down to show how this information can be used to provide more insight …

A Swimming Open-Water Navigation Assistive Headset And Receiver, Zakk B. Rhodes

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

Open water swimming is a common activity dating back to ancient times. One challenge with open water swimming is navigation because while maintaining proper swimming technique suggests the head be in the water, it is difficult to see where one is going. Thus swimmers must bring their head out of the water periodically to sight landmarks. This work describes a solution to this problem by a design for a GPS device to assist swimmers with navigation. The swimmer can plan their own route, send it to the device, and then be guided by the device. They then will not have …

Receptive Fields Optimization In Deep Learning For Enhanced Interpretability, Diversity, And Resource Efficiency., Babajide Odunitan Ayinde

Electronic Theses and Dissertations

In both supervised and unsupervised learning settings, deep neural networks (DNNs) are known to perform hierarchical and discriminative representation of data. They are capable of automatically extracting excellent hierarchy of features from raw data without the need for manual feature engineering. Over the past few years, the general trend has been that DNNs have grown deeper and larger, amounting to huge number of final parameters and highly nonlinear cascade of features, thus improving the flexibility and accuracy of resulting models. In order to account for the scale, diversity and the difficulty of data DNNs learn from, the architectural complexity and …

Methods To Remotely Eliminate Biofilm From Medical Implants Using 2.4 Ghz Microwaves, Brett Glenn

Mechanical Engineering Undergraduate Honors Theses

Infections associated with biofilm growth are usually challenging to eradicate due to their high tolerance toward antibiotics [11, 12]. Biofilms often form on the inert surfaces of medically implanted devices [13]. No matter the sophistication, microbial infections can develop on all medical devices and tissue engineering constructs [12]. Related infections lead to 2 million cases annually in the U.S., costing the healthcare system over $5 billion in additional healthcare expenses [12].

Novel solutions to biofilm’s microbial colonization span the spectrum of engineering and science disciplines. Yet a practical solution still does not exist. The research presented here will explore a …

Designing A Robotic Platform For Investigating Swarm Robotics, Jonathan Gray

Senior Honors Theses

This paper documents the design and subsequent construction of a low-cost, flexible robotic platform for swarm robotics research, and the selection of appropriate swarm algorithms for the implementation of a swarm focused predominantly on target location. The design described herein is intended to allow for the construction of robots large enough to meaningfully interact with their environment while maintaining a low per-robot cost of materials and a low assembly time. The design process is separated into three stages: mechanical design, electrical design, and software design. All major design components are described in detail under the appropriate design section. The BOM …

Communication Debugging Platform, Husam Beitello

Honors Theses

More and more products are becoming “connected” devices, integrating multiple communications subsystems into their design. These subsystems increase the complexity of a design, and require extensive testing and debugging before they reach an end user. The purpose of the project was to create a prototype for a peripheral device that enables bidirectional communication between a typical smartphone and another target device communicating using the infrared, Bluetooth, and/or CAN communication protocols. Such a device could then be used to debug the behavior of a product relying on these forms of communication, by running test procedures referred to as scripts from the …

Ent1201 Introduction To Electricity For Live Entertainment Syllabus, Miguel A. Valderrama

Open Educational Resources

No abstract provided.

Aerial Base Station Deployment For Post-Disaster Public Safety Applications, Jose Antonio Matamoros Vargas

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Earthquakes and floods are constant threats to most of the countries in the world. After such catastrophes, a rapid response is needed, which includes communications not only for first responders but also for local civilians. Even though there are technologies and specialized personnel for rapid deployment, it is common that external factors will hinder the arrival of help while communication requirements are urgently required. Such communication technologies would aid tasks regarding organization and information dissemination from authorities to the civilians and vice-versa. This necessity is due to protocols and applications to allocate the number of emergency resources per location and …

Analysis Of Local Anti-Islanding Detection Methods For Photovoltaic Generators In Distribution Systems, Milad Kahrobaee

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

In the current decade, technology innovations and cost reduction of inverter-based Distributed Energy Resources (DERs) have led to higher integration of distributed energy storage and photovoltaic (PV) solar power systems. Increasing growth in PV penetration to the distribution system can raise operational and safety concerns especially in case of an unintended islanding.

In general, standards require distributed generators (DGs) to detect islanding from the main grid and cease to energize the local system. Multiple methods have been introduced in the literature to detect these islands reliably and quickly. In order to connect an inverter to distribution system, inverter should pass …

Improved Fabrication For Micromirror Arrays, Enoc Flores

Theses and Dissertations

Micromirror devices which consisted of one SU-8 2050 layer, two different exposures, and a series of metal depositions were constructed and evaluated. By varying the exposure, a micromirror structure was fabricated with different thicknesses, a ratio of 1.083 µm/(mJ/cm2) was found. The initial design consisted of four layers. The pillar was made of one SU-8 layer, and the top portion had three layers in the following order: gold, SU-8, and gold. This design could not be released and did not have characteristics of a flat and conformal reflective surface. Several variations of the initial design were explored and all of …

Confirmation Bias Estimation From Electroencephalography With Machine Learning, Micah Villarreal

Theses and Dissertations

Cognitive biases are known to plague human decision making and can have disastrous effects in the fast-paced environments of military operators. Traditionally, behavioral methods are employed to measure the level of bias in a decision. However, these measures can be hindered by a multitude of subjective factors and cannot be collected in real-time. This work investigates enhancing the current measures of estimating confirmation bias with additional behavior patterns and physiological variables to explore the viability of real-time bias detection. Confirmation bias in decisions is estimated by modeling the relationship between Electroencephalography (EEG) signals and behavioral data using machine learning methods.

A State-Of-The-Art Survey On Deep Learning Theory And Architectures, Md Zahangir Alom, Tarek M. Taha, Christopher Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Mahmudul Hasan, Brian C. Van Essen, Abdul A. S. Awwal, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to most traditional application domains, as well as some new areas that present more opportunities. Different methods have been proposed based on different categories of learning, including supervised, semi-supervised, and un-supervised learning. Experimental results show state-of-the-art performance using deep learning when compared to traditional machine learning approaches in the fields of image processing, computer vision, speech recognition, machine translation, art, medical imaging, medical information processing, robotics and control, bioinformatics, natural language …

Development Of A Myoelectric Detection Circuit Platform For Computer Interface Applications, Nickolas Andrew Butler

Master's Theses

Personal computers and portable electronics continue to rapidly advance and integrate into our lives as tools that facilitate efficient communication and interaction with the outside world. Now with a multitude of different devices available, personal computers are accessible to a wider audience than ever before. To continue to expand and reach new users, novel user interface technologies have been developed, such as touch input and gyroscopic motion, in which enhanced control fidelity can be achieved. For users with limited-to-no use of their hands, or for those who seek additional means to intuitively use and command a computer, novel sensory systems …

Applications Of Supervised Machine Learning In Autism Spectrum Disorder Research: A Review, Kayleigh K. Hyde, Marlena N. Novack, Nicholas Lahaye, Chelsea Parlett-Pelleriti, Raymond Anden, Dennis R. Dixon, Erik Linstead

Engineering Faculty Articles and Research

Autism spectrum disorder (ASD) research has yet to leverage "big data" on the same scale as other fields; however, advancements in easy, affordable data collection and analysis may soon make this a reality. Indeed, there has been a notable increase in research literature evaluating the effectiveness of machine learning for diagnosing ASD, exploring its genetic underpinnings, and designing effective interventions. This paper provides a comprehensive review of 45 papers utilizing supervised machine learning in ASD, including algorithms for classification and text analysis. The goal of the paper is to identify and describe supervised machine learning trends in ASD literature as …

Active Recall Networks For Multiperspectivity Learning Through Shared Latent Space Optimization, Theus Aspiras, Ruixu Liu, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Given that there are numerous amounts of unlabeled data available for usage in training neural networks, it is desirable to implement a neural network architecture and training paradigm to maximize the ability of the latent space representation. Through multiple perspectives of the latent space using adversarial learning and autoencoding, data requirements can be reduced, which improves learning ability across domains. The entire goal of the proposed work is not to train exhaustively, but to train with multiperspectivity. We propose a new neural network architecture called Active Recall Network (ARN) for learning with less labels by optimizing the latent space. This …

Deep Temporal Convolutional Networks For Short-Term Traffic Flow Forecasting, Wentian Zhao, Yanyun Gao, Tingxiang Ji, Xili Wan, Feng Ye, Guangwei Bai

Electrical and Computer Engineering Faculty Publications

To reduce the increasingly congestion in cities, it is essential for intelligent transportation system (ITS) to accurately forecast the short-term traffic flow to identify the potential congestion sites. In recent years, the emerging deep learning method has been introduced to design traffic flow predictors, such as recurrent neural network (RNN) and long short-term memory (LSTM), which has demonstrated its promising results. In this paper, different from existing work, we study the temporal convolutional network (TCN) and propose a deep learning framework based on TCN model for short-term city-wide traffic forecast to accurately capture the temporal and spatial evolution of traffic …

Multi-Column Neural Networks And Sparse Coding Novel Techniques In Machine Learning, Ammar O. Hoori

Theses and Dissertations

Accurate and fast machine learning (ML) algorithms are highly vital in artificial intelligence (AI) applications. In complex dataset problems, traditional ML methods such as radial basis function neural network (RBFN), sparse coding (SC) using dictionary learning, and particle swarm optimization (PSO) provide trivial results, large structure, slow training, and/or slow testing. This dissertation introduces four novel ML techniques: the multi-column RBFN network (MCRN), the projected dictionary learning algorithm (PDL) and the multi-column adaptive and non-adaptive particle swarm optimization techniques (MC-APSO and MC-PSO). These novel techniques provide efficient alternatives for traditional ML techniques. Compared to traditional ML techniques, the novel ML …

Effects Of Correlation Of Channel Gains On The Secrecy Capacity In The Gaussian Wiretap Channel, Abhishek Lokur

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Secrecy capacity is one of the most important characteristic of a wireless communication channel. Therefore, the study of this characteristic wherein the system has correlated channel gains and study them for different line-of-sight (LOS) propagation scenarios is of ultimate importance.

The primary objective of this thesis from the mathematical side is to determine the secrecy capacity (SC) for correlated channel gains for the main and eavesdropper channels in a Gaussian Wiretap channel as a function from main parameters (μ, Σ, ρ). f(h₁, h₂) is the joint distribution of the two channel gains at channel use (h …

Recurrent Residual U-Net For Medical Image Segmentation, Md Zahangir Alom, Christopher Yakopcic, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep …

A Survey Of Techniques For Mobile Service Encrypted Traffic Classification Using Deep Learning, Pan Wang, Xuejiao Chen, Feng Ye, Zhixin Sun

Electrical and Computer Engineering Faculty Publications

The rapid adoption of mobile devices has dramatically changed the access to various net- working services and led to the explosion of mobile service traffic. Mobile service traffic classification has been a crucial task that attracts strong interest in mobile network management and security as well as machine learning communities for past decades. However, with more and more adoptions of encryption over mobile services, it brings a lot of challenges about mobile traffic classification. Although classical machine learning approaches can solve many issues that port and payload-based methods cannot solve, it still has some limitations, such as time-consuming, costly handcrafted …

On The Distortion Of Uwb Circularly Polarized Time-Domain Pulses In Presence Of Rotation, Adam Narbudowicz, Janusz Przewocki, Max Ammann

Conference Papers

The paper provides a first theoretical study on the effect of rotational Doppler on circularly polarized pulsed communication. Despite the circularly polarized communication being considered immune to signal fading due to rotary misalignment, such misalignment will cause a frequency-invariant phase-shift. This phase shift will significantly distort the shape of the time-domain pulse. The property can be used for integration of orientation sensing into well establish pulse-based localization. However, it has also the potential to distort communication for some pulse-modulated UWB systems.

Special Issue On Low Temperature Plasma Jets, Mounir Laroussi

Electrical & Computer Engineering Faculty Publications

[Introduction] Low temperature plasma jets are unique plasma sources capable of delivering plasma outside of the confinement of electrodes and away from gas enclosures/chambers. With these jets plasma can be easily delivered to a target located at some distance from the plasma generation region [1].

The Smartbobber, Zachary Pyle, Nick Spoutz, Zachary Hutson, Ryan Pascal

Williams Honors College, Honors Research Projects

In short, the fishing bobber connects to a smartphone app (also designed by members on the team) to notify the user of fish bite data via Bluetooth connection. Additionally, the smartBobber is able to set the hook on fish autonomously and alert the user when it does so. This is possible by the use of a linear solenoid that is spring loaded. Circuitry on the bobber detects the pull distance on the plunger of the solenoid and transmits this data to the user in real time. Once the solenoid has passed a certain pull threshold, the solenoid completes a 12V …

Smart Garage Opener, Jacob Wasson

Williams Honors College, Honors Research Projects

The purpose of this research project was to design an anti-theft device that interfaces with a standard garage door opener to allow packages to easily be delivered into a garage in a safe and secure manner. Primary functionality of the device is to use a package’s tracking number and corresponding barcode to open and close a garage door to a preset height so that a package can be delivered inside the garage before it closes. My contribution to the project revolved around the programming and board design of the microcontroller circuit that controls the input and output signals of the …

Ict-Enabled Control And Energy Management Of Community Microgrids For Resilient Smart Grid Operation, Mahmoud Saleh

Dissertations and Theses

Our research has focused on developing novel controllers and algorithms to enhance the resilience of the power grid and increase its readiness level against major disturbances.

The U.S. power grid currently encounters two main challenges: (1) the massive and extended blackouts caused by natural disasters, such as hurricane Sandy. These blackouts have raised a national call to explore innovative approaches for enhanced grid resiliency. Scrutinizing how previous blackouts initiated and propagated throughout the power grid, the major reasons are lack of situational awareness, lack of real-time monitoring and control, underdeveloped controllers at both the transmission and distribution levels, and lack …

Sniffing, Decoding And Decryption Of Gsm Signals Using Low Cost Hardware And Open-Source Software, Muhammad Talha Choudhry

Dissertations and Theses

We have participated in the creation of almost two terabytes of tables aimed at cracking A5/1, the most common ciphering algorithm used in GSM. Given 114-bit of known plaintext, we are able to recover the session key with a hit rate of 19%. The tables are expected to be unique as they provide the best coverage yet known to the authors and research workers and they are the first step in a real-world passive attack against GSM. An initial investigation and analysis into the air interface of GSM were performed, from both a theoretical and practical point of view. These …

Internet Of Things: Architecture And Services For Healthcare, Ankita Suvagia Ms.

Dissertations and Theses

Internet of Things (IoT) is a recent prominent collaboration of various technologies that enables spatially distributed devices (“things”) to sense, communicate and share information, thus generating a variety of applications and services in Healthcare. IoT is implemented in multiple domains like Smart city, energy and smart grid, Smart home, weather forecasting, Agriculture, Market and Transportation, Manufacturing and testing industries, Healthcare and many more. IoT serves the purpose of making tasks more efficient and productive and at the same time ensuring quality and reliability. IoT technologies provide an enabling framework for inter-connecting devices, systems, and services that go beyond Machine-to-Machine scenarios …

Optimal Compression Of Point Clouds, Benjamin Robert Smith

Graduate Theses, Dissertations, and Problem Reports (ETD)

Image-based localization is a crucial step in many 3D computer vision applications, e.g., self-driving cars, robotics, and augmented reality among others. Unfortunately, many image-based-localization applications require the storage of large scenes, and many camera pose estimators struggle to scale when the scene representation is large. To alleviate the aforementioned problems, many applications compress a scene representation by reducing the number of 3D points of a point cloud. The state-of-the-art compresses a scene representation by using a K-cover-based algorithm. While the state-of-the-art selects a subset of 3D points that maximizes the probability of accurately estimating the camera pose of a new …

Danger-Aware Resource Management In V2x Network, Tsigigenet Dessalgn

College of Graduate Studies: Theses & Dissertations

IEEE 802.11p is one of the key technologies that enable dedicated short-range communications (DSRC) in intelligent transportation system (ITS) for safety on the road. The main challenge in vehicular communication is the large amount of data to be processed. As vehicle density and velocity increases, the data to be transmitted also increases. We proposed a protocol that reduces the number of data to be transmitted at every second according to the level of danger that the transmitter vehicle experiences. The proposed protocol measures inter-vehicle distance, as the representative of the danger of a vehicle, to determine the priority for transmission. …