Digital Commons Network^™

Deep Reinforcement Learning Based Path-Planning For Multi-Agent Systems In Advection-Diffusion Field Reconstruction Tasks, Deepak Talwar

Master's Theses

Many environmental processes can be represented mathematically using spatial-temporal varying partial-differential equations. Timely estimation and prediction of processes such as wildfires is critical for disaster management response, but is difficult to accomplish without the availability of a dense network of stationary sensors. In this work, we propose a deep reinforcement learning-based real-time path-planning algorithm for mobile sensor networks traveling in a formation through a spatial-temporal varying advection-diffusion field for the task of field reconstruction. A deep Q-network (DQN) agent is trained on simulated advection-diffusion fields to direct the mobile sensor network to travel along information-rich trajectories. The field measurements made …

Detecting Feeding And Estimating The Energetic Costs Of Diving In California Sea Lions (Zalophus Californianus) Using 3-Axis Accelerometers, Mason Russell Cole

Master's Theses

Knowledge of when animals feed and the energetic costs of foraging is key to understanding their foraging ecology and energetic trade-offs. Despite this importance, our ability to collect these data in marine mammals remains limited. In this thesis, I address knowledge gaps in both feeding detection and fine-scale diving energetic costs in a model species, the California sea lion (Zalophus californianus). I first developed and tested an analysis method to accurately detect prey capture using 3-axis accelerometers mounted on the head and back of two trained sea lions. An acceleration signal pattern isolated from a ‘training’ subset of synced video …

Lstm-Enabled Level Curve Tracking In Scalar Fields Using Multiple Mobile Robots, Kunj J. Parikh

Master's Theses

Autonomous mobile sensor networks are ideal candidates for exploring large-scaleunknown fields with tasks ranging from source seeking, level curve tracking, mapping an unknown field, and many more. In this work, we investigate the problem of level curve tracking in unknown scalar fields using a limited number of mobile sensors. The level curve tracking problem has been studied in many applications such as monitoring the propagation of fire boundaries and the algae blooms. We design and implement a long short term memory (LSTM) enabled control strategy for a mobile sensor network to detect and track the desired level curve. We develop …

A Meta-Analysis Of Fmri Studies On Emotion Processing In Major Depressive Disorder, Madison Morocco

Master's Theses

The processing of an emotional stimulus involves a multi-step process that includes appraising and identifying a stimulus as well as producing an affective state in response. Many individuals with depressive disorders such as major depressive disorder (MDD) experience impairments related to emotion processing, likely caused by changes in the structure and function of brain regions important for emotion processing. However, the precise neural differences underlying emotion processing impairments in MDD remain unclear given conflicting findings in the neuroimaging literature. This lack of clarity has hindered the development of novel neurostimulation treatments for MDD, which require targeting of specific brain areas. …

The Impact Of Compensation On Engagement And Organizational Tenure: The Moderating Role Of Perceived Organizational Support, Alexis Johnson

Master's Theses

Compensation is a crucial tool utilized by companies to help attract, retain, and motivate employees. However, previous research has overlooked the ways in which compensation might add value to important employee outcomes such as engagement and organizational tenure. Therefore, this present study aimed to close this gap by examining the relationship between pay level and engagement, as well as pay level and organizational tenure. It was hypothesized that higher pay levels would increase the engagement dimensions of dedication, vigor, and absorption in an employee, and that higher pay levels would increase organizational tenure in an individual. It also sought to …

Influence Of Social Circles On User Recommendations, Chaitanya Krishna Kasaraneni

Master's Theses

Recommender systems are powerful tools that filter and recommend content relevant to a user. One of the most popular techniques used in recommender systems is collaborative filtering. Collaborative filtering has been successfully incorporated in many applications. However, these recommendation systems require a minimum number of users, items, and ratings in order to provide effective recommendations. This results in the infamous cold start problem where the system is not able to produce effective recommendations for new users. In recent times, with escalation in the popularity and usage of social networks, people tend to share their experiences in the form of reviews …

A Silicon Valley Life: A Silicon Valley Love Story, Sharon Simonson

Master's Theses

In the last three decades, Silicon Valley has become one of the world’s most watched and imitated communities. Daily news reporters, long-form journalists, cinema and television-programming producers have crafted a public image, but it represents nothing of the lives of hundreds of thousands of Valley residents. These fabrications obscure and diminish our complex human profile and reduce our uniquely beautiful geography to a place to generate financial profits, with all the damaging disregard such attitudes foster. The essays of A Silicon Valley Life: A Silicon Valley Love Story seek to show our true self: our rich mix of people drawn …

Nuclear Thermal Rocket Engine With A Toroidal Aerospike Nozzle, Kyle Stewart

Master's Theses

This thesis describes the coupling of a nuclear thermal rocket engine with a toroidal aerospike nozzle. The coupling of the two systems consists of two phases. The first of these phases begin with top-level systems and subsystems analysis and design of the new engine. The second phase is the analysis and characterization of the major engine systems through the use of computational fluid dynamics analysis. With the coupling of the nuclear thermal rocket engine with the aerospike nozzle, the new system will be known as the Nuclear Thermal Propulsion System. Due to the uniqueness of coupling a nuclear thermal rocket …

Prevalence Of Avoidant/Restrictive Food Intake Disorder And Association With Nutrition Status In Patients With Inflammatory Bowel Diseases, Emily Yelencich

Master's Theses

There is a large body of research on the relationship between inflammatory bowel disease (IBD) and diet; however, few conclusive, generalizable recommendations have been determined. Regardless, IBD patients often alter their normal dietary intake, which is concerning considering the prevalence of malnutrition in the IBD population. Avoidant/restrictive food intake disorder (ARFID) is a feeding disorder that was recently added to the Diagnostic and Statistical Manual of Mental Disorders and its prevalence and impact on the nutritional status of IBD patients has not previously been described. In this study ARFID risk was measured using the Nine-Item ARFID Screen and in the …

Supervisor And Coworker Support: Their Moderating Roles On The Relationship Between Diversity Climate Perceptions And Retention-Related Outcomes, Sarah Crouse

Master's Theses

The purpose of the present study was to examine perceived supervisor support and perceived coworker support as moderators of the relationship between diversity climate perceptions and retention-related outcomes (affective commitment, organizational identification, and turnover intentions). Results from a self-report survey of 150 participants showed that neither perceived supervisor support nor perceived coworker support moderated the relationship between diversity climate perceptions and these outcomes. However, the results showed diversity climate perceptions were positively related to perceived supervisor support and perceived coworker support, and independently predicted these retention-related outcomes. Results also showed that perceived supervisor support was more strongly related to these …

An Efficient Design Methodology For Complex Sequential Asynchronous Digital Circuits, Tomasz Chadzynski

Master's Theses

Asynchronous digital logic as a design alternative offers a smaller circuit area and lower power consumption but suffers from increased complexity and difficulties related to logic hazards and elements synchronization. The presented work proposes a design methodology based on the speed-independent sequential logic theory, oriented toward asynchronous hardware implementation of complex multi-step algorithms. Targeting controller-centric devices that perform data-driven non-linear execution, the methodology offers a CSP language-based controller workflow description approach and the specification of a project implementation template supported by a two-stage design process. First, the CSP layer describes complex speed-independent controller behavior offering better scalability and maintainability than …

Greenhouse Gas Emissions From Lithium-Ion Batteries Operating In California's Electrical Grid In 2019, Peter J. Hilkene

Master's Theses

This work examines the impact on greenhouse gas emissions of energy storage devices operating on the California electrical grid during the year 2019. As solar power gains a greater share in California’s energy production, tools for storing the intermittent energy produced from solar and other variable generation sources become important in continuing their growth. In this study, the impact of the deployment of energy storage capacity in California was determined using three charging and discharging strategies. The first, meeting peak net-demand with solar, looked at battery charging when solar production was highest and discharging when net-demand is highest. The second …

Influence Of Night Work On Performance During Lunar Telerobotic Operations, Zachary Luke Glaros

Master's Theses

Real-time, reactive telerobotic mission control operations require personnel to actively operate remotely controlled vehicles or robots in real time. Due to the physical separation of the vehicle from the operator, such operations present additional factors that can influence fatigue (degraded mental performance) and workload (mental and physical cost of task requirements), making it difficult to assess how long an individual can conduct operations safely. The upcoming Volatiles Investigating Polar Exploration Rover will involve remotely controlling a lunar vehicle from an Earth-based mission control station. In order to determine how long personnel could successfully maintain alertness and performance while operating a …

Inclusive Leadership, Psychological Empowerment, And Affective Organizational Commitment: A Mediated Model, Mariah Lyn Van Buskirk

Master's Theses

Inclusive leadership has become an important contextual factor to study in organizations given its impact on positive workplace outcomes. However, little is known about the ability of inclusive leadership to affect a wider range of outcomes and the various mediating mechanisms between inclusive leadership and outcomes. Therefore, the present study explored the mediating role of psychological empowerment on the relationship between inclusive leadership and affective organizational commitment. It was hypothesized that inclusive leadership would be positively related to affective organizational commitment both directly and indirectly through psychological empowerment. Results of an online survey from 189 employed individuals showed that inclusive …

Adaptive Learning Technique For Facial Recognition, Rachana Dineshkumar Bumb

Master's Theses

This research describes the adaptive learning technique for facial recognition. It is a common practice in convolutional neural network(CNN) based facial recognition to save its trained result on a large dataset and then load and apply it to ongoing facial recognition tasks. This generally used method lacks adaptation, and the ongoing evolution of new knowledge poses a key technical challenge. In this research, we propose a continued learning technique to incorporate new knowledge derived in each facial recognition process. A positive recognition with confidence score is assigned, and the image associated with this confidence is added to the image dataset …

Transfer Learning For Hyperspectral Images Utilizing Channel Selection Techniques And Ensemble Methods, Scott Daniel Vogel

Master's Theses

Hyperspectral images contain information from a wider range of the electromagnetic spectrum than natural images which gives them potential for better classification ability. However, hyperspectral datasets are typically small due to the expensive equipment needed to obtain the images, which can limit classification performance. One solution to this problem is transfer learning, in which a model trained on one dataset is reused for a separate dataset. Research has shown that transfer learning between hyperspectral datasets can give improved performance over models without transfer learning when training data are limited. Since extra hyperspectral data are not always available, the solution proposed …

Cat Tracks – Tracking Wildlife Through Crowdsourcing Using Firebase, Tracy Ho

Master's Projects

Many mountain lions are killed in the state of California every year from roadkill. To reduce these numbers, it is important that a system be built to track where these mountain lions have been around. One such system could be built using the platform-as-a-service, Firebase. Firebase is a platform service that collects and manages data that comes in through a mobile application. For the development of cross-platform mobile applications, Flutter is used as a toolkit for developers for both iOS and Android. This entire system, Cat Tracks is proposed as a crowdsource platform to track wildlife, with the current focus …

A Neat Approach To Malware Classification, Jason Do

Master's Projects

Current malware detection software often relies on machine learning, which is seen as an improvement over signature-based techniques. Problems with a machine learning based approach can arise when malware writers modify their code with the intent to evade detection. This leads to a cat and mouse situation where new models must constantly be trained to detect new malware variants. In this research, we experiment with genetic algorithms as a means of evolving machine learning models to detect malware. Genetic algorithms, which simulate natural selection, provide a way for models to adapt to continuous changes in a malware families, and thereby …

Detecting Deepfakes With Deep Learning, Eric C. Tjon

Master's Projects

Advances in generative models and manipulation techniques have given rise to digitally altered videos known as deepfakes. These videos are difficult to identify for both humans and machines. Typical detection methods exploit various imperfections in deepfake videos, such as inconsistent posing and visual artifacts. In this paper, we propose a pipeline with two distinct pathways for examining individual frames and video clips. The image pathway contains a novel architecture called Eff-YNet capable of both segmenting and detecting frames from deepfake videos. It consists of a U-Net with a classification branch and an EfficientNet B4 encoder. The video pathway implements a …

Lidar Object Detection Utilizing Existing Cnns For Smart Cities, Vinay Ponnaganti

Master's Projects

As governments and private companies alike race to achieve the vision of a smart city — where artificial intelligence (AI) technology is used to enable self-driving cars, cashier-less shopping experiences and connected home devices from thermostats to robot vacuum cleaners — advancements are being made in both software and hardware to enable increasingly real-time, accurate inference at the edge. One hardware solution adopted for this purpose is the LiDAR sensor, which utilizes infrared lasers to accurately detect and map its surroundings in 3D. On the software side, developers have turned to artificial neural networks to make predictions and recommendations with …

Multi-Agent Deep Reinforcement Learning For Walkers, Inhee Park

Master's Projects

This project was motivated by seeking an AI method towards Artificial General Intelligence (AGI), that is, more similar to learning behavior of human-beings. As of today, Deep Reinforcement Learning (DRL) is the most closer to the AGI compared to other machine learning methods. To better understand the DRL, we compares and contrasts to other related methods: Deep Learning, Dynamic Programming and Game Theory.

We apply one of state-of-art DRL algorithms, called Proximal Policy Op- timization (PPO) to the robot walkers locomotion, as a simple yet challenging environment, inherently continuous and high-dimensional state/action space.

The end goal of this project is …

End-To-End Learning Utilizing Temporal Information For Vision- Based Autonomous Driving, Dapeng Guo

Master's Projects

End-to-End learning models trained with conditional imitation learning (CIL) have demonstrated their capabilities in driving autonomously in dynamic environments. The performance of such models however is limited as most of them fail to utilize the temporal information, which resides in a sequence of observations. In this work, we explore the use of temporal information with a recurrent network to improve driving performance. We propose a model that combines a pre-trained, deeper convolutional neural network to better capture image features with a long short-term memory network to better explore temporal information. Experimental results indicate that the proposed model achieves performance gain …

Findfur: A Tool For Predicting Furin Cleavage Sites Of Viral Envelope Substrates, Christine Gu

Master's Projects

Most biologically active proteins of eukaryotic cells are initially synthesized in the secretory pathway as inactive precursors and require proteolytic processing to become functionally active. This process is performed by a specialized family of endogenous enzymes known as proproteases convertases (PCs). Within this family of proteases, the most notorious and well-research is furin. Found ubiquitously throughout the human body, typical furin substrates are cleaved at sites composed of paired basic amino acids, specifically at the consensus sequence, R-X-[K/R]-R↓. Furin is often exploited by many pathogens, such as enveloped viruses, for proteolytic processing and maturation of their proteins. Glycoproteins of enveloped …

Malware Classification With Gaussian Mixture Model-Hidden Markov Models, Jing Zhao

Master's Projects

Discrete hidden Markov models (HMM) are often applied to the malware detection and classification problems. However, the continuous analog of discrete HMMs, that is, Gaussian mixture model-HMMs (GMM-HMM), are rarely considered in the field of cybersecurity. In this study, we apply GMM-HMMs to the malware classification problem and we compare our results to those obtained using discrete HMMs. As features, we consider opcode sequences and entropy-based sequences. For our opcode features, GMM-HMMs produce results that are comparable to those obtained using discrete HMMs, whereas for our entropy-based features, GMM-HMMs generally improve on the classification results that we can attain with …

The Use Of Evidential Reasoning Model With Biomarkers In Pancreatic Cancer Prediction, Qianhui Fan

Master's Projects

In this project, an evidential reasoning model is built to amalgamate factors that could be used in early detection of pancreatic cancer. Our machine learning model outputs a probability of a given patient having prostate cancer based on various input variables. These variables include health history factors, such as smoking and medical history, technical artifacts, such as biopsy sequencing technology, and genomic biomarkers such as mutational, transcriptional and methylomic profiles, cfDNA, and copy number variation. The dataset used in this project is a part of The Cancer Genome Atlas (TCGA) project and was collected from the National Cancer Institute (NIH) …

Visualization Of Large Networks Using Recursive Community Detection, Xinyuan Fan

Master's Projects

Networks show relationships between people or things. For instance, a person has a social network of friends, and websites are connected through a network of hyperlinks. Networks are most commonly represented as graphs, so graph drawing becomes significant for network visualization. An effective graph drawing can quickly reveal connections and patterns within a network that would be difficult to discern without visual aid. But graph drawing becomes a challenge for large networks. Am- biguous edge crossings are inevitable in large networks with numerous nodes and edges, and large graphs often become a complicated tangle of lines. These issues greatly reduce …

Quantifying Deepfake Detection Accuracy For A Variety Of Natural Settings, Pratikkumar Prajapati

Master's Projects

Deep fakes are videos generated from a starting video of a person where that person's face has been swapped for someone else's. In this report, we describe our work to develop general, deep learning-based models to classify Deep Fake content. Our first experiments involved simple Convolution Neural Network (CNN)-based models where we varied how individual frames from the source video were passed to the CNN. These simple models tended to give low accuracy scores for discriminating fake versus non-fake videos of less than 60%. We then developed three more sophisticated models: one based on choosing test frames, one based on …

Malware Classification Using Lstms, Dennis Dang

Master's Projects

Signature and anomaly based detection have long been quintessential techniques used in malware detection. However, these techniques have become increasingly ineffective as malware becomes more complex. Researchers have therefore turned to deep learning to construct better performing models. In this project, we create four different long-short term memory (LSTM) models and train each model to classify malware by family type. Our data consists of opcodes extracted from malware executables. We employ techniques used in natural language processing (NLP) such as word embedding and bidirection LSTMs (biLSTM). We also use convolutional neural networks (CNN). We found that our model consisting of …

Bioinformatics Metadata Extraction For Machine Learning Analysis, Zachary Tom

Master's Projects

Next generation sequencing (NGS) has revolutionized the biological sciences. Today, entire genomes can be rapidly sequenced, enabling advancements in personalized medicine, genetic diseases, and more. The National Center for Biotechnology Information (NCBI) hosts the Sequence Read Archive (SRA) containing vast amounts of valuable NGS data. Recently, research has shown that sequencing errors in conventional NGS workflows are key confounding factors for detecting mutations. Various steps such as sample handling and library preparation can introduce artifacts that affect the accuracy of calling rare mutations. Thus, there is a need for more insight into the exact relationship between various steps of the …

Façade Improvement Programs In The San Francisco Bay Area, Liz Lange

Master's Projects

The purpose of this research project is to provide a comprehensive inventory and analysis of FIPs that currently operate in the SFBA, identify common components, analyze unique features, evaluate program goals, and determine successful practices. The intent of this study is to encourage municipalities, particularly in the SFBA, that do not operate a FIP to consider implementing one by providing a starting point and guidelines for program development. Many municipalities are unable to research FIPs due to limited staff hours and other competing priorities. Through this research, staff will be able to identify what resources are required to operate a …