Digital Commons Network^™

Scalable Container Caching Optimization With Action Masking For Serverless Edge Computing, Manikanta Sanjay Veera

Master's Projects

Serverless edge computing is an emerging technology that realizes the low latency and resource-efficient function calls for responsive computing. In cloud-based serverless computing, it is a common practice to cache sufficiently many function containers for future reuse to reduce the overhead of container initiation. In contrast, the capacity limitation of edge nodes poses a complex problem to the caching strategy in serverless edge computing of selecting an appropriate set of container caches based on the request distribution. Deep Reinforcement Learning (DRL) can play a crucial role in optimizing the caching decisions under dynamic request arrivals. In this paper, we propose …

Skin Cancer Detection Using Reinforcement Learning, Vikas Chercadu

Master's Projects

Advances in medical diagnostics have increasingly harnessed the power of artificial

intelligence, offering substantial improvements in early and accurate disease identifi- cation. This paper elaborates on a novel integration of Multi-Agent Reinforcement

Learning (MARL) with Deep Learning for the early detection of skin cancer, one of the most prevalent and lethal forms of cancer when left unchecked. Our project capitalizes on the sophisticated VGG16 Network for the extraction of detailed features from the widely-utilized HAM10000 dermatoscopic dataset, enhancing these features with additional color, texture, and shape analysis. Utilizing a custom-designed MARL environment, we facilitate a collaboration among multiple intelligent agents, …

Mitigating Learning Bias In Healthcare Datasets, Samyak Jagdish Kumbhalwar

Master's Projects

CVDs have been a major cause of deaths worldwide with WHO reporting 17.9 million deaths annually. Although there are advancements in the treatment of these diseases, most of the fatalities are a result of untimely diagnosis. Active research is going on to collect data points and risk factors related to these diseases, which can enable early diagnosis. Of the datasets available, many researchers have employed different ML models to predict/detect the prevalence of heart diseases. Many employed Tree based, regression models [3, 6]. Few also tried ensemble approaches [1, 2, 4]. These healthcare datasets are generally found to be imbalanced. …

Hindi Image Captioning Using Indictrans2 And Encoder-Decoder Architecture, Anahita Vayalombrone Dinesh

Master's Projects

One of the most prominent tasks that lie on the conjunction of Natural Language Processing (NLP) and computer vision, is image captioning. Image captioning is the generative task of achieving textual descriptions from images. Its application finds use in many real-world scenarios like aiding the visually impaired, editing applications, recommendation systems, and medical imaging. This research focus lies in Hindi image captioning, the official language of India, as it has not been explored as far as its need. Several challenges such as the lack of substantial Hindi text data for training models, the need for human annotators to verify the …

Multimodal Emotion Detection In Conversations And Dialogues: A Fusion Model Approach, Abhinay Jatoth

Master's Projects

Emotion recognition is gaining traction due to its wide range of potential applications across different fields. With the rise of social media, chat platforms, and voice assistants, there is a vast increase in data through which humans implicitly and explicitly carry emotional cues. With new algorithms being developed for understanding the nuances of human language and emotion, businesses can tailor more personalized and empathetic service. Sentiment analysis, expresses a positive, negative, or neutral viewpoint laid the foundation of Emotion classification. Emotion classification in conversations represents the most advanced stage of classification. It is also challenging due to the existence and …

Load Balancing For Cloud-Based Applications, Nitish Ranjan

Master's Projects

Effective load balancing is critical in ensuring optimal resource utilization, reducing latency, and improving the overall performance of distributed systems. This report commences with a comprehensive literature review on existing load-balancing algorithms, examining their methodologies, strengths, and limitations within various computing environments, including cloud computing, data centers, and network traffic management. Despite significant advancements in this field, the dynamic nature of distributed systems, coupled with the ever-increasing demand for efficient data processing, poses ongoing challenges. In response, this study proposes a novel load-balancing algorithm to address these contemporary challenges. The approach leverages dynamic and hybrid load balancing, distinguishing it from …

Artifacts In Low-Pass Whole Genome Sequencing, Nguyen Mai Anh Do

Master's Projects

Low-pass whole genome sequencing (LP-WGS) provides a cost-effective way to achieve broad genomic coverage, but it comes with the challenge of sequencing artifacts that can complicate accurate variant detection. To address this, we developed a bioinformatics pipeline using Nextflow. Starting with raw sequencing data, the pipeline performed variant calling using VarDict, with Genome in a Bottle (GIAB) high-confidence variants serving as the benchmark for variant validation. We explored machine learning approaches, testing classifiers such as AdaBoost, ExtraTrees, and RandomForest, to evaluate variant classification. Twenty-two features generated by VarDict were fed into Machine Learning pipeline, with AdaBoost standing out for its …

Enhanced Inter-Satellite Routing With Multi-Path Selection And Congestion Modeling, Jaesung Yoo

Master's Projects

Satellite networks play a crucial role in global connectivity today and making efficient routing algorithms is crucial for optimal performance. While existing routing algorithms have made significant progress using machine learning techniques, they often overlook network congestion and multiple path availability. This report introduces an enhanced routing framework that builds upon LSTM-based predictive routing using dynamic congestion modeling and multi-path selection. Our approach introduces a busy state metric that tracks satellite memory utilization, allowing for adaptive path selection based on both distance and current network load. Through simulations using a constellation of 20 satellites, our enhanced algorithm demonstrates significant improvements …

Evaluating The Implementation Of A Relationship-Centered Communication Training For Connecting With Patients In Virtual Visits, Rachyl Pines, Marie C. Haverfield, Stephanie Wong Chen, Ethan Lee, Cati Brown-Johnson, Merisa Kline, Barbette Weimer-Elder

Faculty Research, Scholarly, and Creative Activity

The use of telehealth, specifically virtual visits, has increased and adoption continues. Providers need effective training for how to communicate with patients to develop a connection during virtual visits. This article describes the implementation and evaluation of a course called Mastering Presence in Virtual Visits. Results show that although providers perceive lack of time, technology issues, and lacking experiential knowledge as barriers to enacting course behaviors, the course was feasible and acceptable. Following the course, providers rated key course behaviors as helpful for practice, and 80.7% of providers were likely to recommend the course to a colleague. The course shifted …

Participation In Collaborative Fisheries Research Improves The Perceptions Of Recreational Anglers Towards Marine Protected Areas, Erin M. Johnston, Grant T. Waltz, Rosamaria Kosaka, Ellie M. Brauer, Shelby L. Ziegler, Erica T. Jarvis Mason, Hunter S. Glanz, Lauren Zaragoza, Allison N. Kellum, Rachel O. Brooks, Brice X. Semmens, Christopher J. Honeyman, Jennifer E. Caselle, Lyall F. Bellquist, Sadie L. Small, Steven G. Morgan, Timothy J. Mulligan, Connor L. Coscino, Jay M. Staton

Faculty Research, Scholarly, and Creative Activity

Collaborative fisheries research programs engage stakeholders in data collection efforts, often with the benefit of increasing transparency about the status and management of natural resources. These programs are particularly important in marine systems, where management of recreational and commercial fisheries have historically been contentious. One such program is the California Collaborative Fisheries Research Program (CCFRP), which was designed in 2006 to engage recreational anglers in the scientific process and evaluate the efficacy of California’s network of marine protected areas. CCFRP began on the Central Coast of California and expanded statewide in 2017 to include six partner institutions in three regions: …

Creating Valid Adversarial Examples Of Malware, Matouš Kozák, Martin Jureček, Mark Stamp, Fabio Di Troia

Faculty Research, Scholarly, and Creative Activity

Because of its world-class results, machine learning (ML) is becoming increasingly popular as a go-to solution for many tasks. As a result, antivirus developers are incorporating ML models into their toolchains. While these models improve malware detection capabilities, they also carry the disadvantage of being susceptible to adversarial attacks. Although this vulnerability has been demonstrated for many models in white-box settings, a black-box scenario is more applicable in practice for the domain of malware detection. We present a method of creating adversarial malware examples using reinforcement learning algorithms. The reinforcement learning agents utilize a set of functionality-preserving modifications, thus creating …

Influencers And Luxury Fashion Brands On Instagram. Effects Of Mediated Actions In The Relationship With The User, Tania Blanco Sánchez, Belén Moreno Albarracín

Faculty Research, Scholarly, and Creative Activity

Influencers act on Instagram as images of brands that transcend their personal one. However, there is a lack of research focused on the link that is generated between the brand and the user as a result of collaborations between these firms and certain prescribers. Does an influencer's participation change that relationship? To answer this research question, this study aims to analyze the relationship between the most followed luxury fashion brands on Instagram and their followers around collaborations with influencers on their corporate profiles, through action in itself and the prescriber's participation in the content. To do this, a comparative content …

Fuzzy Similarity Analysis Of Effective Training Samples To Improve Machine Learning Estimations Of Water Quality Parameters Using Sentinel-2 Remote Sensing Data, Alireza Taheri Dehkordi, Mohammad Javad Valadan Zoej, Ali Mehran, Mohsen Jafari, Amir Masoud Chegoonian

Faculty Research, Scholarly, and Creative Activity

Continuous monitoring of water quality parameters (WQPs) is crucial due to the global degradation of water quality, primarily caused by climate change and population growth. Typically, machine learning (ML) models are employed to retrieve WQPs, but they require a large amount of training samples to accurately capture the data relationships. Even with sufficient training data, discrepancies still exist between values of predicted and in-situ WQPs. This study proposes a fuzzy similarity analysis (FSA) technique to enhance ML estimates of WQPs by using the prediction errors in effective training samples. The method was successfully applied to retrieve turbidity (Turb) and specific …

Classification And Online Clustering Of Zero-Day Malware, Olha Jurečková, Martin Jureček, Mark Stamp, Fabio Di Troia, Róbert Lórencz

Faculty Research, Scholarly, and Creative Activity

A large amount of new malware is constantly being generated, which must not only be distinguished from benign samples, but also classified into malware families. For this purpose, investigating how existing malware families are developed and examining emerging families need to be explored. This paper focuses on the online processing of incoming malicious samples to assign them to existing families or, in the case of samples from new families, to cluster them. We experimented with seven prevalent malware families from the EMBER dataset, four in the training set and three additional new families in the test set. The features were …

Effects Of The Sacramento Neighborhood Alcohol Prevention Project On Rates Of Child Abuse And Neglect 7 Years Post-Implementation (1999–2010), Bridget Freisthler, Jennifer Price Wolf

Faculty Research, Scholarly, and Creative Activity

Introduction: Evaluations of alcohol environmental prevention efforts examine short-term effects of these interventions on alcohol-related problems. We examine whether the effects of the Sacramento Neighborhood Alcohol Prevention Project (SNAPP), an alcohol environmental intervention aimed to reduce alcohol-related problems in two neighbourhoods, on child abuse and neglect remained 7 years post-implementation. Methods: SNAPP used a quasi-experimental non-equivalent control group design, where intervention activities occurred in the South area, followed by those in the North area 2 years later. Our sample size is 3912 space–time units (326 census block groups × 12 years [1999–2010]). Outcomes were measured at the household level and …

Lessons From A Professional Learning Community: Navigating Tensions While Moving Between Theory And Practice In Teaching Chemistry For Social Justice, Kathryn Ribay

Faculty Research, Scholarly, and Creative Activity

Maintaining a commitment to social justice teaching can be especially challenging when navigating the bureaucratic systems and ever-spiraling responsibilities of the education system. To better understand how social-justice-oriented educators navigate these tensions, this paper uses qualitative methods to investigate the social justice problems of practice identified by five chemistry teachers in a year-long professional learning community. By analyzing the challenges described in their problem-posing segments, I identify seven major themes that represent key sources of tension and possibility as teachers move from theory to practice in teaching chemistry for social justice. These findings indicate that the practical considerations of day-to-day …

Access To Digital Finance: Equity Crowdfunding Across Countries And Platforms, Saul Estrin, Susanna Khavul, Alexander S. Kritikos, Jonas Löher

Faculty Research, Scholarly, and Creative Activity

Financing entrepreneurship spurs innovation and economic growth. Digital financial platforms that crowdfund equity for entrepreneurs have emerged globally, yet they remain poorly understood. We model equity crowdfunding in terms of the relationship between the number of investors and the amount of money raised per pitch. We examine heterogeneity in the average amount raised per pitch that is associated with differences across three countries and seven platforms. Using a novel dataset of successful fundraising on the most prominent platforms in the UK, Germany, and the USA, we find the underlying relationship between the number of investors and the amount of money …

Emergency And Disaster Preparedness For Individuals Who Use Augmentative And Alternative Communication: A Pilot Study On Supported Planning Using A Toolkit, Andrea Barton-Hulsey, Miriam C. Boesch, Yoosun Chung, Tina Caswell, Amy Miller Sonntag, Wendy Quach

Faculty Research, Scholarly, and Creative Activity

Purpose: When emergencies or disasters arise, individuals who use augmenta-tive and alternative communication (AAC) are particularly vulnerable. It is critical that individuals who use AAC are supported to make decisions that impact their own lives and are able to communicate during such a crisis. Preparedness efforts that include a plan around communication needs and supports are necessary for ensuring that individuals who use AAC are able to understand options that ensure personal safety and express their needs during a time of crisis. Method: Qualitative methods were used to identify and describe the experi-ences of two young adults who use AAC …

The Effect Of A Night Shift Nap On Post-Night Shift Performance, Sleepiness, Mood, And First Recovery Sleep: A Randomized Crossover Trial, P. Daniel Patterson, Cassie J. Hilditch, Matthew D. Weaver, David G.L. Roach, Tiffany S. Okerman, Sarah E. Martin, Charity G. Patterson, Leonard S. Weiss

Faculty Research, Scholarly, and Creative Activity

Objectives This study aimed to test the effect of a 30-minute nap versus a 2-hour nap opportunity taken during a simulated night shift on performance, fatigue, sleepiness, mood, and sleep at the end of shift and during post-night shift recovery. Methods We conducted a randomized crossover trial of three nap conditions (30-minute, 2-hour, and no-nap) during 12-hour simulated night shifts. We tested for differences in performance, fatigue, sleepiness, mood, and sleep during in-lab and at-home recovery. Performance was measured with the Brief Psychomotor Vigilance Test (PVT-B). Subjective ratings were assessed with single-item surveys. Results Twenty-eight individuals consented to participate [mean …

Emf Revisited, Art Davis

Faculty Research, Scholarly, and Creative Activity

This paper was inspired by a recent publication by Redžíc (2018 Eur. J. Phys. 39 025205) which threw into bold relief the differences between the way Maxwell viewed the current and the way Lorentz visualized it. We make the assumption that for a circuit of laboratory dimensions current (and charge perturbation effects in general) can be assumed to propagate instantaneously around the loop. Our second fundamental assumption is the commonly accepted one that E is the force per unit charge on a stationary charge. We use these facts to make the usual definition of electromotive force more rigorous and to …

Association Of Dietary Adherence And Dietary Quality With Weight Loss Success Among Those Following Low-Carbohydrate And Low-Fat Diets: A Secondary Analysis Of The Dietfits Randomized Clinical Trial, Michelle E. Hauser, Jennifer C. Hartle, Matthew J. Landry, Priya Fielding-Singh, Cynthia W. Shih, Fei Fei Qin, Joseph Rigdon, Christopher D. Gardner

Faculty Research, Scholarly, and Creative Activity

Background: Eating a high-quality diet or adhering to a given dietary strategy may influence weight loss. However, these 2 factors have not been examined concurrently for those following macronutrient-limiting diets. Objective: To determine whether improvement in dietary quality, change in dietary macronutrient composition, or the combination of these factors is associated with differential weight loss when following a healthy low-carbohydrate (HLC) or healthy low-fat (HLF) diet. Design: Generally healthy adults were randomly assigned to HLC or HLF diets for 12 mo (n = 609) as part of a randomized controlled weight loss study. Participants with complete 24-h dietary recall data …

Chapter 17. Approaches To Inclusive Recruitment: Practical And Hopeful, Adriana Poo, Anamika Megwalu, Nick Szydlowski, Kathryn Blackmer Reyes, Peggy Cabrera, Ann Agee

Faculty Research, Scholarly, and Creative Activity

San José State University (SJSU) is located in downtown San José, a city of over one million residents in California’s San Francisco Bay Area. Established in 1857, SJSU is the oldest public university on the west coast of the United States. It is also the founding campus of the California State University (CSU) system that comprises twenty-three campuses, making it the largest four-year public university system in the country. SJSU has nine colleges and sixty-seven departments, which offer bachelor’s, master’s, and a growing number of doctoral degree programs. It enrolls over 36,000 students and employs more than 2,100 faculty members. …

[Review Of] Abolition Geography, By Ruth Wilson Gilmore, Jennifer Rycenga

Faculty Research, Scholarly, and Creative Activity

No abstract provided.

Enhancing Diagnostic Accuracy: A Hybrid Approach To Mitigate Speckle And Rician Noise In Medical Images, Naveenkumar Jayakumar, Saurabh Saoji, Sagar V. Joshi, Hemlata Mane, Roshni Narkhede, Shrikant Jadhav

Faculty Research, Scholarly, and Creative Activity

This research explores the detrimental effects of Rician and speckle noise in medical imaging, particularly within MRI and radiographic modalities. Such noise can significantly obscure critical details, potentially leading to misdiagnoses and inaccurate measurements. Rician noise candidly dangles on the signal strength. Removing this noise affects the origial information in image that makes this noise removal perplexing. On other hand speckle noise is visualised like granular clog in ultrasound imageries. It creates ambiguous details and edges in the images. To address this challenge, the study introduces a novel hybrid method implemented in Java. The method employs a frequency-based decomposition approach …

Eyes On Higher Education: Evaluating Web Usability In Kuwaiti Private Universities Using Eye-Tracking And Supr-Q Metrics, Reem Albaghli, Ayah Beidas, Nada Attar

Faculty Research, Scholarly, and Creative Activity

Website design and usability are critical factors that impact the effectiveness of a website, influencing both user attraction and retention. Understanding user preferences is essential for designers and researchers when optimizing user interfaces (UI) and user experiences (UX). This study addressed key research questions about usability by examining which design heuristics have the most impact on students’ interactions with private university websites in Kuwait. By assessing web design and usability across three private universities in Kuwait through specific tasks, we analyzed user experiences using eye-tracking data, task completion times, user inputs, and qualitative feedback from the Standardized User Experience Percentile …

Marine Protection And Environmental Forcing Influence Fish-Derived Nutrient Cycling In Kelp Forests, June Shrestha, Joseph R. Peters, Jennifer E. Caselle, Scott L. Hamilton

Faculty Research, Scholarly, and Creative Activity

Animal consumers excrete dissolved inorganic nitrogen, an essential nutrient for regulating primary production and macroalgal growth in the ocean. Often overlooked in attempts to explain kelp forest productivity, relatively little is known about the role of consumers in nutrient cycling in temperate systems, such as the magnitude of nutrients excreted and the factors that influence spatial and temporal variability in consumer-derived nutrients. To investigate the supply of ammonium (NH4+) excreted by the dominant members of the nearshore rocky reef fish community, we combined empirically-measured relationships between excretion rate and body mass with data on fish density and size structure from …

Next Steps For Assessing Ocean Iron Fertilization For Marine Carbon Dioxide Removal, Ken O. Buesseler, Daniele Bianchi, Fei Chai, Jay T. Cullen, Margaret Estapa, Nicholas Hawco, Seth John, Dennis J. Mcgillicuddy, Paul J. Morris, Sara Nawaz, Nishioka, Anh Pham, Kilaparti Ramakrishna, David A. Siegel, Sarah R. Smith, Deborah Steinberg, Kendra A. Turk-Kubo, Benjamin S. Twining, Romany M. Webb

Faculty Research, Scholarly, and Creative Activity

There are many potential approaches to marine carbon dioxide removal (mCDR), of which ocean iron fertilization (OIF) has the longest history of study. However, OIF studies to date were not primarily designed to quantify the durability of carbon (C) storage, nor how wise OIF might be as an mCDR approach. To quantify C sequestration, we introduce a metric called the “centennial tonne,” defined as 1,000 kg of C isolated from atmospheric contact for on average at least 100 years. We present the activities needed to assess OIF from a scientific and technological perspective, and additionally, how it might be responsibly …

Optimal Tool Path For Extrusion-Based Additive Manufacturing To Improve Geometrical Accuracy And Productivity, Robert Ehlers, Amir Armani

Faculty Research, Scholarly, and Creative Activity

The objective of this study was to improve the geometrical accuracy and productivity of extrusion-based additive manufacturing processes. Four algorithms were developed to adaptively change the track width in each layer (i.e., adaptive rastering); optimize the rastering orientation for each layer; adaptively change the layer thickness (i.e., adaptive slicing); and optimize the overall orientation of part. These algorithms were implemented in a commercial 3D printer and several case-studies were conducted to examine their efficacy (individually and combined). The results were compared with standard tool path planning software and indicated a significant improvement in both geometrical accuracy and productivity.

Poor Nutrition Status Associated With Low Patient Satisfaction Six Months Into Treatment For Head And Neck/Esophageal Cancer Treatment: A Prospective Multicenter Cohort Study, Adrianne M. Widaman, Andrew G. Day, Maggie A. Kuhn, Rupinder Dhaliwal, Vickie Baracos, Merran Findlay, Judith D. Bauer, Marian De Van Der Schueren, Alessandro Laviano, Lisa Martin, Leah Gramlich

Faculty Research, Scholarly, and Creative Activity

Background: Patient-reported outcome measures have been associated with survival in oncology patients. Altered intake and malnutrition are common symptoms for patients treated for head and neck cancer and esophageal cancer (HNC/EC). The purpose of this study was to examine the relationship between patient-reported satisfaction with medical care and nutrition status. Methods: This prospective cohort study collected data from 11 international cancer care sites. Results: One hundred and sixtythree adult patients (n = 115 HNC; n = 48 EC) completed a patient satisfaction questionnaire (the Canadian Health Care Evaluation Project Lite) and were included. HNC/EC patient global satisfaction with medical care …

Public Libraries Encouraged To Meet The Health Information Needs Of Tribal Women In Bangladesh, Lili Luo

Faculty Research, Scholarly, and Creative Activity

Objective – To investigate public libraries’ existing community engagement practices, explore their willingness to provide health information services to tribal communities in Bangladesh, and examine tribal women’s health information-seeking behavior and interest in obtaining health information from public libraries. Design – A cross-sectional study using online interviews and structured questionnaires. Setting – Public libraries and tribal communities in tribal regions of Bangladesh. Subjects – Public librarians (n=11) and tribal women (n=276) from three tribal districts in Bangladesh (Bandarban, Khagrachari, and Mymensingh). Methods – Interviews were conducted with librarians via Zoom in January 2023. Survey questionnaires were distributed to a convenience …