Digital Commons Network^™

Adversarial Attacks On Speech Separation Systems, Kendrick Trinh

Master's Projects

Speech separation is a special form of blind source separation in which the objective is to decouple two or more sources such that they are distinct. The need for such an ability grows as speech activated device usage increases in our every day life. These systems, however, are susceptible to malicious actors. In this work, we repurpose proven adversarial attacks and leverage them against a combination speech separation and speech recognition system. The attack adds adversarial noise to a mixture of two voices such that the two outputs of the speech separation system are similarly transcribed by the speech recognition …

Robustness Of Image-Based Malware Analysis, Katrina Tran

Master's Projects

Being able to identify malware is important in preventing attacks. Image-based malware analysis is the study of images that are created from malware. Analyzing these images can help identify patterns in malware families. In previous work, "gist descriptor" features extracted from images have been used in malware classification problems and have shown promising results. In this research, we determine whether gist descriptors are robust with respect to malware obfuscation techniques, as compared to Convolutional Neural Networks (CNN) trained directly on malware images. Using the Python Image Library, we create images from malware executables and from malware that we obfuscate. We …

Differential Gene Expression Analysis Of Zebrafish Embryos Exposed To Simulated Microgravity And Insights Into Cellular Effects, Nicholas Lien

Master's Projects

Spaceflight consists of many dangers which adversely affects the health of astronauts through hazards such as microgravity and cosmic radiation. One area that is still poorly understood is how spaceflight impacts human reproductive health. This study aims to shed insight into how microgravity may impact the development of embryos. Differential gene expression analysis was performed via Jupyter Notebook and SLURM scripts and run on SJSU’s HPC server as a method of implementing NASA GeneLab’s RNA-Seq Consensus Pipeline. Data for this project utilized RNA-Seq files for early-stage embryonic zebrafish (Danio rerio), stored under GLDS-373. Gene Set Enrichment Analysis was performed to …

Understanding How The Relative Abundance Of Candida Species Impacts Transcriptional Regulation In Coculture Biofilms, Diksha Kool

Master's Projects

ABSTRACT Candida albicans and Candida glabrata are common fungal species that can change from commensal to pathogen due to their ability to form robust biofilms. Candida species are the leading cause of life-threatening conditions like Candidemia, and the existing treatments for biofilm-related infections are suboptimal. Research shows that the relative abundance of the two Candida species promotes biofilm formation, enhances pathogenicity, and increases antibiotic resistance. Thus, focusing on the importance of coculture, this paper utilizes RNA sequencing to investigate the gene expression leading to biofilm development in coculture through a time-series study.

Concept Drift And Malware Detection, Xiaoli Tong

Master's Projects

In software development, new software is often based on a previous version with some improvements or new features. A similar software development practice holds true for malware writers, that is, hackers tend to add features to existing malware and release revised versions, which can be viewed as belonging to existing malware families. Therefore, a malware family typically evolves over time. In this paper, we build on recent research that has demonstrated that malware evolution can be detected using machine learning techniques. Specifically, we account for concept drift in the context of malware evolution, in the sense that we retrain our …

“What I Have Learned About Ethnic Studies Is To Love Myself More”: A Look At Culturally Sustaining Pedagogy And Newcomer Students, Lan Nguyen

Master's Projects

Throughout American history, schooling has been used as a tool of settler colonialism, hegemony, and white supremacy. This process of utilizing schooling as a tool of domination has been labeled by theorists as “miseducation”. To attempt to combat the miseducation that students experience in their schooling, I implemented culturally sustaining pedagogy, which necessitates the maintenance and strengthening of students’ relationships with their cultures in schools. In my project, I focused on newcomer students, as immigrant students are often the most underserved population in schools, and also are the most vulnerable to assimilationist teachings. This project utilized classroom observations, student work, …

Investigating Lattice-Based Cryptography, Michaela Molina

Master's Projects

Cryptography is important for data confidentiality, integrity, and authentication. Public key cryptosystems allow for the encryption and decryption of data using two different keys, one that is public and one that is private. This is beneficial because there is no need to securely distribute a secret key. However, the development of quantum computers implies that many public-key cryptosystems for which security depends on the hardness of solving math problems will no longer be secure. It is important to develop systems that have harder math problems which cannot be solved by a quantum computer.

In this project, two public-key cryptosystems which …

A Novel Handover Method Using Destination Prediction In 5g-V2x Networks, Pooja Shyamsundar

Master's Projects

This paper proposes a novel approach to handover optimization in fifth generation vehicular networks. A key principle in designing fifth generation vehicular network technology is continuous connectivity. This makes it important to ensure that there are no gaps in communication for mobile user equipment. Handovers can cause disruption in connectivity as the process involves switching from one base station to another. Issues in the handover process include poor load management for moving traffic resulting in low bandwidth or connectivity gaps, too many hops resulting in multiple unneccessary handovers, short dwell times and ineffective base station selection resulting in delays and …

Benchmarking Newsql Database Voltdb, Kevin Schumacher

Master's Projects

NewSQL is a type of relational database that is able to horizontally scale while retaining linearizable consistency. This is an improvement over a traditional SQL relational database because SQL databases cannot effectively scale across multiple machines. This is also an improvement over NoSQL databases because NewSQL databases are designed from the ground up to be consistent and have ACID guarantees. However, it should be noted that NewSQL databases are not a one size fits all type of database, each specific database is designed to perform well on specific workloads. This project will evaluate a NewSQL database, VoltDB, with a focus …

Virtual Machine For Spartangold, William Wang

Master's Projects

The field of blockchain and cryptocurrencies can be both difficult to grasp and improve upon, which makes aids that can assist in these tasks very useful. SpartanGold is a simplified blockchain-based cryptocurrency created at San Jose State University as a learning aid for blockchain and cryptocurrencies. In its current state, it closely resembles Bitcoin, and it is also easily expandable to implement other features.

This project extends SpartanGold with a virtual machine resembling the Ethereum Virtual Machine. Implementing this feature results in SpartanGold having Ethereum- related features, which would allow the cryptocurrency to both be a helpful learning aid for …

Cloud Provisioning And Management With Deep Reinforcement Learning, Alexandru Tol

Master's Projects

The first web applications appeared in the early nineteen nineties. These applica- tions were entirely hosted in house by companies that developed them. In the mid 2000s the concept of a digital cloud was introduced by the then CEO of google Eric Schmidt. Now in the current day most companies will at least partially host their applications on proprietary servers hosted at data-centers or commercial clouds like Amazon Web Services (AWS) or Heroku.

This arrangement seems like a straight forward win-win for both parties, the customer gets rid of the hassle of maintaining a live server for their applications and …

Analysis Of Public Sentiment Of Covid-19 Pandemic, Vaccines, And Lockdowns, Devinesh Singh

Master's Projects

CoV-2 pandemic prompted lockdown measures to be implemented worldwide; these directives were implemented nationwide to stunt the spread of the infection. Throughout the lockdowns, millions of individuals resorted to social media for entertainment, communicate with friends and family, and express their opinions about the pandemic. Simultaneously, social media aided in the dissemination of misinformation, which has proven to be a threat to global health. Sentiment analysis, a technique used to analyze textual data, can be used to gain an overview of public opinion behind CoV-2 from Twitter and TikTok. The primary focus of the project is to build a deep …

Task Force Rattlesnake: A Cost Analysis Of Fire Crew Base Pay In California, Galen R. Yusufzai-Boggs

Master's Projects

Wildfire management in California is an expensive program totaling over $3 billion in 2020, where the state provides two-thirds of the budget from the general fund (Peters et al., 2020). California has consistently used the state military to assist in wildland fire mitigation efforts; however, for the first time it has created a year-round team to reduce fuels to clean up the state’s forests. Further analysis would determine if Task Force Rattlesnake is an effective use of the state’s budget for wildfire mitigation.

An Analysis Of Kindergarten Childhood Disease Vaccination Rates And Practices In Bay Area Counties, Janice Zelaya

Master's Projects

Immunizations are the most effective method for preventing communicable diseases, especially among children. Ensuring that children are vaccinated is of the utmost importance but remains a challenge due to misinformation and the growing anti-vaccination movement. With a population of 39.5 million people as of 2020 (Census Bureau, n.d.), California is the most populous state in the United States. In 2020, the San Francisco Bay Area, which includes the counties of Alameda, Contra Costa, Marin, Napa, San Francisco, San Mateo, Santa Clara, Solano, and Sonoma, is home to 7.7 million of those people (Census Bureau, 2021). This research will explore how …

An Evaluation Of The County Of Santa Clara’S Reentry Alcohol And Drug Studies Peer Mentor Program, Sarah Oliveira

Master's Projects

In the United States, incarceration rates have increased dramatically over the last three decades, soaring above any other country. Significant factors contributing to the increase include changes in sentencing laws and policies that target drug-related offenders and prioritize punishment over rehabilitation. Strict sentencing laws have led to mass incarceration, which has caused severe prison overcrowding and led to the infringement of fundamental human rights in prisons (Gottesdiener, 2011).

According to the U.S. Department of Labor, approximately 600,000 individuals are released from federal and state prisons each year (Carson, 2018). In California, an estimated one in three adults has an arrest …

Factors Affecting Web-Based Social Service Referral Technology Adoption In The Nonprofit Sector, Elizabeth A. Hutton

Master's Projects

Nonprofits play a significant role in providing social services that increase communities' overall well-being (Ressler et al., 2021; Reckhow et al., 2019; Smith & Phillips, 2016), and adopting new technologies helps promote these positive outcomes (Hackler & Saxton, 2007). However, with new technologies emerging at a pace few nonprofit organizations can keep up with, how do nonprofit leaders decide which technologies to adopt given their limited resources? This study seeks to understand what factors affect nonprofit leaders' technology adoption decision-making. Online referral platforms are not new in health or homeless organizations. Web-based coordinated social service referral tools are more recently …

Perception Of Inclusion Among Minority Civilian Personnel Within The Military Departments And Defense Agencies Of The Department Of Defense, René Moreno

Master's Projects

As the racial and ethnic composition of the United States’ population becomes increasingly diverse, government agencies must adhere to the theory of representative bureaucracy and promote a workforce reflective of the diverse American population (Mosher, 1968). Scholars reason that public administrators must be diligent in developing systems and structures to ensure that the public administration workforce appropriately embodies the communities they support (Pitts & Wise, 2010). Organizations have adopted diversity management practices to establish a mechanism that promotes diversity within their workforce. Researchers argue that organizations must accompany diversity management with a culture of inclusion to build an environment that …

Housing Choice Vouchers: Moving To Work Program In California, Benjamin Tran

Master's Projects

This research project examined whether the US Department of Housing and Urban Development’s (HUD’s) Moving To Work (MTW) program enabled California’s public housing authorities to provide more efficient service, while meeting MTW program goals, from 2015 to 2020.

Ending Homelessness In Santa Clara County: A Program Evaluation Of Homefirst Services’ Rapid Re-Housing Program Using Client Feedback, Karen Gomez

Master's Projects

This research was designed to evaluate whether HomeFirst Services’ RRH Program has proven to be more effective than traditional approaches in eliminating homelessness for its participants in Santa Clara County, California. Research was based on the Program Satisfaction Survey conducted at the end of the participants’ program enrollment in comparison with data collected for clients in other HomeFirst Services programs. The research question that is being answered from this survey is whether or not the HomeFirst Services RRH Program is fulfilling the clients’ needs. This questionnaire has been able to help HomeFirst Services understand the factors that help satisfy program …

Increasing Calfresh Access And Participation For Seniors: Benchmarking Calfresh Strategies Within Selected Coastal Agricultural Counties Against Santa Cruz County, Mayra Rocha

Master's Projects

The Supplemental Nutrition Assistance Program (SNAP), formerly known as Food Stamps, and called CalFresh in California, is the largest federally funded food assistance program in the United States. The program aims to reduce food insecurity and poverty by increasing access to nutritious food for low income eligible individuals (California Department of Social Services [CDSS], 2021a). The program is administered by county offices that are responsible for ensuring that the program is accessible, and that eligible individuals participate. Reports from the United States Department of Agriculture Food and Nutrition Service (USDA FNS) indicate that eligible seniors in California had the lowest …

Canvas Autoquiz, Archit Jain

Master's Projects

Online learning management platforms such as Canvas are thriving and quickly replacing traditional classrooms, especially during these pandemic-struck times. As more and more quizzes are administered online, we need tools that make the quiz creation process easier and faster. Canvas Autoquiz is a command-line tool that allows instructors to automatically create and upload quizzes of varying difficulty levels. It also allows instructors to export quizzes from one LMS platform to another. This project explores the need, design, and implementation of the tool, and prospective future work.

Codis: Community Detection Via Distributed Seed-Set Expansion On Graph Streams, Austin Anderson

Master's Projects

Community detection has been and remains a very important topic in several fields. From marketing and social networking to biological studies, community detec- tion plays a key role in advancing research in many different fields. Research on this topic originally looked at classifying nodes into discrete communities, but eventually moved forward to placing nodes in multiple communities. Unfortunately, community detection has always been a time-inefficient process, and recent data sets have been simply to large to realistically process using traditional methods. Because of this, recent methods have turned to parallelism, but all these methods, while offering sig- nificant decrease in …

Metagenomic Analysis Of Microbial 18s Eukaryotes Communities And Environmental Factors In The Western Antarctic Peninsula Waters During Austral Summers, Idan Siman-Tov

Master's Projects

Little is known about the environmental factors that impact eukaryotic microbial populations in the Western Antarctic Peninsula. Metagenomic and environmental data have been collected over the course of three consecutive austral summers in the Western Antarctic Peninsula off Palmer Station. More than 13 million 18S rRNA eukaryotic sequences have been taxonomically identified and categorized from the Antarctic water samples collected. Here we will investigate the environmental factors that affect eukaryotic organism populations, as well as possible indicator species that could provide insight as to the status of other eukaryotic species. Due to climate change, understanding these factors and identifying status …

Caption And Image Based Next-Word Auto-Completion, Meet Patel

Master's Projects

With the increasing number of options or choices in terms of entities like products, movies, songs, etc. which are now available to users, they try to save time by looking for an application or system that provides automatic recommendations. Recommender systems are automated computing processes that leverage concepts of Machine Learning, Data Mining and Artificial Intelligence towards generating product recommendations based on a user’s preferences. These systems have given a significant boost to businesses across multiple segments as a result of reduced human intervention. One similar aspect of this is content writing. It would save users a lot of time …

Proxy Re-Encryption In Blockchain-Based Application, Wangcheng Yuan

Master's Projects

Nowadays, blockchain-based technology has risen to a new dimension. With the advantage of the decentralized identity, data are transferred through decentralized and public ledgers. Those new contracts provide great visibility. However, there is still a need to keep some data private in many cases. Those private data should be encrypted while still benefiting from the decentralized on-chain protocol. Securing those private data in such a decentralized blockchain-based system is thus a critical problem. Our solution provides a decentralized protocol that lets users grant access to their private data with proxy re-encryption in SpartanGold (a blockchain-based cryptocurrency). We implement a third-party …

Multi-Step Prediction Using Tree Generation For Reinforcement Learning, Kevin Prakash

Master's Projects

The goal of reinforcement learning is to learn a policy that maximizes a reward function. In some environments with complete information, search algorithms are highly useful in simulating action sequences in a game tree. However, in many practical environments, such effective search strategies are not applicable since their state transition information may not be available. This paper proposes a novel method to approximate a game tree that enables reinforcement learning to use search strategies even in incomplete information environments. With an approximated game tree, the agent predicts all possible states multiple steps into the future and evaluates the states to …

Empirical Evaluation Of The Shift And Scale Parameters In Batch Normalization, Yashna Peerthum

Master's Projects

Batch Normalization (BatchNorm) is a technique that enables the training of deep neural networks, especially Convolutional Neural Networks (CNN) for computer vision tasks. It has been empirically demonstrated that BatchNorm increases per- formance, stability, and accuracy, although the reasons for these improvements are unclear. BatchNorm consists of a normalization step with trainable shift and scale parameters. In this paper, we examine the role of normalization and the shift and scale parameters in BatchNorm. We implement two new optimizers in PyTorch: a version of BatchNorm that we refer to as AffineLayer, which includes the shift and scale transform without normalization, and …

Using Machine Learning To Maximize First-Generation Student Success A Contribution To The Mission Of Aiding The Underserved, Mustafa Emre Yesilyurt

Master's Projects

The Leadership and Career Accelerator (UNVS 101) is a course offered at San José State University (SJSU) designed to hone industry skills in and provide support to students of underserved backgrounds. The main goal of this study is to determine which features are most significant to identifying the students at risk of failing the course. This will allow faculty to better focus data collection efforts and facilitate an increase in classifier accuracy. The data came as three distinct sets (sources). One contained features describing student demographics and academic history, another described the students’ experience in the course, and a third …

Enabling Use Of Signal In A Disconnected Village Environment, Evan Chopra

Master's Projects

A significant portion of the world still does not have a stable internet connection. Those people should have the ability to communicate with their loved ones who may not live near by or to share ideas with friends. To power this achievable reality, our lab has set out on making infrastructure for enabling delay tolerant applications. This network will communicate using existing smartphones that will relay the information to a connected environment. The proof of concept application our lab is using is Signal as it offers end to end encryption messaging and an open source platform our lab can develop.

A Lims-Less System For Genotyping Data In Marker-Assisted Selection, Alex Rios

Master's Projects

Climate change and feeding the growing human population are two tightly intertwined problems we face now. Innovations across several agricultural sectors are needed to meet these challenges as we proceed into the future. Seed companies and plant breeders are at the forefront of producing new plant varieties that must survive under the unique stresses of extreme weather patterns caused by changing climates. This project aims to provide breeders with faster marker results by streamlining the data process of marker-assisted selection (MAS). Manually managing genotyping data in MAS can take several hours or days to compile results for breeders. Although some …