Digital Commons Network^™

Multimodal Techniques For Malware Classification, Jonathan Jiang

Master's Projects

The threat of malware has remained a serious concern for computer networks and systems, highlighting the need for accurate classification techniques. This research adopted the structured nature of PE files incorporated with a multi-modal machinelearning approach, to classify malware types. Features extracted from the PE headers were used to train an LSTM model. Features extracted from the PE sections were used to train a CNN model. Probabilities produced from these two models were then concatenated and fed into an SVM classifier. This multi-modal approach demonstrated high accuracy by experimenting with and verifying the approach on a large and labeled dataset. …

Explainable Reinforcement Learning For Network Routing Optimization, Yu Xiu

Master's Projects

Software-defined Networking (SDN) provides a solution for configuring multiple network devices by offering a centralized controller architecture. Network routing is one of the most crucial problems in network configuration. In particular, the surging network traffic demands require efficient routing techniques to load balance communication links. In order to optimize the communication path’s utilization and reduce request blocking, this project utilizes Reinforcement Learning (RL) to decide the routes for given network requests. Furthermore, we adopt Explainable Reinforcement Learning (XRL) to explain the RL learning agent’s decision-making process to enhance the trustworthiness of our approach. In particular, we focus on Feature Importance …

Ai Generated Text Detection & Source Identification, Anjana Priyatham Tatavarthi

Master's Projects

The detection of AI-generated text by the application of advanced machine learning techniques not only presents a promising approach toward distinguishing human-written content from machine-generated text, but also identifies the source model used for the generation of the text. This helps address the growing concerns about authenticity and accountability in digital communication. The difference between human-generated and AI-generated text lies in the core of several applications, from news media to academic integrity.It also helps in ensuring the transparency and trust in content-driven environments. However, existing models fall short in accurately detecting AI-generated text and identifying the specific AI source due …

The Global Partners Program A New International Volunteer Opportunity For Ams Members, Walter Dabberdt, Darrel Baumgardner, Robert Bornstein, Gregory Carmichael, Richard Clark, Jeffrey Collett, Harindra Fernando, Efi Foufoula-Georgiou, Dev Niyogi, Mohan Ramamurthy, Alan Robock, Julie Winkler

Faculty Research, Scholarly, and Creative Activity

No abstract provided.

Tiktok As Social Communication Tool To Encourage Participation In Volunteering Projects, Belén Moreno-Albarracín, Tania Blanco-Sánchez

Faculty Research, Scholarly, and Creative Activity

Social media are regarded as tools of communication and social influence. Notwithstanding this, TikTok’s majority audience in 2023 is made up of members of generations Z and Alpha, associated in previous studies with a participatory crisis. Given this contradiction, a research question is proposed: do young people use TikTok to consolidate social values such as solidarity? To answer it, the main objective is to analyse the use of TikTok as an instrument for youth participation in volunteer projects. A mixed methodology is used, based on a content analysis of the 150 videos uploaded to TikTok with the hashtag #voluntariado and …

Use Or Not: A Qualitative Study On The User Adoption And Abandonment Of Voice Shopping With Smart Speakers, Jiahe Lan, Yu Chen, Zheng Yan

Faculty Research, Scholarly, and Creative Activity

The recent advances in smart speakers impel the emergence and prevalence of voice shopping - placing orders on voice assistants. Previous work has studied user acceptance of voice shopping and the factors influencing users' experience of voice shopping. However, despite the growing interest in the use of voice shopping, little is known about the limited usage or abandonment of voice shopping. In this paper, we address this research gap through a qualitative study of 43 users of Tmall Genie, a smart speaker popular in China. We found that participants are willing to make low-involvement purchases via voice shopping. However, after …

Corrigendum: A Live Fuel Moisture Climatology In California (Front. For. Glob. Change, (2023), 6, 1203536, 10.3389/Ffgc.2023.1203536), Jack R. Drucker, Angel Farguell, Craig B. Clements, Adam K. Kochanski

Faculty Research, Scholarly, and Creative Activity

In the published article, there was an error in Figures 4, 5 as published. The plots originally appearing in Figure 4 should be interchanged with those in Figure 5, and vice versa. The corrected Figure 4 and its caption “Figure 4. The general (annual average) (black dashed line), maximum (green dashed line), and minimum (red dashed line) LFMC trends for the (A) Bay Area, (B) Central Coast, and (C) South Coast regions. The differences in the time ranges stem from the length of the data record which varies across the regions” and the corrected Figure 5 along with its caption …

Cross-Cultural Adaptation Of The Voice-Related Experiences Of Nonbinary Individuals - Veni To Brazilian Portuguese, Isabela Dos Santos, Mara Behlau, Grace Shefcik, Pei Tzu Tsai, Vanessa Veis Ribeiro

Faculty Research, Scholarly, and Creative Activity

Purpose: This study aimed to translate and cross-culturally adapt the “Voice-related Experiences of Nonbinary Individuals” (VENI) to Brazilian Portuguese (BP). Methods: Cross-cultural adaptation was performed based on the combined guidelines of the World Health Organization’s (WHO) Translation Recommendations and the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN). The process included five stages: a) Translation of the instrument into BP by a translator specialized in the construct and a non-specialist, both native BP speakers and fluent in English; b) Synthesis of the two translations by consensus; c) Back-translation by a translator specialized in the construct and a non-specialist, …

Evaluating The Influence Of Marine Protected Areas On Surf Zone Fish, M. L. Marraffini, S. L. Hamilton, J. R. Marin Jarrin, M. Ladd, G. Koval, J. R. Madden, I. Mangino, L. M. Parker, K. A. Emery, K. Terhaar, D. M. Hubbard, R. J. Miller, J. E. Dugan

Faculty Research, Scholarly, and Creative Activity

Marine protected areas (MPAs) globally serve conservation and fisheries management goals, generating positive effects in some marine ecosystems. Surf zones and sandy beaches, critical ecotones bridging land and sea, play a pivotal role in the life cycles of numerous fish species and serve as prime areas for subsistence and recreational fishing. Despite their significance, these areas remain understudied when evaluating the effects of MPAs. We compared surf zone fish assemblages inside and outside MPAs across 3 bioregions in California (USA). Using seines and baited remote underwater videos (BRUVs), we found differences in surf zone fish inside and outside MPAs in …

Fpdclustering: A Comprehensive R Package For Probabilistic Distance Clustering Based Methods, Cristina Tortora, Francesco Palumbo

Faculty Research, Scholarly, and Creative Activity

Data clustering has a long history and refers to a vast range of models and methods that exploit the ever-more-performing numerical optimization algorithms and are designed to find homogeneous groups of observations in data. In this framework, the probability distance clustering (PDC) family methods offer a numerically effective alternative to model-based clustering methods and a more flexible opportunity in the framework of geometric data clustering. Given nJ-dimensional data vectors arranged in a data matrix and the number K of clusters, PDC maximizes the joint density function that is defined as the sum of the products between the distance and the …

Lithium And Water: Hydrosocial Impacts Across The Life Cycle Of Energy Storage, James J.A. Blair, Noel Vineyard, Dustin Mulvaney, Alida Cantor, Ali Sharbat, Kate Berry, Elizabeth Bartholomew, Ariana Firebaugh Ornelas

Faculty Research, Scholarly, and Creative Activity

As a key ingredient of batteries for electric vehicles (EVs), lithium plays a significant role in climate change mitigation, but lithium has considerable impacts on water and society across its life cycle. Upstream extraction methods—including open-pit mining, brine evaporation, and novel direct lithium extraction (DLE)—and downstream processes present different impacts on both the quantity and quality of water resources, leading to water depletion and contamination. Regarding upstream extraction, it is critical for a comprehensive assessment of lithium's life cycle to include cumulative impacts related not only to freshwater, but also mineralized or saline groundwater, also known as brine. Legal frameworks …

A Comparative Multivariate Analysis Of Var And Deep Learning-Based Models For Forecasting Volatile Time Series Data, Saroj Gopali, Sima Siami-Namini, Faranak Abri, Akbar Siami Namin

Faculty Research, Scholarly, and Creative Activity

The existing literature on forecasting time series data is primarily based on univariate analysis and techniques such as Univariate Autoregressive (UAR), Univariate Moving Average (UMA), Simple Exponential Smoothing (SES), deep learning models, and, most notably, univariate Long Short-Term Memory (LSTM) built based on univariate variable where the next lag of time series is leveraged for forecasting the next cycle of data. This paper takes this line of research to the next level by focusing on forecasting time series data based on “multivariate” modeling and analysis. To have a better insight of the performance of various deep learning-based models when multivariate …

A Comparison Of Adversarial Malware Generators, Pavla Louthánová, Matouš Kozák, Martin Jureček, Mark Stamp, Fabio Di Troia

Faculty Research, Scholarly, and Creative Activity

Machine learning has proven to be a valuable tool for automated malware detection, but machine learning systems have also been shown to be subject to adversarial attacks. This paper summarizes and compares related work on generating adversarial malware samples, specifically malicious Windows Portable Executable files. In contrast with previous research, we not only compare generators of adversarial malware examples theoretically, but we also provide an experimental comparison and evaluation for practical usability. We use gradient-based, evolutionary-based, and reinforcement-based approaches to create adversarial samples, which we test against selected antivirus products. The results show that applying optimized modifications to previously detected …

A Fresh Take: Seasonal Changes In Terrestrial Freshwater Inputs Impact Salt Marsh Hydrology And Vegetation Dynamics, Maya S. Montalvo, Emilio Grande, Anna E. Braswell, Ate Visser, Bhavna Arora, Erin C. Seybold, Corianne Tatariw, John C. Haskins, Charlie A. Endris, Fuller Gerbl, Mong Han Huang, Darya Morozov, Margaret A. Zimmer

Faculty Research, Scholarly, and Creative Activity

Salt marshes exist at the terrestrial-marine interface, providing important ecosystem services such as nutrient cycling and carbon sequestration. Tidal inputs play a dominant role in salt marsh porewater mixing, and terrestrially derived freshwater inputs are increasingly recognized as important sources of water and solutes to intertidal wetlands. However, there remains a critical gap in understanding the role of freshwater inputs on salt marsh hydrology, and how this may impact marsh subsurface salinity and plant productivity. Here, we address this knowledge gap by examining the hydrologic behavior, porewater salinity, and pickleweed (Sarcocornia pacifica also known as Salicornia pacifica) plant productivity along …

Anti-Trafficking And Humanitarian Operations: Transferring Learnings For A Better World, Kezban Yagci Sokat, Maria Besiou

Faculty Research, Scholarly, and Creative Activity

Purpose: The purpose of this study is twofold: first, to draw insights from the rich literature on humanitarian operations efforts to combat human trafficking; second, to inspire humanitarian operations researchers to work more on human anti-trafficking. Design/methodology/approach: This is a conceptual paper inspired by recent relevant reports, the academic literature and the authors’ years of involvement in both humanitarian operations and anti-trafficking. Findings: Humanitarian supply chains and human trafficking supply chains very often operate in the same environments and hence face similar challenges. The paper highlights the overlaps between the two domains and demonstrates how two decades of learnings from …

Assessment Of Digital Collaboration Skills, Esperanza Huerta, Ana Lidia Franzoni Velázquez, Scott Jensen

Faculty Research, Scholarly, and Creative Activity

This exploratory study proposes a methodology for assessing digital collaboration skills based on the students' actual behavior. Students' comments using a digital collaboration tool during a one-month long project were manually coded. This methodology is not context specific and can be used across different domains. This assessment contrasts with self-reported measures in which students rate themselves as already possessing collaboration skills. Finally, the study explores the use of generative AI to automatically code student's comments to alleviate the labor-intensive process that coding requires and to enable scalability in coding data.

Covid-19 Vaccination-Related Tinnitus Is Associated With Pre-Vaccination Metabolic Disorders, Weihua Wang, Anusha Yellamsetty, Robert M. Edmonds, Shaun R. Barcavage, Shaowen Bao

Faculty Research, Scholarly, and Creative Activity

Cases of tinnitus have been reported following administration of COVID-19 vaccines. The aim of this study was to characterize COVID-19 vaccination-related tinnitus to assess whether there is a causal relationship, and to examine potential risk factors for COVID-19 vaccination-related tinnitus. We analyzed a survey on 398 cases of COVID-19 vaccination-related tinnitus, and 699,839 COVID-19 vaccine-related reports in the Vaccine Adverse Effect Reporting System (VAERS) database that was retrieved on 4 December 2021. We found that following COVID-19 vaccination, 1) tinnitus report frequencies for Pfizer, Moderna and Janssen vaccines in VAERS are 47, 51 and 70 cases per million full vaccination; …

Graduate Public Health Student Learning Experiences, Social Connectedness, And Mental Health During Covid-19: Pedagogical Implications For Public Health Academic Departments, Harit Agroia, Rachel Berkowitz, Andrew Carter, Vicky Gomez, Monica Allen

Faculty Research, Scholarly, and Creative Activity

Introduction: The COVID-19 pandemic impacted college student learning both globally and nationally. Current literature points to decreases in social connectedness, adverse mental health outcomes, and decreased overall learning outcomes; however, there are limited findings from higher education institutions within the Bay Area, California. There are also limited studies that examine the COVID-19 impact among public health graduate students, especially to understand how the pandemic renewed their interest in the field. The purpose of this study was to investigate the effects of COVID-19 on graduate student learning experiences, social connectedness and mental health within the Master of Public Health program at …

Is Knowledge Management (Finally) Extractive? – Fuller’S Argument Revisited In The Age Of Ai, Norman Mooradian

Faculty Research, Scholarly, and Creative Activity

Aim/Purpose The rise of modern artificial intelligence (AI), in particular, machine learning (ML), has provided new opportunities and directions for knowledge management (KM). A central question for the future of KM is whether it will be dominated by an automation strategy that replaces knowledge work or whether it will support a knowledge-enablement strategy that enhances knowledge work and uplifts knowledge workers. This paper addresses this question by re-examining and updating a critical argument against KM by the sociologist of science Steve Fuller (2002), who held that KM was extractive and exploitative from its origins. Background This paper re-examines Fuller’s argument …

Opening The Black Box: Carbon-Footprint Calculators, Meat Consumption, And The “Wicked Problem” Of Metric Governance, E. Melanie Dupuis, Dustin Mulvaney

Faculty Research, Scholarly, and Creative Activity

Carbon-footprint calculators are widely used as communication and education tools, designed to make people aware of the ways their personal actions contribute to greenhouse-gas emissions. However, they have come under criticism for emphasizing individual behavior versus structural change. We extend this critique to argue that carbon-footprint calculators are a form of “metric governance” that not only disciplines users but also constrains their abilities to engage with the complexities of climate change and social action. We focus on a particularly wicked problem of carbon-metric governance: livestock greenhouse-gas emissions. We show that carbon-footprint calculators black box and fix the complex politics and …

Perturbation Walking Effects On Prefrontal Cortical Activation And Walking Performance In Older Women With And Without Osteoarthritis: A Fnirs Study, Alka Bishnoi, Yang Hu, Manuel E. Hernandez

Faculty Research, Scholarly, and Creative Activity

Introduction: Perturbation walking (PW) has been shown to improve gait, however its effect on the cortical control of gait might provide insights on neural mechanisms underlying falls in adults with osteoarthritis. The objective of this study is to investigate the effect of PW on prefrontal cortical (PFC) activation in older women with (OA) and without osteoarthritis (HOA). We hypothesized that there would be an increase in PFC activation during PW relative to comfortable walking (CW) and higher increase in PFC activation during PW in HOA compared to OA. Methods: Twenty community-dwelling older women (66.7 ± 5.41 years old) walked on …

Chronic Pelvic Pain Among Transgender Men And Gender Diverse Adults Assigned Female At Birth, Diana M. Tordoff, Mitchell R. Lunn, Annesa Flentje, Diana Atashroo, Bertha Chen, Zubin Dastur, Micah E. Lubensky, Matthew Capriotti, Juno Obedin-Maliver

Faculty Research, Scholarly, and Creative Activity

Background: There are limited data on pelvic pain among transgender men and gender diverse people, and the impact of testosterone on pelvic pain is poorly understood. Objective: Characterize the prevalence and correlates of chronic pelvic pain (CPP) among transgender men and gender diverse people and examine the association between testosterone use and CPP. Materials and methods: We used 2020–2022 data from The Population Research in Identity and Disparities for Equality (PRIDE) Study, an online prospective cohort study of sexual and gender minority adults in the United States, to conduct complementary cross-sectional and longitudinal analyses. Our primary outcome was self-reported CPP …

Effect Of Fermentation, Malting And Ultrasonication On Sorghum, Mopane Worm And Moringa Oleifera: Improvement In Their Nutritional, Techno-Functional And Health Promoting Properties, Mpho Sebabiki Maleke, Oluwafemi Ayodeji Adebo, Jonathan Wilkin, Moira Ledbetter, Xi Feng, John Gieng, Tumisi Beiri Jeremiah Molelekoa

Faculty Research, Scholarly, and Creative Activity

Background: Food processing offers various benefits that contribute to food nutrition, food security and convenience. This study investigated the effect of three different processes (fermentation, malting and ultrasonication) on the nutritional, techno-functional and health-promoting properties of sorghum, mopane worm and Moringa oleifera. Methods: The fermented and malted flours were prepared at 35°C for 48 h, and for ultrasonication, samples were subjected to 10 min at 4°C with amplitudes of 40–70 Hz. The biochemical, nutritional quality and techno-functional properties of the obtained flours were analysed using standard procedures. Results: Fermentation resulted in significantly lower pH and higher titratable acidity in sorghum …

Webometrics Analysis Of Government Medical Colleges Of Bihar: A Study, Debashish Pandit Paul, Mohd. Aslam Khan, Anubhaw Kumar Suman

Library Philosophy and Practice (e-journal)

The study presents the webometrics analysis of 9 websites of Government Medical Colleges under the Health Department, Government of Bihar. The Purpose of in study to identify the web presence, domain analysis and other webometrics indicators of the selected website. The study uses SEO MOZ for data collection. It was found that the website of Sri Krishna Medical College and Hospital, Muzaffarpur (SKMCH) has the highest domain authority of 27 and the highest page authority of Nalanda Medical College and Hospital, Patna (NMCH) of 35. The study concluded that all websites should be inter-connected, well-maintained and …

The Impact Of Daylight Saving Time Transitions On Domestic Violence Call Volume, Quynh-Nhu Pham

Master's Projects

Daylight Saving Time (DST) is a longstanding practice in many countries, involving the seasonal adjustment of clocks by one hour forward in the spring, and one hour backward in the fall. Although DST was initially introduced to promote energy conservation and maximize daylight hours, it has become a subject of debate, given its impact on physical and mental health, cognitive performance, and criminal behavior (Kountouris & Remoundou, 2014).

In 2022, Colorado enacted a law adopting year-round DST, contingent upon a federal law enabling states to maintain DST throughout the year as opposed to ST, like Hawaii and Arizona (Chasan, 2024). …

A Two-Stage Machine Learning Approach For Fake News Detection And News Article Categorization, Snegdha Adusumilli

Master's Projects

This project employs machine learning techniques to develop a sequential model for detecting and categorizing fake news, aiming to mitigate its proliferation in today's digital landscape. The model operates in two phases: in the first phase, the classification algorithms like Naïve Bayes, XGBoost and Random Forest are used to distinguish between true and false news stories and in the second phase the capabilities of Naïve Bayes, XGBoost, Random Forest, and the Transformer-based BERT (Bidirectional Encoder Representations from Transformers) model are leveraged to further categorize the news into specific topics.

The methodology encompasses several key steps: data acquisition, preprocessing, feature extraction, …

A Censorship Resistant News Website Using The Ethereum Blockchain, Hoang Lai

Master's Projects

Misleading information, false claims, and fabricated news articles not only misguide readers but also undermine the trustworthiness of the news platforms themselves. The blockchain provides decentralized, immutable data storage and offers a promising solution to prevent censorship on news websites. Compared to traditional news websites, a decentralized application (dApp) offers benefits such as greater stability and resistance to information manipulation. A decentralized web app is harder to attack than centralized servers since the database is stored across a blockchain network. Moreover, blockchain prevents censorship by letting readers check data across all blocks in the Blockchain, which is good for a …

Echo: A Browser Extension That Runs Experimental Javascript, Prayuj Pillai

Master's Projects

Narcissus is a JavaScript interpreter written in JavaScript. While it is a good engine for experimenting with JavaScript’s design, it does not integrate easily into the browser. This project introduces ‘‘Echo’’, a browser add-on designed to execute Narcissus JavaScript files and scripts within web browsers. The project explores the performance of the Narcissus interpreter against native browser JavaScript engines and benchmarks the results, showcasing the trade-offs in running an experimental engine—the Narcissus interpreter—on the browser versus native JavaScript. Additionally, as a proof of concept, we implement taint tracking, a capability meant to boost security by preventing sensitive data from being …

Credit Score-Based Lending System On The Ethereum Platform, Mayuri Shimpi

Master's Projects

Traditional banking systems act as intermediaries, assessing risks and profiting from interest rate differentials. Credit scores, provided by trusted bureaus, are commonly used to evaluate the creditworthiness of borrowers. Cryptocurrencies have emerged as a significant and innovative medium due to their decentralized nature, operating without reliance on a central authority, such as a government.

This report describes a project to implement the Autonomous Lending system on the Ethereum Platform (ALOE), as proposed in [1], aiming to seamlessly integrate traditional credit scoring methodologies for evaluating a borrower's risk of default. The objective of this project report is to establish a robust …

Domain Switch On Sentiment Analysis Using Gradient Reversal Layer, Hemish Veeraboina

Master's Projects

Switching domains in sentiment analysis presents the challenge of transferring learned knowledge from one context to another without the need to label data. Traditional methods often struggle when dealing with differences in data distribution a problem known as the domain shift issue. To tackle this using Gradient Reversal Layers (GRL) has emerged as a solution for adapting to different domains in an unsupervised learning setting. This study introduces an enhancement to the standard GRL approach by incorporating a sigmoid function that gradually adjusts how intensely domain adaptation occurs during training. This upgraded GRL technique ensures controlled learning outcomes making it …