Computer Engineering Commons^™

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 …

Beyond Just Money Transactions: Redesigning Digital Peer-To-Peer Payments For Social Connections, Lingyuan Li

All Dissertations

Financial activities, such as the exchange of money between individuals, have long been considered a crucial aspect of how people build and maintain their interpersonal relationships (i.e., a strong, deep, or close association/acquaintance between two or more people) with individuals they know because money is a sensitive social construct. In particular, over the past decade, how to conduct, manage, and experience money exchanges and processes between individuals has been dramatically transformed due to the increasing popularity of digital peer-to-peer (P2P) payment services (i.e., performing one to one online money transactions via a digital device). In this sense, digital P2P payments …

Enhanced Mobile Networking Using Multi-Connectivity And Packet Duplication In Next-Generation Cellular Networks, Prabodh Mishra

All Dissertations

Modern cellular communication systems need to handle an enormous number of users and large amounts of data, including both users as well as system-oriented data. 5G is the fifth-generation mobile network and a new global wireless standard that follows 4G/LTE networks. The uptake of 5G is expected to be faster than any previous cellular generation, with high expectations of its future impact on the global economy. The next-generation 5G networks are designed to be flexible enough to adapt to modern use cases and be highly modular such that operators would have the flexibility to provide selective features based on user …

Culture In Computing: The Importance Of Developing Gender-Inclusive Software, Creighton France

Computer Science and Computer Engineering Undergraduate Honors Theses

The field of computing as we know it today exists because of the contributions of numerous female mathematicians, computer scientists, and programmers. While working with hardware was viewed as “a man’s job” during the mid-20th century, computing and programming was viewed as a noble and high-paying field for women to occupy. However, as time has progressed, the U.S. has seen a decrease in the number of women pursuing computer science. The idea that computing is a masculine discipline is common in the U.S. today for reasons such as male-centered marketing of electronics and gadgets, an inaccurate representation of what it …

Svar: A Virtual Machine For Portable Code On Reconfigurable Accelerators, Nathaniel Fredricks

Computer Science and Computer Engineering Undergraduate Honors Theses

The SPAR-2 array processor was designed as an overlay architecture for implementation on Xilinx Field Programmable Gate Arrays (FPGAs). As an overlay, the SPAR-2 array processor can be configured to take advantage of the specific resources available on different FPGAs. However once configured, the SPAR-2 requires programmer’s to have knowledge of the low level architecture, and write platform-specific code. In this thesis SVAR, a hardware/software co-designed virtual machine, is proposed that runs on the SPAR-2. SVAR allows programmers to write portable, platform-independent code once and have it interpreted for any specific configuration. Results are presented that verify the virtual machine …

Laying The Foundation For A Miniatuairzed Scada Testbed To Be Built At Csusb, Ryan Perera

Electronic Theses, Projects, and Dissertations

This culminating experience sought to lay the foundation for a miniaturized physical SCADA testbed to be built at California State University San Bernardino to enable students to apply the cybersecurity knowledge, skills and abilities in a fun and engaging environment while learning about what SCADA is, how it works, and how to improve the security of it. This project was conducted in response to a growing trend of cybersecurity attacks that have targeted our critical infrastructure systems through SCADA systems which are legacy systems that manage critical infrastructure systems within the past 10 years. Since SCADA systems require constant availability, …

Probabilistic Verification For Modular Network-On-Chip Systems, Jonah W. Boe

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Modeling physical systems with formal analysis tools can help in the design of more fault-proof systems, by helping to determine if unpredictable or unwanted behavior may occur. Probabilistic verification further advances such processes, by providing quantitative information about the system. More complex systems can especially benefit from formal modeling and verification, as testing the physical system in every possible condition manually, can be extremely complex, and often impossible.

There is a growing interest in the application of Network-on-Chip (NoC) systems. NoCs can help simplify communication between the subsystems of many technologies, including the ever more complex multicore processors being produced. …

Meat Quality Prediction Using Machine Learning, Rohit Buddiga

Electronic Theses, Projects, and Dissertations

Meat quality is an essential aspect of the food industry. However, traditional methods of meat quality prediction have limitations in terms of accuracy, cost, and time efficiency. This project focused on utilizing advanced Deep learning and Machine learning algorithms to develop- machine learning models that could predict the freshness (or spoilage) of meat with a 100% accuracy, based on image data. In addition to accuracy, this study emphasizes the significance of speed and time in selecting the optimal machine learning model. The research questions are: Q1. What hybrid neural networks should be used to predict freshness? Q2. How do hybrid …

Leveraging Blockchain Technology For Sla Enforcement In Health Care Cloud Partnerships, Shivani Uday Jahagirdar

Electronic Theses, Projects, and Dissertations

The healthcare industry is rapidly adopting cloud-based solutions to improve operational efficiency and patient outcomes. However, healthcare cloud partnerships often face challenges related to the lack of scalability, trust, and Service Level Agreement (SLA) enforcement, and has a notable impact on consumer care quality. To address this issue, the study proposed leveraging blockchain technology to enhance SLA enforcement by using smart contracts in health care cloud partnerships for small and medium-sized facilities. The research questions were: Q.1 What are the current challenges facing small to medium sized healthcare facilities in enforcing SLAs in cloud partnerships? Q.2 How can BC-based smart …

Guided Data Augmentation For Improved Semi-Supervised Image Classification In Low Data Regime., Fadoua Khmaissia

Electronic Theses and Dissertations

Deep learning models have achieved state of the art performances, especially for computer vision applications. Much of the recent successes can be attributed to the existence of large, high quality, labeled datasets. However, in many real-world applications, collecting similar datasets is often cumbersome and time consuming. For instance, developing robust automatic target recognition models from infrared images still faces major challenges. This is mainly due to the difficulty of acquiring high resolution inputs, sensitivity to the thermal sensors' calibration, meteorological conditions, targets' scale and viewpoint invariance. Ideally, a good training set should contain enough variations within each class for the …

Radic Voice Authentication: Replay Attack Detection Using Image Classification For Voice Authentication Systems, Hannah Taylor

Undergraduate Honors Theses

Systems like Google Home, Alexa, and Siri that use voice-based authentication to verify their users’ identities are vulnerable to voice replay attacks. These attacks gain unauthorized access to voice-controlled devices or systems by replaying recordings of passphrases and voice commands. This shows the necessity to develop more resilient voice-based authentication systems that can detect voice replay attacks.

This thesis implements a system that detects voice-based replay attacks by using deep learning and image classification of voice spectrograms to differentiate between live and recorded speech. Tests of this system indicate that the approach represents a promising direction for detecting voice-based replay …

Protecting The Infrastructure Of Michigan: Analyzing And Understanding Internet Infrastructure, Samuel Blaser, Travis Munyer, Damian Ramirez, Lester Juarez, Jackson Servant

Theses/Capstones/Creative Projects

The Michigan Army National Guard DCOE is hoping to increase their understanding of the physical, electrical, protocol, and logical topography of internet service. In order to understand the infrastructure of the internet, information must be collected on its pieces. By studying, describing, and illustrating the infrastructure of the global internet we can develop hardening tactics, improve user training, and develop contingency plans in the case of an attack. The research is focused on where data lives, locating data centers in the region, identifying global infrastructure and who owns it, and potential for hardening. An interactive map has been created in …

Vanet Applications Under Loss Scenarios & Evolving Wireless Technology, Adil Alsuhaim

All Dissertations

In this work we study the impact of wireless network impairment on the performance of VANET applications such as Cooperative Adaptive Cruise Control (CACC), and other VANET applications that periodically broadcast messages. We also study the future of VANET application in light of the evolution of radio access technologies (RAT) that are used to exchange messages. Previous work in the literature proposed fallback strategies that utilizes on-board sensors to recover in case of wireless network impairment, those methods assume a fixed time headway value, and do not achieve string stability. In this work, we study the string stability of a …

Enabling High Throughput And Reliable Low Latency Communication Over Vehicular Mobility In Next-Generation Cellular Networks, Snigdhaswin Kar

All Dissertations

The fifth-generation (5G) networks and beyond need paradigm shifts to realize the exponentially increasing demands of next-generation services for high throughputs, low latencies, and reliable communication under various mobility scenarios. However, these promising features have critical gaps that need to be filled before they can be fully implemented for mobile applications in complex environments like smart cities. Although the sub-6 GHz bands can provide reliable and larger coverage, they cannot provide high data rates with low latencies due to a scarcity of spectrum available in these bands. Millimeter wave (mmWave) communication is a key enabler for a significant increase in …

Analyzing The Impact Of Automation On Employment In Different Us Regions: A Data-Driven Approach, Thejaas Balasubramanian

Electronic Theses, Projects, and Dissertations

Automation is transforming the US workforce with the increasing prevalence of technologies like robotics, artificial intelligence, and machine learning. As a result, it is essential to understand how this shift will impact the labor market and prepare for its effects. This culminating experience project aimed to examine the influence of computerization on jobs in the United States and answer the following research questions: Q1. What factors affect how likely different jobs will be automated? Q2. What are the possible effects of automation on the US workforce across states and industries? Q3. What are the meaningful predictors of the likelihood of …

Improving Classification In Single And Multi-View Images, Hadi Kanaan Hadi Salman

Graduate Theses and Dissertations

Image classification is a sub-field of computer vision that focuses on identifying objects within digital images. In order to improve image classification we must address the following areas of improvement: 1) Single and Multi-View data quality using data pre-processing techniques. 2) Enhancing deep feature learning to extract alternative representation of the data. 3) Improving decision or prediction of labels. This dissertation presents a series of four published papers that explore different improvements of image classification. In our first paper, we explore the Siamese network architecture to create a Convolution Neural Network based similarity metric. We learn the priority features that …

Information-Theoretic Model Diagnostics (Infomod), Armin Esmaeilzadeh

UNLV Theses, Dissertations, Professional Papers, and Capstones

Model validation is a critical step in the development, deployment, and governance of machine learning models. During the validation process, the predictive power of a model is measured on unseen datasets with a variety of metrics such as Accuracy and F1-Scores for classification tasks. Although the most used metrics are easy to implement and understand, they are aggregate measures over all the segments of heterogeneous datasets, and therefore, they do not identify the performance variation of a model among different data segments. The lack of insight into how the model performs over segments of unseen datasets has raised significant challenges …

Ott Subscriber Churn Prediction Using Machine Learning, Needhi Devan Senthil Kumar

Electronic Theses, Projects, and Dissertations

Subscriber churn is a critical issue for companies that rely on recurring revenue from subscription-based services like the OTT platform. Machine Learning algorithms can be used to predict churn and develop targeted retention strategies to address the specific needs and concerns of at-risk subscribers. The research questions are 1) What Machine Learning algorithms are used to overcome subscriber churn? 2) How to predict subscribers’ churn in the OTT platform using Machine Learning? 3) How to retain subscribers and improve customer targeting? The dataset was collected from the Kaggle repository and implemented it into the various prediction algorithms used in previous …

Lignin Copolymer Property Prediction Using Machine Learning, Collin Larsen

Chemical Engineering Undergraduate Honors Theses

Lignin, an abundant biopolymer, is a waste byproduct of the paper and pulp industry. Despite its renewable nature and potential applicability in various products, such as plastics and composites, the development of lignin-based materials has been impeded by the cumbersome, Edisonian process of trial and error. This research proposes a novel approach to forecasting the properties of lignin-based copolymers by utilizing a recurrent neural network (RNN) based on the Keras models previously created by Tao et al. Example units of modified lignin were synthesized via esterification and amination functional group modifications. To increase the efficiency and accuracy of the prediction …

The Effects Of Social Media On Mental Health And Career Planning, Spencer A. Rowan

Honors Theses

Social media use is prevalent and necessary in society—nearly anything can be accomplished with a mobile device or smartphone. Among the US population, two thirds of American adults admit to using social media (Perrin, 2015) and in 2022, Georgiev (2023) found Americans spent an average of two and a half hours daily on social media. Furthermore, social media use is tied to mental well-being, work confidence levels, and feelings of being an imposter (Johnson et al., 2020; Uram & Skalski, 2022; Hernandez & Chalk, 2021; Myers, 2021; Ramm, 2019).

This project examined the role of social media use among college …

Connecting The Dots For Contextual Information Retrieval, Pei-Chi Lo

Dissertations and Theses Collection (Open Access)

There are many information retrieval tasks that depend on knowledge graphs to return contextually relevant result of the query. We call them Knowledgeenriched Contextual Information Retrieval (KCIR) tasks and these tasks come in many different forms including query-based document retrieval, query answering and others. These KCIR tasks often require the input query to contextualized by additional facts from a knowledge graph, and using the context representation to perform document or knowledge graph retrieval and prediction. In this dissertation, we present a meta-framework that identifies Contextual Representation Learning (CRL) and Contextual Information Retrieval (CIR) to be the two key components in …

Dynamic Scene Understanding: Pedestrian Tracking From Aerial Devices., Abdelhamid Bouzid

Electronic Theses and Dissertations

Multiple Object Tracking (MOT) is the problem that involves following the trajectory of multiple objects in a sequence, generally a video. Pedestrians are among the most interesting subjects to track and recognize for many purposes such as surveillance, and safety. In the recent years, Unmanned Aerial Vehicles (UAV’s) have been viewed as a viable option for monitoring public areas, as they provide a low-cost method of data collection while covering large and difficult-to-reach areas. In this thesis, we present an online pedestrian tracking and re-identification from aerial devices framework. This framework is based on learning a compact directional statistic distribution …

Modeling, Simulation And Control Of Microrobots For The Microfactory., Zhong Yang

Electronic Theses and Dissertations

Future assembly technologies will involve higher levels of automation in order to satisfy increased microscale or nanoscale precision requirements. Traditionally, assembly using a top-down robotic approach has been well-studied and applied to the microelectronics and MEMS industries, but less so in nanotechnology. With the boom of nanotechnology since the 1990s, newly designed products with new materials, coatings, and nanoparticles are gradually entering everyone’s lives, while the industry has grown into a billion-dollar volume worldwide. Traditionally, nanotechnology products are assembled using bottom-up methods, such as self-assembly, rather than top-down robotic assembly. This is due to considerations of volume handling of large …

Cross-Platform Development Of Wake-Up-Word, Christopher Ryan Woodle

Theses and Dissertations

The goal of this project will be to explore cross-platform implementation of Wake-Up- Word (WUW). To enable the development of future speech-based artificial intelligence applications, it is important to have robust and accessible implementations of WUW. Adoption of Unix based operating systems continues to expand for server, backend, and embedded applications, therefore a WUW implementation in Unix will become essential. As web technologies continue to grow, WUW will also need to be implemented in web, using technologies such as JavaScript and Web Assembly (WASM). This project encompasses porting the previous implementation of WUW from Microsoft Windows to Unix, building a …

Digital Simulations Of Memristors Towards Integration With Reconfigurable Computing, Ivris Raymond

Computer Science and Computer Engineering Undergraduate Honors Theses

The end of Moore’s Law has been predicted for decades. Demand for increased parallel computational performance has been increased by improvements in machine learning. This past decade has demonstrated the ever-increasing creativity and effort necessary to extract scaling improvements in CMOS fabrication processes. However, CMOS scaling is nearing its fundamental physical limits. A viable path for increasing performance is to break the von Neumann bottleneck. In-memory computing using emerging memory technologies (e.g. ReRam, STT, MRAM) offers a potential path beyond the end of Moore’s Law. However, there is currently very little support from industry tools for designers wishing to incorporate …

Reverse Engineering Post-Quantum Cryptography Schemes To Find Rowhammer Exploits, Sam Lefforge

Computer Science and Computer Engineering Undergraduate Honors Theses

Post-quantum cryptography is a necessary countermeasure to protect against attacks from quantum computer. However, the post-quantum cryptography schemes are potentially vulnerable to side channel attacks. One such method of attacking involves creating bit-flips in victim memory through a process called Rowhammer. These attacks can vary in nature, but can involve rowhammering bits to raise the encryption scheme's decryption failure rate, or modifying the scheme's random seed. With a high enough decryption failure rate, it becomes feasible to generate sufficient information about the secret key to perform a key recovery attack. This thesis proposed two attacks on proposed post-quantum cryptography algorithms, …

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 …

Fuel Prediction: Determining The Desirable Stops For The Cheapest Road Trips, Maxx Smith

Computer Science and Computer Engineering Undergraduate Honors Theses

Current technology has given rise to many advanced route-planning applications that are available for use by the general public. Gone are the days of preparing for road trips by looking at a paper map for hours on end trying to determine the correct exits or calculate the distance to be traveled. However, with the use of modern technology, there is a certain aspect of forward-thinking that is now lost with planning a road trip. One of the biggest constraints that often gets left on the backburner is deciding when and where to stop to refuel the car. This report is …

Critical Infrastructure Workforce Development Pods For Teaching Cybersecurity Using Netlab+, Gideon Sutterfield

Computer Science and Computer Engineering Undergraduate Honors Theses

As digital automation for Industrial Control Systems has grown, so has its
vulnerability to cyberattacks. The world of industry has responded effectively to this, but the world of academia is still lagging as its emphasis is still almost entirely on information technology. Considering this, we created a workforce development pod that serves as a hands-on learning module for teaching students key cybersecurity ideas surrounding operational technology using the NETLAB+ platform. A pod serves as the virtual environment where the learning exercise takes place. This project’s implementation involved the creation of a segmented network within the pod where a student starts …

Deep Reinforcement Learning And Game Theoretic Monte Carlo Decision Process For Safe And Efficient Lane Change Maneuver And Speed Management, Shahab Karimi

All Dissertations

Predicting the states of the surrounding traffic is one of the major problems in automated driving. Maneuvers such as lane change, merge, and exit management could pose challenges in the absence of intervehicular communication and can benefit from driver behavior prediction. Predicting the motion of surrounding vehicles and trajectory planning need to be computationally efficient for real-time implementation. This dissertation presents a decision process model for real-time automated lane change and speed management in highway and urban traffic. In lane change and merge maneuvers, it is important to know how neighboring vehicles will act in the imminent future. Human driver …