Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

San Jose State University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 211 - 240 of 11653

Full-Text Articles in Entire DC Network

Multi-Agent Path Planning And Optimization Using Q-Learning, Chirag Rudrish Jan 2026

Multi-Agent Path Planning And Optimization Using Q-Learning, Chirag Rudrish

Master's Projects

Robot navigation in a multi-agent setting requires a balance between safety and efficiency, especially in dense environments. In these two-dimensional spaces, the scope for geometric errors is much less and could lead to collisions or immobility. This project proposes to address the navigation task using a two-phase path planning pipeline that combines reinforcement learning and convex optimization in a scalable and robust manner. The first phase consists of generating diverse collision-free paths using a Q-learning agent that is trained on a visibility graph representation of the environment. The discretization of the environment using waypoint-based graphs allows the agent to train …

Go to article

Cost-Aware Predictive Routing For Vision-Language Models, Sahil Sait Naveed Jan 2026

Cost-Aware Predictive Routing For Vision-Language Models, Sahil Sait Naveed

Master's Projects

Vision-language models (VLMs) are increasingly used for multimodal tasks, but their inference costs vary widely across model tiers. This work presents a predictive routing framework that assigns each query to the most cost-effective VLM by using multimodal embeddings, clustering, and per-cluster model error estimates. Evaluated on six commercial VLMs, the selected router reduces average cost by about 49 percent relative to the quality-first setting on both validation and test. This comes with accuracy losses of 0.4 percentage points on validation and 0.9 on held-out test data. It also outperforms K-NN and ZeroRouter routing baselines while providing lowercost operating points than …

Go to article

Impact Of Cigarette Smoke On Immune And Stromal Cells, Justin Wong Jan 2026

Impact Of Cigarette Smoke On Immune And Stromal Cells, Justin Wong

Master's Projects

Cigarette smoke is a plight on human health, being a major contributor to lung diseases. The aryl hydrocarbon receptor (AHR) directs immune regulation and metabolic adaptation in response to environmental toxins. This study investigates transcriptomic changes between wild-type and AHR knockout mouse lung tissue under smoke and air conditions. Single-cell RNA sequencing data were generated by the Butcher Lab and analyzed in Seurat for differential gene expression (DGE) analysis. A two way ANOVA framework was used with DGE analysis to classify genes as smoke induced or suppressed in an AHR dependent or independent manner, and these gene sets were analyzed …

Go to article

Searching For Cause Of Unexplained Protein Interaction With Multiple Assembly Methods, Gavin Anderson Jan 2026

Searching For Cause Of Unexplained Protein Interaction With Multiple Assembly Methods, Gavin Anderson

Master's Projects

Research into colistin adjuvants has identified interactions between a host of proteins and proteins found within certain strains of bacteria. BLAST, a widely adopted local sequence alignment tool, was used to create a database containing the genomes of relevant bacterial strains, which would then be used to query against the previously identified proteins. Many of these strains do not have publicly available assemblies, which makes database construction difficult. CATwalk, a new naïve fragment extender, is first described in this paper and used to extend fragments of interest. BLAST results first identified short fragments with sufficient similarity, which can then be …

Go to article

Detection And Characterization Of Cancer Using Cfdna Fragmentomic Analysis, Guneet Bhogal Jan 2026

Detection And Characterization Of Cancer Using Cfdna Fragmentomic Analysis, Guneet Bhogal

Master's Projects

Cell-free DNA (cfDNA) fragmentomics has emerged as a promising non-invasive approach for detecting and characterizing cancer by analyzing DNA fragmentation patterns. These fragment patterns are unique and can be used to distinguish between tumor and healthy DNA. This paper uses machine learning models to detect cancer by evaluating Shannon entropy of fragment lengths at the first coding exon 1 regions and correlating them to targeted cancer genes. This approach was applied to two datasets consisting of samples with prostate, breast, and lung cancers. Our results indicated that exon 1 fragmentation entropy captures biologically relevant differences in cancer-specific chromatin organization and …

Go to article

Combining Crispr And Nanoasv To Uncover The Rare Bacterial Communities Of The Human Oral Microbiome, Gilma Ruth Sevilla Alvarez Jan 2026

Combining Crispr And Nanoasv To Uncover The Rare Bacterial Communities Of The Human Oral Microbiome, Gilma Ruth Sevilla Alvarez

Master's Projects

Studying the oral microbiome is vital because its health implications are not contained to the mouth. Cariogenic bacteria cause tooth demineralization and oral microbes that translocate to extra-oral organ systems are linked to conditions like Alzheimer’s disease, heart disease, diabetes, and cancer. Some of these pathogens belong to the most abundant phyla in the oral cavity: Bacillota, Pseudomonadota, Bacteroidota, Actinomycetota, Spirochaetota, and Fusobacteriota, which together comprise 94% of the oral microbiome. This project uses CRISPR-Cas9 to deplete sequences from highly abundant phyla and the Eubacteria domain, enriching the remaining 6% of rarer taxa. Paired with NanoASV for single-nucleotide resolution, this …

Go to article

Javatutor: An Integrated Llm Framework For Structured Programming Tutoring And Problem-Solving In Java, Amey Makarand Dhongade Jan 2026

Javatutor: An Integrated Llm Framework For Structured Programming Tutoring And Problem-Solving In Java, Amey Makarand Dhongade

Master's Projects

Large Language Models (LLMs) are being adopted more actively to assist in pro- gramming tasks, but much of the available AI code assistants devices are encouraging the rapid generation of solutions, as opposed to assisting students in developing an understanding. As a result, they can give the students correct code without teaching on how to judge a problem and how to build solutions or how to debug their programs themselves. This study describes JavaTutor, an LLM-based tutoring system that is used to assist learners in the learning process in a three-step process of understand- ing, generating a solution, and refining …

Go to article

Safe-R2r: A Safety-Aware And Budget-Optimized Retrieval Controller For Rag Systems, Mandar Sunil Gondane Jan 2026

Safe-R2r: A Safety-Aware And Budget-Optimized Retrieval Controller For Rag Systems, Mandar Sunil Gondane

Master's Projects

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models by incorporating external evidence during inference. However, most RAG systems rely on fixed retrieval strategies that ignore query difficulty, computational cost, and prediction uncertainty. This project introduces SAFE-R2R (Safety-Aware and Budget-Optimized Reason-to-Retrieve), a retrieval controller that treats retrieval as a query-dependent decision problem. SAFE-R2R organizes retrieval into a multi-rung ladder ranging from no retrieval to deeper retrieval with reranking. At each rung, the system generates an answer, computes reliability signals, and combines them into a risk score used within a conformal calibration framework to decide whether to accept the answer …

Go to article

Multimodal Emotion Detection System, Shubhankar Sameer Munshi Jan 2026

Multimodal Emotion Detection System, Shubhankar Sameer Munshi

Master's Projects

Trying to understand emotion from speech is a problem that is present in human computer interaction. Nevertheless, there are still some shortcomings in current SER methods. Text-based systems may miss vital vocal cues, such as sarcasm, tone changes, and delivery. On the other hand, purely audio-based systems are prone to noise and unstable acoustic features. The combination of linguistic and acoustic features in multimodal approaches partially solves this problem, but many existing approaches use inflexible multimodal fusion techniques that cannot adjust their behaviors according to the quality of input signals. In this work, we propose a multimodal approach based on …

Go to article

Modeling Sealed Deck Construction In Collectible Card Games Using Learning-To-Rank Approach, Michael Dinh Nguyen Jan 2026

Modeling Sealed Deck Construction In Collectible Card Games Using Learning-To-Rank Approach, Michael Dinh Nguyen

Master's Projects

Artificial intelligence has demonstrated strong performance in complex decision-making domains such as chess and Go, motivating research into its application for games with even richer rules and combinatorial complexity. In collectible card games like Magic: The Gathering, deck construction from a constrained card pool is a critical and challenging task that requires evaluating card strength, synergy, and resource balance. This project explores whether machine learning, specifically learning-to-rank (LTR), can effectively model these human decision processes to construct competitive decks in a sealed format. The results found here can also be applicable to other areas of note, such as sports drafting …

Go to article

Stepwise Sudoku Reasoning Training Using Transformers, Lok Man Chu Jan 2026

Stepwise Sudoku Reasoning Training Using Transformers, Lok Man Chu

Master's Projects

Sudoku is a constraint satisfaction problem that serves as a testbed for studying reasoning and stepwise deduction. While many solvers can produce correct solutions, they often fail to generate human interpretable sequences of logically consistent steps. This study investigates whether a transformer trained on stepwise deduction traces can learn to solve Sudoku puzzles through sequential, logically deducible moves. Results show that solve accuracy improves significantly with more training data, reaching approximately 78% at 1500k samples. Stepwise analysis indicates that the model effectively learns simple strategies, achieving near-perfect performance. However, performance on more complex strategies remains limited. Overall, while the model …

Go to article

Multi-Agent Path Planning And Optimization Using Q-Learning, Chirag Rudresh Jan 2026

Multi-Agent Path Planning And Optimization Using Q-Learning, Chirag Rudresh

Master's Projects

Robot navigation in a multi-agent setting requires a balance between safety and efficiency, especially in dense environments. In these two-dimensional spaces, the scope for geometric errors is much less and could lead to collisions or immobility. This project proposes to address the navigation task using a two-phase path planning pipeline that combines reinforcement learning and convex optimization in a scalable and robust manner. The first phase consists of generating diverse collision-free paths using a Q-learning agent that is trained on a visibility graph representation of the environment. The discretization of the environment using waypoint-based graphs allows the agent to train …

Go to article

Broadening Replication Standards For Vignette Studies: Introducing Contextually Appropriate Replications, Birgit Schyns, Gretchen Vogelgesang Lester, Michelle M. Hammond Jan 2026

Broadening Replication Standards For Vignette Studies: Introducing Contextually Appropriate Replications, Birgit Schyns, Gretchen Vogelgesang Lester, Michelle M. Hammond

Faculty Research, Scholarly, and Creative Activity

Vignette studies present specific challenges for replications, yet vignettes are a popular choice for replication studies in leadership. In our review of eight vignette-based leadership publications, only two were able to fully replicate the original study's findings. We suggest that part of the failure to replicate the results of vignette studies may be due to a misalignment between the vignettes and social reality at the time of data collection. This paper highlights the challenges vignettes present due to societal progression and includes recommendations regarding potential methodological artifacts including the appropriateness of the sample, vignette content, and modality. We first discuss …

Go to article

Scoring Equitable Transit: A Data-Driven Framework For Affordable Transit-Oriented Development In California, Ahoura Zandiatashbar, Anton Rozhkov, Stephanie Nemet, Atticus Washington, Mounashree Prasanna Jan 2026

Scoring Equitable Transit: A Data-Driven Framework For Affordable Transit-Oriented Development In California, Ahoura Zandiatashbar, Anton Rozhkov, Stephanie Nemet, Atticus Washington, Mounashree Prasanna

Mineta Transportation Institute

Transit-Oriented Development (TOD) is a cornerstone of California’s climate and land use policy, promising walkable, compact neighborhoods near high-quality transit. However, these benefits are not always distributed equitably. This study introduces a scalable framework for identifying and scoring Affordable Transit-Oriented Development (A-TOD) across the state’s High-Quality Transit Areas (HQTAs). The goal is to equip policymakers, planners, and housing agencies with tools to evaluate station areas based on their physical form, affordability, and equity outcomes. Using a 1.5-mile network-based pedestrian buffer around over 66,000 transit stations, the research team developed a three-stage clustering and scoring system. Station areas were classified by …

Go to article

Numerical Modeling Of Climate Change Impacts On Transportation Embankments, Amr Morsy, Mamata Sapkota, Emma Varela, Odalys Portillo Jan 2026

Numerical Modeling Of Climate Change Impacts On Transportation Embankments, Amr Morsy, Mamata Sapkota, Emma Varela, Odalys Portillo

Mineta Transportation Institute

Embankments are essential components of transportation infrastructure, providing crucial support for long stretches of highways, railways, and other routes in California and around the world. Clay embankments are susceptible to weather-related deterioration processes that can gradually compromise their stability and, in some cases, lead to unexpected failures. Climate change, along with the associated shifts in weather patterns, is projected to adversely impact the weather-related deterioration processes, leading to exacerbated failures and/or shorter service life. Additionally, climate change is projected to increase the frequency of extreme precipitation events, leading to an increase in embankment failure potential. This study evaluated (1) the …

Go to article

The Ideological Work Of Penal Reform: How Reformers Justify Penal-Welfare Hybridization, John Halushka, Brandon Miller Jan 2026

The Ideological Work Of Penal Reform: How Reformers Justify Penal-Welfare Hybridization, John Halushka, Brandon Miller

Faculty Research, Scholarly, and Creative Activity

This article uses the Santa Clara County Reentry Resource Center (RRC) as a case study to explore the cultural content of penal reform. Specifically, we explore the discourses that officials use to publicly justify projects of penal-welfare hybridization, or the linking of state systems of punishment and welfare to manage criminalized populations. Our qualitative analysis draws on a dataset consisting of county planning documents, budgets, videos, press releases, and newsletters published online between 2011 and 2023. By examining these materials over time, we are able to chart patterns of consistency and variation in how officials justify hybridization. We find that …

Go to article

Generation Of Impact Factor-Driven Security Rating Questionnaire Using Llms For Aiot Applications, Yuna Han, Simon Shim, Deva Kumar Gajulamandyam, Yeji Choi, Hyunwoo Lee, Hangbae Chang Jan 2026

Generation Of Impact Factor-Driven Security Rating Questionnaire Using Llms For Aiot Applications, Yuna Han, Simon Shim, Deva Kumar Gajulamandyam, Yeji Choi, Hyunwoo Lee, Hangbae Chang

Faculty Research, Scholarly, and Creative Activity

Industry 4.0 has transformed industries by accelerating the adoption of artificial intelligence of things (AIoT); however, it has also led to security risks, such as data leakage. Existing data protection research focuses on network layers, whereas application-layer rating systems rely on subjective evaluations, limiting consistency and applicability. This study proposes a scalable and objective AIoT security rating framework that clarifies ambiguities in the five-question rating system of the Korean Intellectual Property Office and unifies fragmented managerial and technical rating systems. By leveraging large language models (LLMs), the framework integrates a security rating model based on 14 impact factors with automated …

Go to article

Re-Evaluating Virtual Reality Manipulation Techniques For Precise Alignment Of Complex 3d Objects, Cherelle Connor, Alexander Giovannelli, Leonardo Pavanatto, Francielly Rodrigues, Haichao Miao, Vuthea Chheang, Brian Giera, Peer Timo Bremer, Doug A. Bowman Jan 2026

Re-Evaluating Virtual Reality Manipulation Techniques For Precise Alignment Of Complex 3d Objects, Cherelle Connor, Alexander Giovannelli, Leonardo Pavanatto, Francielly Rodrigues, Haichao Miao, Vuthea Chheang, Brian Giera, Peer Timo Bremer, Doug A. Bowman

Faculty Research, Scholarly, and Creative Activity

Prior research has developed a number of manipulation techniques that can achieve precise object placement in virtual reality, but studies of these techniques typically use simple objects. We conducted a study comparing two existing techniques, (AMP-IT and WISDOM), during alignment of objects with complex geometry to evaluate the potential influence of geometric complexity on performance, usability, workload and preference. Our findings indicate that participants had faster completion times and higher trial completion rates with AMP-IT on high-precision alignment tasks, contrary to earlier findings that used simple objects. Yet WISDOM is still preferred and considered more usable, despite increased workload and …

Go to article

Pattern-Aware Graph Neural Networks For Handling Missing Data, Minett Tran, Taehee Jeong Jan 2026

Pattern-Aware Graph Neural Networks For Handling Missing Data, Minett Tran, Taehee Jeong

Faculty Research, Scholarly, and Creative Activity

Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that missingness occurs randomly. However, missingness patterns might provide additional information. We propose pattern-aware graph neural networks that explicitly encode which features are missing alongside observed values. We used four encoding strategies-learned embeddings, frozen random embeddings, statistical features, and hierarchical representations-across seven UCI datasets with naturally occurring missingness. Our Pattern-aware methods achieve substantial improvements over baselines, with an average improvement of 17% in balanced accuracy and 22% in F1-macro across all datasets. Our code and …

Go to article

Rethinking Library Opac: From Siloed Retrieval To Ai And Ml-Driven Discovery Using Fastapi And Mysql, Sukumar Mandal Jan 2026

Rethinking Library Opac: From Siloed Retrieval To Ai And Ml-Driven Discovery Using Fastapi And Mysql, Sukumar Mandal

Library Philosophy and Practice (e-journal)

The paper explores integration methods between MySQL and FastAPI to develop dynamic Online Public Access Catalog services including functionalities for modern libraries and information centers. It addresses evolving user expectations by replacing rigid keyword-based search models with adaptive, intelligent discovery experiences that prioritize search relevance. The goal involves transforming traditional library retrieval tools into contextual discovery platforms that effectively understand specific user intent and complex needs. The prototype was created on Ubuntu in a customized Python environment. It uses FastAPI to manage asynchronous API calls and MySQL to store bibliographic data. SQLAlchemy abstracts the database layer, and Pydantic validates data. …

Go to article

Comment On Shamsaei Et Al. The Role Of Fuel Characteristics And Heat Release Formulations In Coupled Fire-Atmosphere Simulation. Fire 2023, 6, 264, Aurélien Costes, Adam K. Kochanski Dec 2025

Comment On Shamsaei Et Al. The Role Of Fuel Characteristics And Heat Release Formulations In Coupled Fire-Atmosphere Simulation. Fire 2023, 6, 264, Aurélien Costes, Adam K. Kochanski

Faculty Research, Scholarly, and Creative Activity

Accurate vertical distribution of fire-induced heat fluxes in the atmosphere is critical for realistic coupled fire–atmosphere simulations. In response to concerns raised by Shamsaei et al. (2023) regarding potential energy conservation issues in the WRF-SFIRE heat distribution scheme, this study first conducts a comprehensive theoretical analysis, demonstrating that the original exponential formulation exhibits negligible error under typical domain configurations. Then, it introduces a novel formulation, called the Versatile Energy-Conservative Distribution scheme, that rigorously guarantees energy conservation while providing enhanced flexibility in specifying vertical distribution profiles. The proposed method accommodates multiple profiles, including exponential, Gaussian, and gamma, and enables the independent …

Go to article

Exploring Math Word Problem Generation With Llms, Trung Hieu Vuong Dec 2025

Exploring Math Word Problem Generation With Llms, Trung Hieu Vuong

Master's Theses

Math Word Problem (MWP) is an important building block for learning math. This type of problem is particularly useful for younger audiences because solving it involves two simultaneous skill sets: reading comprehension and mathematical reasoning. With publicly available large language models (LLMs), generating additional MWPs is readily achievable. While researchers have started using LLMs as MWP facilitators, there still exists a gap in studies about the diversity of MWPs generated by unmodified, publicly accessible LLMs. For that reason, our study focused on two goals: (1) to evaluate the diversity of MWPs generated by publicly available LLMs when provided with examples …

Go to article

Developing A Vietnamese Text Summarization Large Language Model On Limited Hardware, Tin Pho Dec 2025

Developing A Vietnamese Text Summarization Large Language Model On Limited Hardware, Tin Pho

Master's Theses

Text summarization models have achieved significant growth during the last few years because of major Large Language Model (LLM) technological advancements. The application of LLMs are widely used in news distribution (TL;DR news), translation tools (DeepL Translate), or virtual assistants (ChatGPT, DeepSeek, Claude, etc.). However, the progress has not yet reached all languages equally. The Vietnamese language is used by more than 90 million people, but the language is not as highly developed for LLM as it has many homophones, five different tones that affect meaning of words, and irregular grammar compared to other languages (e.g. English, Spanish, etc.). Also, …

Go to article

Estimating Prey Capture Attempts And Activity Costs In Foraging Emperor Penguins (Aptenodytes Forsteri) Using Integrated Biologging Data, Taylor Rose Azizeh Dec 2025

Estimating Prey Capture Attempts And Activity Costs In Foraging Emperor Penguins (Aptenodytes Forsteri) Using Integrated Biologging Data, Taylor Rose Azizeh

Master's Theses

To forage efficiently in patchy and unpredictable prey landscapes, marine predators must optimize energy intake while minimizing costs. Central place foragers like emperor penguins face greater energetic constraints during demanding periods of high investment like chick-rearing. I used high-resolution tri-axial acceleration, depth, and GPS data from 25 birds from two feeding seasons (2019 and 2022) to quantify prey capture attempts and a proxy for energy expenditure (overall dynamic body acceleration; ODBA) across dive types (epipelagic, mesopelagic, benthic), phases (descent, bottom, ascent), and over time at-sea. While prey capture attempts per minute did not differ when looking across dive types alone, …

Go to article

Automatic Guitar Transcription Of Polyphonic Music, Ritwik Patil Dec 2025

Automatic Guitar Transcription Of Polyphonic Music, Ritwik Patil

Master's Theses

Transcribing guitar music automatically is a complex task due to polyphonic overlap, tuning variations, and diverse playing techniques. Current transcription systems focus on identifying note pitches and timing while ignoring performance techniques that describe how the notes are played, treating guitar recordings as generic polyphonic audio and producing MIDI-like outputs that lose important information about articulation and style. To address these challenges, we propose an end-to-end transformer model for automatic guitar transcription. The system uses a T5-based encoder-decoder architecture that processes the Constant-Q Transform (CQT) of stereo audio input. The stereo representation helps separate individual guitar parts within a mix …

Go to article

Latent Action Trajectory Optimization, Rahul Milind Kandekar Dec 2025

Latent Action Trajectory Optimization, Rahul Milind Kandekar

Master's Theses

Learning from demonstrations offers a path to bypass the sample inefficiency of reinforcement learning, but obtaining action-labeled expert demonstrations remains expensive and often impractical. Learning from Observations (LFO) addresses this by learning policies from observation-only demonstrations. Recent LFO work relies heavily on behavior cloning: VPT and LAPO use observation-only data combined with limited action labels to train BC policies, while AIME offers an alternative policy inference approach but requires the majority of its training data to have action labels. Through systematic experiments in the Lunar Lander environment, we investigate whether latent action methods can function when state and action dimensionalities …

Go to article

Attitudes And Perception Of Lis Students Towards Artificial Intelligence(Ai), Shahzadi Humbhi, Shabbir Tareen, Alia Humbhi Dec 2025

Attitudes And Perception Of Lis Students Towards Artificial Intelligence(Ai), Shahzadi Humbhi, Shabbir Tareen, Alia Humbhi

Library Philosophy and Practice (e-journal)

Artificial Intelligence refers to computer systems that can think and behave like humans. It is becoming essential in the education system as it has the potential to transform the way of teaching and learning in an academic environment. Therefore, the current study aims to investigate LIS students' attitudes and perceptions of AI, as well as how these technologies benefit their academic performance. The study also identified barriers that LIS students confront when adopting AI tools. For this purpose, a survey questionnaire was designed to assess students' knowledge and attitudes concerning AI, as well as its applications to improve academic performance. …

Go to article

Ischool Student Research Journal, Vol.15, Iss.2 Dec 2025

Ischool Student Research Journal, Vol.15, Iss.2

School of Information Student Research Journal

No abstract provided.

Go to article

Supporting Literacy And The Scholarly Conversation Through Understanding Apa Citation Style, Vanessa Sztym Dec 2025

Supporting Literacy And The Scholarly Conversation Through Understanding Apa Citation Style, Vanessa Sztym

School of Information Student Research Journal

No abstract provided.

Go to article

The Effects Of Educational Materials On Knowledge And Attitudes Toward Psilocybin, Lindsey Elise Wade Dec 2025

The Effects Of Educational Materials On Knowledge And Attitudes Toward Psilocybin, Lindsey Elise Wade

Master's Theses

Depression is one of the most prevalent and burdensome mental health conditions worldwide, affecting millions and contributing to over 700,000 deaths by suicide annually. Nearly half of patients with major depressive disorder fail to respond adequately to standard antidepressant treatments such as selective serotonin reuptake inhibitors (SSRIs). Psilocybin-assisted therapy (PAT) has emerged as a promising alternative for treatment-resistant depression (TRD), yet public understanding of this therapy remains limited. The present study examined whether a brief psychoeducational intervention could affect knowledge and attitudes toward PAT among members of the general public in the United States. Participants were randomly assigned to read …

Go to article

First Prev Next Last