足彩app哪个是正规的sis/Project Final Defense Schedule

Join us as the School of STEM master’s degree candidates present their culminating thesis and project work. 足彩app哪个是正规的 schedule is updated throughout the quarter, check back for new defenses.

View previous quarter schedules

Select a master’s program to navigate to candidates:

Master of Science in Computer Science & Software Engineering

SPRING 2026

Monday, May 18

Khushaal Kamal Kurswani

Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Khushaal Kamal Kurswani’s online defense
Project: Building an Extensible Explainable AI Module for Mental Health Conversational AI

Due to the rise of mental health issues and shortage of mental health professionals, people turn towards AI powered chatbots and virtual assistants for support and mental health related advice. One such chatbot application is the Data Analysis & Intelligent Systems (DAIS) laboratory’s iCare web application. 足彩app哪个是正规的 Large Language Models used in such chatbots are black boxes and it is difficult to trust and verify their advice. 足彩app哪个是正规的 solution to this lack of transparency is Explainable AI which are tools and algorithms that can provide insight into a machine learning model’s inner workings and explain their decision-making process in a human understandable manner.

This project integrates several Explainable AI algorithms such as Feature Ablations, Layer Integrated Gradients, and Shapley Value Sampling into the iCare web application to explain the LLM’s text generation process. Furthermore, an extensible framework was added to iCare to allow for easy integration of Explainable AI in the future. 足彩app哪个是正规的se algorithms were evaluated based on time and accuracy. User surveys were also conducted to gather feedback on user experience of the explanation feature. Based on the evaluation results, all three algorithms achieved similar levels of accuracy and had excessive processing times. Layer Integrated Gradients performed the best with the highest accuracy and shortest processing time. Additionally, user feedback highlighted a significant preference for natural language explanations over raw token attributions, indicating a need for more intuitive communication of model reasoning.

Tuesday, May 19

Bo Fu

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Bo Fu’s online defense
足彩app哪个是正规的sis: Enhancing Parallelization of Agent-based Graph Computing

足彩app哪个是正规的 demand for distributed data processing grows as modern applications involve increasingly large and complex datasets. Traditional distributed computing frameworks, such as Apache Spark and Hadoop MapReduce, are effective for large-scale data processing but are not always well suited for graph computation. 足彩app哪个是正规的 MASS (Multi-Agent Spatial Simulation) Java library instead provides an agent-based approach to distributed graph computation and has been proven effective for graph computing applications and graph database. However, the performance of MASS Java remains limited in some cases because graph applications often require many agent operations, which introduces significant overhead.

To address these limitations, this thesis introduces several enhancements for improving agent execution performance in MASS Java and evaluates them using graph computing applications and graph database queries. 足彩app哪个是正规的 evaluation shows that the enhancements can improve MASS Java performance in both graph computing and graph database query execution. In addition, this thesis identifies a major overhead in the current MASS graph database and proposes a solution to reduce it. Overall, this thesis contributes to the optimization and evaluation of MASS Java for graph applications and provides useful guidance for future development.

Wednesday, May 20

Josiah Zacharias

Chair: Dr. William Erdly
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Josiah Zacharias’ online defense
Project: Opto-mistic 足彩app哪个是正规的rapy: Modernizing Stereoscopic Vision 足彩app哪个是正规的rapy through Cutting-Edge Games

Pediatric vision impairments frequently go undiagnosed in underserved communities, impacting learning and cognitive development. 足彩app哪个是正规的 EYE Toolbox, developed by the Near Vision Institute (NVI) in partnership with the EYE Research Group at UW Bothell, is a web-based platform supporting NVI’s school-based optometry services across 50+ Washington districts. This project modernized the platform in three engineering phases. Phase 0 hardened 573 PHP files: raw mysqli_query references dropped from 3,905 to 97, jQuery was upgraded from 1.7.1 to 3.7.1, credentials moved to environment variables, and 41 of 45 live black-box attack probes were rejected against the dev deployment. Phase 1 introduced a REST API and React-based frontend to coexist with the legacy PHP/jQuery pages; paired-endpoint benchmarks showed response payloads 30–98% smaller across five surfaces and cumulative session bandwidth 65.1% lower than the legacy path. Phase 2 improved the production RDS vergence therapy application and added three new gamified prototypes (Base Builder, Balloon Pop, Animal Cart) on the shared Phase-1 infrastructure, each preserving the fusion-required vergence demand mechanism. Within-clinic before/after analysis of NVI’s session telemetry (14,653 sessions, 321 patients) found median peak vergence per session rose from 12.0 to 16.0 prism diopters under the new RDS application (+33% relative), with post-cutover patients leading at 19 of 20 session positions when controlling for therapy-course position; per-session personal-best rate rose from 7.5% to 10.4%. NVI standardized on the new application from cutover forward. A 5-week public demo-portal pilot (199 users, 207 sessions, 16 multiplayer challenges all finishing cleanly) shows voluntary engagement absent clinical referral pressure. A controlled clinical efficacy study integrating all four evaluation pillars is documented for follow-on work.

Thursday, May 21

Dazhi Li

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Dazhi Li’s online defense
足彩app哪个是正规的sis: Towards Smarter Trading: An AI Trading Framework Combining Reinforcement Learning and Large Language Model

足彩app哪个是正规的 rapid evolution of financial markets demands intelligent trading systems capable of synthesizing heterogeneous information and making adaptive decisions under uncertainty. In this paper, we propose a trading framework that leverages reinforcement learning (RL) to fine-tune a Large Language Model (LLM) for autonomous trade decision-making. Unlike prior approaches that depend on supervised pre-training with expert-annotated analyses or domain-specific corpora for cold-start guidance, our method applies Group Relative Policy Optimization (GRPO) directly to a general-purpose instruction-tuned LLM, enabling the model to develop trading competence purely through reward-driven exploration without curated professional signals.

足彩app哪个是正规的modelingests multi-source market observations — encompassing technical indicators, financial news, and corporate financial statements — within a rolling temporal window, and outputs structured trading strategies specifying action type, share quantity, take-profit price, and stop-loss price. This formulation enforces strategy completeness through explicit exit conditions while supporting flexible position sizing, bridging the gap between simplified academic models and practical trade execution.

To guide learning, we design a multi-dimensional reward function grounded in profitability and trading discipline. Each strategy is evaluated on path-dependent profit-and-loss, risk exposure relative to stop-loss levels, position sizing appropriateness, and regulatory adherence, providing fine-grained feedback that cultivates the model’s awareness of both return potential and downside risk.

We conduct comprehensive experiments along three dimensions: (1) model comparisons —contrasting the RL-trained LLM against its base model, alternative LLM architectures, and a DQN-based traditional RL trading agent to quantify improvements from RL fine tuning and LLM-based reasoning respectively; (2) training budget analyses — investigating how training steps influence the model; and (3) strategy ablations — examining the contributions of quantity-based position sizing. Results demonstrate that the proposed framework produces coherent, risk-aware trading strategies without supervised warm-up; the ablation analyses further yield insights into the respective roles of model capacity, training sufficiency, and strategy design.

Aqsa Inamdar

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Aqsa Inamdar’s online defense
Project: FinWise: Personalized Financial Empowerment

FinWise is a personal finance web application designed to help users better understand their spending behavior, manage transactions, track financial goals, and receive actionable financial guidance. 足彩app哪个是正规的 system combines a React and TypeScript frontend with a Node.js, Express, and Firebase backend to support transaction management, PDF-assisted transaction import, visual analytics, goal planning, and AI-assisted financial reasoning.

A key focus of the project is explainability. Rather than presenting users with opaque predictions, FinWise combines deterministic financial calculations, machine learning models, and large language model narration to produce responses that are traceable and easy to understand. 足彩app哪个是正规的 goal projection module uses LightGBM-based regression and classification models to forecast monthly savings, estimate goal completion timelines, and evaluate whether users are likely to meet their deadlines. 足彩app哪个是正规的 assistant supports descriptive, predictive, and prescriptive finance questions, helping users interpret trends, compare categories, forecast savings, and explore spending-reduction scenarios.

足彩app哪个是正规的 project emphasizes accessibility, usability, and financial literacy by presenting complex financial insights in plain language while preserving the underlying calculations. FinWise demonstrates how machine learning and AI-assisted interfaces can be integrated into a practical personal finance tool that supports informed decision-making and goal-oriented financial planning.

Pragnya Ambekar

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
2:00 PM.; Join Pragnya Ambekar’s online defense
足彩app哪个是正规的sis: Automated Detection of Architectural Anti-Patterns in React Applications Using Static Analysis

Architectural quality in React applications is difficult to measure and even harder to enforce automatically. As components grow over time, they tend to accumulate responsibilities gradually, through changes that are each individually reasonable, until they become too large and complex to maintain effectively. Unlike syntax errors or type violations, these structural problems are invisible to existing tools such as ESLint, TypeScript, and SonarQube, which means teams rely entirely on code review to catch them, an approach that is inconsistent and does not scale.

This research investigates whether architectural anti-patterns in React can be detected through static analysis with enough precision to be practically useful. 足彩app哪个是正规的 key methodological contribution is a combined metric approach for detecting oversized components, where a component must simultaneously exceed thresholds on Lines of Code, JSX element count, and hook count to be flagged. 足彩app哪个是正规的 reasoning is that any one of these metrics can be elevated for legitimate reasons, but a component that is large, structurally complex, and stateful all at once is almost always doing too much. This achieved 98.04 percent precision in the validation study, compared to roughly 62 percent when using a single metric.

Three independent reviewers assessed 71 components drawn from four production React codebases, Grafana, Mattermost, Refine, and TodoMVC. Average precision across all patterns was 86.39 percent, with Extreme severity cases reaching 100 percent. 足彩app哪个是正规的 62.5 percent inter-rater agreement also revealed something important: architectural quality is partly subjective, which means the right role for a tool like this is to flag components for human discussion, not to make final judgments.

One unexpected finding was that detection rates were consistent across all four repositories despite them varying enormously in size and age, suggesting that teams naturally maintain a stable level of architectural complexity over time rather than letting debt accumulate indefinitely.

Friday, May 22

Yumeng Pang

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Yumeng Pang’s online defense
足彩app哪个是正规的sis: Design and Benchmarking of a Citation Graph DB Across Neo4j, ArangoDB, and MASS Graph DB Systems

Academic collaboration, citation influence, and institutional research visibility are increasingly reflected through scholarly relationship networks. However, existing academic platforms remain largely profile-centered and do not provide an institution-focused, interactive, and queryable graph system for multi-hop exploration across authors, works, affiliations, and citations. This thesis investigates the design and benchmarking of a UWB citation graph, for practicality, seeded from CSS faculty scholarly activities, and examines how effectively different graph database systems support this richer graph model for practical scholarly exploration.

To address this problem, this work designs and implements a scholarly citation and co-authorship graph pipeline that constructs a heterogeneous Author–Work–citation–Affiliation graph using institutional seed data and OpenAlex-derived metadata. 足彩app哪个是正规的 resulting graph is intended to support practical use cases such as collaborator discovery and referee exploration for UWB CSS faculty. 足彩app哪个是正规的 system is evaluated across three graph databases—Neo4j, ArangoDB, and MASS Graph DB—and is benchmarked using LDBC-aligned workloads and metrics, including bulk ingestion throughput, query throughput, and multi-hop traversal latency. In addition to the institutional citation graph, the evaluation framework includes public benchmark datasets of different graph types, densities, and scales to enable broader cross-platform comparison.

足彩app哪个是正规的 results show that the heterogeneous scholarly citation graph provides substantially richer analytical capability than simpler single-relation citation graphs by enabling cross-relational exploration over authorship, affiliation, and citation structure. 足彩app哪个是正规的 benchmarking results further indicate that platform strengths are workload-and-graph-dependent: Neo4j performs strongly for interactive read-heavy exploration on the institutional citation graph, ArangoDB remains competitive in selected ingestion-oriented scenarios, and MASS Graph DB performs especially well on loading structurally simpler single-relation graph workloads.

Overall, the findings suggest that richer institutional citation graph modeling can remain practical for interactive exploration, while platform suitability depends on how well each system handles heterogeneous topology, traversal complexity, and deployment conditions.

Kris Yu

Chair: Dr. Annuska Zolyomi
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Kris Yu’s online defense
Project: Mystoria: AI-Assisted Authoring of Personalized Social Stories for Autistic Children

Social Stories? are a widely used intervention that helps autistic children understand and prepare for social situations, but creating personalized stories that follow established Social Stories? criteria can be time-consuming for caregivers. Existing digital tools often provide either fixed story libraries or free-form editors with limited support for methodological fidelity. This project presents Mystoria, an iPad and iPhone application that supports caregivers in authoring personalized Social Stories? with large language model assistance while preserving caregiver control. Mystoria combines multimodal story creation, including text, AI-generated and camera-sourced images, AAC pictograms, and caregiver-recorded audio, with an AI Draft workflow designed around the structural criteria for Social Stories?. 足彩app哪个是正规的 application includes an in-app draft-quality scorer that helps caregivers review saved drafts against those criteria, as well as a hybrid AI design that combines cloud-based generation with an optional on-device fine-tuned Gemma model for more privacy-aware authoring. Mystoria will be evaluated through a caregiver-only within-subject study in which each participant creates two stories on the same anchor topic: one manually and one with AI Draft. 足彩app哪个是正规的 study examines caregiver preference, trust in AI-generated content, perceived usability and usefulness, analysis of edits and sentence types, and feedback on appropriateness, privacy, and acceptable boundaries for AI assistance. 足彩app哪个是正规的 goal is to understand whether AI-assisted authoring can reduce caregiver burden while preserving personalization, caregiver agency, and adherence to established Social Stories? criteria.

Tuesday, May 26

Siddharth Thammineni

Chair: Dr. Geethapriya Thamilarasu
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Discovery Hall (DISC) 464
Project: Hybrid XAI-based Intrusion Detection for IoT Networks

足彩app哪个是正规的 rapid expansion of the Internet of Things (IoT) has created the need for anomaly-based intrusion detection systems (IDS) to use Machine Learning. Deep learning models are effective at identifying adaptive security threats, but their opaque nature limits interpretability. Explainable Artificial Intelligence (XAI) addresses this by providing techniques for producing an explanation for a model’s predictions. This project addresses how a hybrid XAI approach can provide accurate, valid explanations for IoT ML IDS models while maintaining real-time performance. 足彩app哪个是正规的 proposed solutions aggregate local explanations for global insight, using efficient feature attribution calculation provided by the FESP method, to produce an explanation using the MAPLE explanation framework that provides local diagnostics with awareness of global patterns. Experimental evaluation demonstrates that hybrid explanation approaches can provide accurate and defensible global and local interpretability while maintaining performance within practical real-time constraints

Wednesday, May 27

Robert Foskin

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Robert Foskin’s online defense
Project: Multi-GPU Agent Based Modeling MASS Agent Implementation

Agent-based models (ABM) attempt to simulate complex systems from the ground up using independent agents. ABMs are particularly suited to examining the emergent behavior of large-scale problems such as biological, economic or social systems. Success in modeling these systems depends on the ability to parallelize the execution of these models, reducing run times for very large problem sets.

足彩app哪个是正规的 Multi-Agent Spatial Simulation (MASS) library has been under development at UW Bothell since 2011. MASS abstracts many of the lower-level implementation details required for parallelizing agent-based modeling problems, providing researchers with a more accessible framework for developing large-scale simulations. MASS CUDA extends this approach to GPU-based execution, allowing agent-based models to take advantage of the massive parallelism offered by modern graphics processors. 足彩app哪个是正规的 library has undergone several iterations and enhancements, with recent development enabling simulation spaces to be extended across multiple GPUs connected using NVIDIA NVLink.

This project further extends MASS CUDA by enabling agents to migrate across GPU boundaries, allowing ABM simulations to fully function across multiple GPUs. Experimental results showed increases in both simulation size and execution performance.

Thursday, May 28

Garrett Woelfl

Chair: Dr. Brent Legesse
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Garrett Woelfl’s online defense
Project: MAST: A Maritime Analytics Platform for Operational Safety and Optimization

足彩app哪个是正规的 maritime logistics industry generates large volumes of operational data from vessel systems; however, much of this data remains underutilized within existing enterprise environments. This work presents the design and evaluation of the MAST (Maritime Analytics and Supporting Technology) platform, a data-driven platform developed in collaboration with Bernert Navigation Inc. to transform raw vessel data into actionable insights that support operational decision-making.

Unlike traditional approaches that require the development of entirely new software ecosystems, MAST leverages existing data infrastructure and augments it with easy to use, scalable capabilities. Through iterative development and stakeholder driven design, the system evolved from an initial focus on performance analytics to a broader platform emphasizing training augmentation and proactive safety improvement. By enabling users to review a large and diverse set of real vessel scenarios, MAST addresses key limitations of conventional training methods, which are often constrained by limited observational opportunities.

Evaluation of the system was conducted through stakeholder engagement, including detailed system walkthroughs and structured feedback sessions with operational leadership. Results indicate strong potential for improving training efficiency and reducing operational risk through increased scenario exposure and data accessibility by supporting a culture of continuous learning. Additional opportunities were identified such as contextual data integration.

This work contributes a practical framework for extending the value of existing maritime data systems while minimizing implementation overhead. More broadly, it demonstrates how data driven platforms can bridge the gap between operational data collection and meaningful organizational impact, enabling scalable improvements in training and long-term performance optimization.

Harsha Agarwal

Chair: Dr. Annuska Zolyomi
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Harsha Agarwal’s online defense
足彩app哪个是正规的sis: Connected Wellness: Designing a Peer-Supported Mobile Platform to Promote Social and Emotional Wellbeing Among Older Adults

Digital health technologies increasingly help people monitor physical activity, reflect on wellness data, and manage everyday health routines. However, many health-tracking systems emphasize individual metrics such as steps, goals, and progress indicators while overlooking older adults’ accessibility needs, social routines, and preferences for meaningful community engagement. Grounded in Self-Determination 足彩app哪个是正规的ory, HealthMate investigates how mobile health-tracking technologies can support older adults’ autonomy, competence, and relatedness through accessible design, clear feedback, and socially supportive wellness features.

This work examines older adults’ experiences with physical activity tracking, their preferences for peer-supported and community-based wellness tools, and the tradeoffs they consider when sharing progress or participating in socially oriented health features. Through interviews, co-design sessions, prototype development, and evaluation, the project identifies opportunities for designing health technologies that are usable, motivating, trustworthy, and socially meaningful.

HealthMate supports activity tracking, wellness reflection, community participation, and lightweight social connection. Rather than emphasizing competition or public achievement sharing, the design focuses on practical coordination, accessible progress feedback, and features that help older adults feel confident, independent, and connected. 足彩app哪个是正规的 project contributes design insights for personal health informatics systems that support healthy aging through both individual reflection and shared participation.

Rishabh Pratap Singh

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Discovery Hall (DISC) 464
足彩app哪个是正规的sis: Feature Extension of MASS C++ towards a General Purpose Library

MASS (Multi-Agent Spatial Simulation) C++ is a parallel computing library for agent-based simulations on distributed memory clusters, organised around the Bulk Synchronous Parallel model and a master-worker coordination scheme. Three structural limitations have constrained its applicability as a general-purpose runtime. An integer-based method dispatch scheme couples user-defined Place and Agent classes to the framework and propagates renumbering errors silently. A per-iteration master coordination cost of K × N barrier round-trips dominates wall-clock time on communication-intensive workloads. And a Places abstraction restricted to regular grids leaves social, biological, and transportation graphs without first-class support.

This thesis presents three feature extensions that address these limitations while preserving backward compatibility with existing MASS C++ programs. A three-tier dispatch architecture replaces integer switch/case with string-named methods, header-defined lambdas, and JIT-compiled lambdas, unified through a single registry. An IterationConfig phase pipeline backed by an AsyncHandle executor collapses the K × N master round-trip pattern into a single dispatch by allowing workers to advance through compute, communication, and agent-management phases autonomously. A graph stack consisting of GraphTopology, GraphPlaces, and GraphAgents extends MASS C++ from grid-only topologies to arbitrary graphs, with bidirectional adjacency, locality-aware partitioning, edge-constrained agent migration, Pregel-inspired combiners and aggregators, and a pluggable parser interface for user-defined graph formats.

足彩app哪个是正规的 extensions are evaluated on five benchmarks (Wave2D, SugarScape, PageRank, BFS Wavefront, and Random Walk) covering correctness, performance, and programmability. Compound execution reduces barrier round-trips by orders of magnitude and yields speedups that grow with the number of workers on Places-only workloads. SugarScape scaling exposes an O(P?) bottleneck in the existing all-to-all agent exchange protocol, which caps compound speedup as P grows and motivates the sparse neighbour-rank exchange that GraphAgents adopts. 足彩app哪个是正规的 graph stack also positions MASS C++ as the only system among the surveyed prior art that supports mobile agents over irregular topologies while remaining a drop-in extension of the existing grid-based runtime. 足彩app哪个是正规的 new dispatch tiers reduce per-method boilerplate by approximately 46% at overheads of 0-6% for header lambdas and 5-15% for JIT lambdas.

Nathaniel Jewel

Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Nathaniel Jewel’s online defense
Project: DeepTracer Diffusion: Atomic Structure Modeling with Generative Diffusion

Accurate identification of atomic positions and types in macromolecular structures is fundamental to understanding biological function at the molecular scale. Cryo-electron microscopy (cryo-EM) has transformed structural biology by enabling high-resolution visualization of complex biomolecules, yet deriving precise atomic models from cryo-EM density maps remains challenging due to noise, heterogeneity, and variability across datasets.

DeepTracer is an established de novo framework that employs four specialized U-Net models to predict atom locations and types from cryo-EM maps, with each network learning a distinct structural signal that is subsequently integrated into a complete protein model.

With DeepTracer Diffusion, we introduce the next evolution of this framework by integrating diffusion-based generative modeling to improve atomic position prediction and residue classification within cryo-EM density maps. Using a single Denoising Diffusion Probabilistic Model (DDPM), we jointly generate refined atomic coordinates and atom-type labels while remaining fully compatible with the existing DeepTracer post-processing pipeline. To support direct prediction of discrete atom-class labels, we introduce a novel one-hot reverse diffusion procedure that produces segmentation masks at every timestep. Across benchmark datasets, DeepTracer Diffusion increases residue coverage by 24.80\% and improves the total F1 score by 11.63\%.

足彩app哪个是正规的se gains demonstrate that DeepTracer Diffusion more accurately reconstructs atomic structures from experimental cryo-EM maps, even under substantial noise and resolution constraints. Our work advances computational structural biology by providing a scalable, AI-driven framework for macromolecular model building, with broad implications for drug discovery, protein engineering, and structural refinement.

Friday, May 29

Athresh Kiran

Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Athresh Kiran’s online defense
Project: 足彩app哪个是正规的 iCare Validation Engine: An Adaptive Framework for Assessing AI 足彩app哪个是正规的rapeutic Efficacy

足彩app哪个是正规的 iCare platform provides AI-driven mental health support through therapeutic chatbots, yet it currently lacks a systematic method to empirically validate the efficacy and safety of new generative models. To address this bottleneck in digital mental health AI, this project introduces the iCare Validation Engine, a foundational MLOps framework built as an extension of the existing platform. 足彩app哪个是正规的 engine integrates a full-stack A/B experimentation backend for stable user routing with an automated, asynchronous LLM-as-a-Judge evaluation pipeline that scores conversation transcripts on therapeutic alliance, empathy, and safety. Engineering validation confirmed consistent assignment integrity, correct lifecycle transition behavior, and a score parser success rate exceeding 97% against malformed model outputs. A pilot experiment successfully demonstrated the complete system operating end-to-end, transforming iCare into a dynamic “living laboratory” and establishing a viable foundation for continuous, evidence-based model improvement.

Adrian Albu

Chair: Dr. Kaylea Champion
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Discovery Hall (DISC) 464 or join Adrian Albu’s defense online
Project: Prism: Article-Level Media Comparison Through Automated Claim Extraction

Prism is a public website that, for each ongoing news event, produces a report showing which specific claims each news source reported, which it omitted, where sources directly contradict one another, and how each article’s tone and framing compare. Existing consumer tools such as Ground News and AllSides answer adjacent questions by attaching bias ratings to whole outlets rather than computing them from each article’s text. Prism’s contribution is to compute those signals from each article’s text at scale, across thousands of sources, without inheriting any third-party editorial labels. Behind the report, Prism extracts atomic claims from every article using a large language model, deduplicates them into a cross-source consensus pool, scores each article against the pool, and flags mutually exclusive claims as conflicts. Tone and framing are computed per article from the text. To establish that the extraction step is trustworthy on unfamiliar single-document text, the pipeline was benchmarked on two academic datasets, reaching F1=0.874 on Rotowire and recall=0.938 on BillSum. New events are ingested and analyzed within minutes of publication. Prism uses “claim” rather than “fact” deliberately: it extracts assertions without evaluating their correctness, and cross-source consensus reflects what is widely reported, not what is true.

Deepak Sujay Gudiseva

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
5:45 P.M.; Discovery Hall (DISC) 464
Project: Agent-Based Distributed Node2vec

Graph representation learning algorithms like Node2Vec generate highly accurate topological embeddings but impose severe memory and computational bottlenecks on centralized architectures. This paper presents a scalable, distributed Node2Vec engine engineered natively within the Multi-Agent Spatial Simulation (MASS) framework. By mapping second-order, biased random walks to autonomous mobile software agents, our architecture efficiently samples complex networks while bypassing single-machine memory limitations. We introduce a novel Compute-Node-Centric training paradigm that pairs isolated Skip-Gram neural network optimization with a decentralized, logarithmic tree-reduction synchronization protocol. Empirical evaluations across benchmark graphs (Cora and OGBL-DDI) demonstrate that this distributed engine achieves strict predictive parity with industry-standard PyTorch baselines across key ranking metrics like MAP, Recall.. etc. Ultimately, this architecture successfully outperforms linear methods like FastRP in topological accuracy while comprehensively unlocking the spatial scalability required for parallelized, deep graph learning.

Monday, June 1

Meghana Dayathri

Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Meghana Dayathri’s online defense
Project: Model-Grounded Explanations for Responses Generated from Conversational AI

Mental health conversational AI systems are becoming more common as tools for emotional support, reflection, and early guidance. For researchers and system designers, transparency helps evaluate whether a system’s responses are grounded in the conversation rather than simply sounding supportive. For users, this transparency matters because they may want to understand whether the system recognized their concern and responded to the right part of what they shared. A common approach is to ask a language model to explain its own response in free-form text, but these explanations can sound reasonable without being closely tied to the model behavior behind the response. This project develops a user-facing explanation feature for CareBot, a conversational AI system within the iCare project at the Data Analysis and Intelligent Systems (DAIS) Laboratory. Instead of generating a free-form justification, the feature traces a selected CareBot response back to earlier user messages that most strongly supported it. 足彩app哪个是正规的 approach uses Layer Integrated Gradients to compute token-level attribution scores for a selected response, maps those scores back to the original conversation, and converts the strongest user-side evidence into short, readable phrases. 足彩app哪个是正规的 explanation feature was evaluated through phrase-level deletion and human evaluation to examine both model-level faithfulness and user perceptions. Results showed that top-ranked phrases had a stronger effect on the model’s response score than low-ranked phrases, while human evaluation helped assess the explanation feature in terms of clarity, usefulness, and transparency.

Haobo Peng

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Commons Hall (UW2) 327
足彩app哪个是正规的sis: Agent-based Modeling with MASS CUDA on Multi-GPUs over Multi-Hosts

Agent-based modeling (ABM) is an approach for simulating the behaviour of a system through simple interation between individual agents and the environment, which is widely adopted in various fields. For better simulation performance, attempts have been made to utilize the GPU to parallelize the simulation tasks, and the CUDA version of the Multi-Agent Spatial Simulation library (MASS CUDA) is one of the general purpose ABM libraries aims at providing high-level APIs for users to implement and execute their simulations on a single NVIDIA GPU. However, as the scale and complexity of the ABM simulation increase, a single GPU may not be sufficient to handle large-scale simulations that cannot fit into the device memory. To handle such situations, a new version of MASS CUDA is intorduced in this paper that support offloading simulation tasks across multiple GPUs over multiple hosts. With the redesigned architecture, Grid Topology for data splitting, optimized communication design and refined memory layout, the new version of MASS CUDA achieves significantly better performance and spatial scalability for large-scale ABM simulations when executed with multiple GPUs.

Naman Naswa

Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
2:30 P.M.; Join Naman Naswa’s online defense
Project: A Multimodal EEG – EMG Framework for Quantifying Parkinsonian Motor Patterns in Rehabilitation Oriented Tasks

Parkinson’s disease can affect how a person initiates, controls, and sustains movement during rehabilitation exercises, particularly through symptoms such as tremor, bradykinesia, and rigidity. This project develops a reproducible EEG – EMG pipeline for analyzing neural and muscle activity during rehabilitation oriented motor tasks. Data collection sessions were designed around structured Parkinson’s rehabilitation exercises and included rest, movement, and rest-to-action transition tasks performed by both healthy subjects and subjects with Parkinson’s disease.

足彩app哪个是正规的 pipeline synchronizes these EEG and EMG recordings with task timestamps, filters and removes ICA based EEG artifacts, segments the signals by exercise type, extracts motor relevant signal features, and uses these features to compare healthy and Parkinson’s subject groups. Symptom specific models are then used to generate three interpretable measures: a Tremor Index from rest segments, a Bradykinesia Index from movement tasks, and a Rigidity Proxy Index from transition windows. Among the various models used to compare the recordings, Logistic Regression performs the best based on balanced accuracy. Together, these indices provide a structured way to measure differences in motor patterns between subject groups, offering a foundation for objective, quantitative motor assessment in Parkinson’s rehabilitation research.

Tuesday, June 2

Meenal Shah

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Meenal Shah’s online defense
足彩app哪个是正规的sis: Design, Simulation, and Implementation of an Affordable Farm Maintenance Robot for Small- and Medium-Scale Farmers

Small and medium farms need timely field data—soil moisture, temperature, humidity, and early plant disease symptoms. Although autonomous agricultural robots exist, they are designed for large-scale operations and typically cost tens of thousands of dollars. This project presents the design, simulation, and implementation of a compact (25 cm × 25 cm) autonomous ground robot for crop monitoring and leaf disease detection, built for under $1,000. 足彩app哪个是正规的 robot follows a boustrophedon coverage pattern, samples environmental and soil parameters at fixed intervals, captures leaf images for on-device disease inference, avoids obstacles using IR sensing, and returns to a docking station to charge and upload data to a cloud-backed dashboard. Control is implemented as a finite state machine for predictability and low compute cost. Alongside the prototype, this work evaluates whether bio-inspired AI can support lightweight on-robot disease detection: three nature-inspired feature selectors and five classifiers spanning traditional CNNs and bio-inspired architectures were trained on a PlantVillage subset covering twelve diseases and three crops. LiteCShuffle achieved the highest accuracy (97.63%) at a model size under 2 MB, outperforming all bio-inspired alternatives tested. This suggests that the bio-inspired models evaluated—originally designed for non-agricultural perceptual tasks—do not transfer directly to leaf disease classification without further adaptation. 足彩app哪个是正规的 prototype demonstrates that meaningful autonomous crop monitoring is achievable at a price point compatible with small-farm budgets.

Patricija Cerkaite

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Patricija Cerkaite’s online defense
足彩app哪个是正规的sis: On-Device Web Accessibility: Latency and Quality Trade-offs in Browser-Based GIF Captioning

Animated GIFs (Graphics Interchange Format) are ubiquitous on the modern web, yet they are rarely described, leaving visually impaired users without context. While artificial intelligence (AI) can now automatically generate GIF captions, speed remains a limitation in web browsers.

This thesis rebuilds an existing GIF captioning approach by migrating AI inference from the cloud to the user’s device. 足彩app哪个是正规的 redesign reduces initial latency by 70\% and eliminates both API costs and privacy risks associated with transmitting data to external servers. We evaluated the system by benchmarking the quality and latency of three AI configurations for GIF captioning. 足彩app哪个是正规的 results show that backend choice and the input processing pipeline dominate page-to-accessible latency, whereas model architecture is the primary driver of caption accuracy. 足彩app哪个是正规的se outcomes validate the feasibility of developing localized, on-device browser accessibility tools.

Enbai Kuang

Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Enbai Kuang’s online defense
足彩app哪个是正规的sis: Application of Deep Learning for the Detection of Intracranial Hemorrhage Through Different Planes Using Ultrasound Imaging

Traumatic Brain Injury (TBI) is a significant medical condition that can result in long-term neurological impairment or life-threatening intracranial hemorrhage. While computed tomography (CT) and magnetic resonance imaging (MRI) are effective diagnostic tools, their high cost and lack of portability limit accessibility in certain scenarios such as rural and combat environments where rapid triage is essential. Tissue Pulsatility Imaging (TPI), an ultrasound-based technique developed at the University of Washington through Department of Defense funding, offers a potential alternative by enabling the collection of ultrasound data with a portable device. This method measures tissue displacement within the brain resulting from pulsatile blood flow. Previous work at the University of Washington utilized TPI displacement data and CT-derived masks as ground truth to train machine learning models for cranial feature and hemorrhage detection; however, blood segmentation remained challenging due to excessive noise and a limited sample size.

This thesis extends previous research by assessing whether blood-focused segmentation models trained on distinct participant subsets yield different detection outcomes. Eight blood-mode U-Net models were developed using participant groups categorized by scan orientation and blood-region location, with axial and coronal views further divided into top, bottom, left, and right regions. Each model was evaluated on its own held-out test set as well as on the test sets from the other seven groups, enabling comprehensive cross-test comparisons. Participant-level positivity was determined by thresholding predicted blood-mask pixels and applying a majority-vote analysis across models. Support Vector Machine (SVM) and k-Nearest Neighbors (KNN) baselines were also evaluated for comparison with previous results using the entire dataset.

足彩app哪个是正规的 U-Net models demonstrated limited performance in blood localization, with an average cross-test Dice coefficient of 0.101. Models trained on axial views achieved the highest segmentation accuracy and were the only ones to produce participant-level positive predictions. However, when applying a stricter majority-vote criterion that required at least half of the models to classify a result as positive, no test set met this threshold, as each received only three out of eight positive votes. 足彩app哪个是正规的 SVM and KNN baselines yielded substantially higher positive classification rates, but their results were heavily influenced by class imbalance and lacked spatial blood localization capability. Collectively, these findings indicate that TPI displacement data contain signals relevant to hemorrhage detection, yet reliable intracranial hemorrhage localization remains difficult due to limitations in sample size, diversity, and model architecture.

Shreevatsa Ganapathy Hegde

Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Shreevatsa Ganapathy Hegde’s online defense
Project: Tuning Metilda: Enhancing Web-Based Tools for Tonal Language Analysis

MeTILDA is a web-based platform for melodic transcription in language documentation and instructional workflows, with prior work establishing its core architecture, pitch-processing pipeline, and reproducibility goals. This report reports project-driven enhancements that improve reliability, maintainability, and usability of the current system for tonal and pitch-sensitive analysis tasks. 足彩app哪个是正规的 implementation prioritizes stakeholder-requested updates across key application areas, with emphasis on Pitch Art interaction behavior, playback semantics, comparative visualization controls, and stability of user-facing workflows. In parallel, the client architecture is refined to better separate interaction logic and presentation concerns, enabling safer iteration as new linguistic and pedagogical requirements emerge. Results are presented through stakeholder requirement completion with verification figures, Lighthouse accessibility audits on updated routes, and engineering checks after dependency upgrades. Together, these outcomes show improved stability in high-frequency Pitch Art and rhythm interactions while preserving MeTILDA’s web-accessible workflow. 足彩app哪个是正规的 combined findings indicate that the updated system reduces interaction friction in recurring analysis paths while preserving the web-accessible collaboration model that motivates MeTILDA. 足彩app哪个是正规的se outcomes position the platform for broader and more dependable use in language documentation and classroom-oriented pronunciation support, and they establish a practical foundation for future performance tuning, expanded evaluation, and continued feature evolution.

Wednesday, June 3

Kartikay Naswa

Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Kartikay Naswa’s online defense
Project: Multimodal EEG-EMG decoding for Neurorehabilitation 足彩app哪个是正规的rapy-Specific Upper Limb Motor Execution Exercises

Upper limb motor impairments arising from conditions such as stroke, peripheral nerve damage, and compressive neuropathies like carpal tunnel syndrome often require structured, repetitive fine-motor rehabilitation. Despite growing interest in neural and muscular signal monitoring for neurorehabilitation, tools for tracking neural and muscular engagement and benchmarks for classifying clinically prescribed movements rather than generic gestures remain scarce. This project investigates whether EEG, EMG, or their multimodal fusion can be reliably decoded for a structured set of rehabilitation-relevant upper limb exercises spanning wrist and finger movements, and rest and focuses on building a processing pipeline and automating multiple common steps for current and future experiments.

EEG and EMG signals were recorded from healthy subjects performing these exercises. A data collection tool called EEG Task Marker was developed to timestamp and cue subjects through exercises to enable more accurate EEG and EMG synchronization. In addition, a framework was devised to process collected signals in a modular, reusable pipeline covering automated data trimming, synchronization, preprocessing, and feature extraction designed to eliminate need for manual labelling and marking of tasks and support future experiments with different exercise sets. Preliminary results indicate that EMG can provide stronger discriminative signal across evaluation conditions, with muscular activation patterns stable enough to generalize for binary movement detection across our experimental sample. EEG captures cortical motor intent and contributes complementary neural information that muscular signals alone cannot provide alone. Multimodal EEG-EMG fusion improves robustness and classification accuracy. Cross subject, kinematically similar movements like finger actions remain the hardest to distinguish. 足彩app哪个是正规的se findings establish an initial benchmark for rehabilitation-specific motor decoding and demonstrate the potential of integrated bio-signal frameworks to support future adaptive, data-driven neurorehabilitation systems.

Jayalakshmi Sasidharan

Chair: Dr. Annuska Zolyomi
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Jayalakshmi Sasidharan’s online defense
Project: StoryPath: Designing a Human-Centered AI-Assisted Reminiscence 足彩app哪个是正规的rapy Platform for Dementia Care

Dementia affects 57 million individuals globally, with limited pharmaceutical treatments available. Reminiscence therapy, the intentional exploration of meaningful memories, is evidence-supported for improving mood, reducing agitation, and helping people maintain their sense of identity. However, traditional reminiscence therapy demands significant time and preparation. Caregivers must gather and organize photos, document the stories behind them, and guide meaningful conversations. Digital reminiscence therapy tools exist but often fall short in two ways: they lack grounding in established therapeutic principles, or they don’t adequately support the caregiver’s role in the process.

StoryPath was developed through a human-centered design approach that centers caregiver agency and therapeutic expertise. 足彩app哪个是正规的 system supports two interconnected experiences: one for people with dementia and their caregivers to explore memory albums together, and one for caregivers to actively shape the therapeutic experience by managing patient information, organizing memories, and reviewing engagement patterns. 足彩app哪个是正规的 system uses artificial intelligence to generate personalized prompts that invite storytelling and reflection. 足彩app哪个是正规的se prompts are designed around validation therapy principles, meaning they focus on sensory details, avoid testing memory, and affirm emotional truth rather than factual accuracy. Importantly, caregivers maintain control throughout. 足彩app哪个是正规的y can review every AI-generated prompt and edit it to better fit their loved one’s personality and history. This ensures the therapy remains deeply personal while reducing the preparation burden that traditionally falls on caregivers.

This project demonstrates how thoughtful design and artificial intelligence can make evidence-based therapy more accessible and less burdensome for families and caregivers. Findings will inform a larger research study and contribute to the growing field of human-AI collaboration in digital health interventions for older adults.

Thursday, June 4

Maria Ixchel Arias Cruz

Chair: Dr. Geethapriya Thamilarasu
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Discovery Hall (DISC) 464
Project: A Two-Level Firewall for Preventing Direct Prompt Injection and PII Exfiltration in Hybrid Mobile-Cloud Clinical RAG Systems

Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) are increasingly used in healthcare chatbots to provide evidence-based answers grounded in clinical documents, but this integration also exposes sensitive data to direct prompt-injection attacks that aim to exfiltrate data in hybrid mobile-cloud deployments. This capstone project addresses the lack of lightweight, deployment-ready defenses for such systems by designing and evaluating a two-level firewall for a hybrid mobile-cloud healthcare RAG chatbot. 足彩app哪个是正规的 architecture places a first-level input firewall on the mobile device to screen user queries and a second-level output firewall in the cloud to validate and sanitize model responses before they are returned to the phone, aligning security enforcement with mobile performance constraints. Using a synthetic healthcare knowledge base and a structured set of direct prompt-injection queries, the system is evaluated on PII and metadata leakage, a composite compound score that combines detection quality and latency, and standard classification metrics (accuracy, precision, recall, F1, and latency) relative to a baseline mobile RAG system without defenses. Results show that the proposed two-level firewall substantially reduces prompt-injection-driven leakage, with the on-device input firewall emerging as the main contributor and improving the compound score by up to 13% while preserving high accuracy and recall on benign clinical questions. At the same time, the on-device firewall introduces no significant performance overhead, maintaining interactive response times and modest CPU and memory usage on the mobile device.

Sonal Singh

Chair: Dr. Annuska Zolyomi
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Sonal Singh’s online defense
Project: SafeSpace AI: A Human-Centered Guardrailed Retrieval-Augmented Conversational System for Anxiety and Stress Support

SafeSpace AI is a human-centered, guardrailed conversational platform designed to provide accessible emotional support for individuals experiencing anxiety, stress, and emotional overwhelm. Existing mental wellness applications often rely on static self-help content, limited personalization, or costly professional support models that may not be readily accessible to students, young professionals, and underserved communities. Furthermore, many AI-powered conversational systems lack emotional safety mechanisms, contextual grounding, and responsible response generation, making them unsuitable for sensitive mental wellness interactions. Unlike conventional wellness applications, SafeSpace AI combines retrieval-augmented generation (RAG), prompt-orchestrated large language models, and multimodal calming interventions to create an empathetic, context-aware, and supportive user experience.

SafeSpace AI employs a retrieval-augmented architecture that grounds conversational responses in curated cognitive behavioral therapy (CBT)-inspired wellness resources, reducing hallucinations and improving contextual relevance during emotionally sensitive interactions. 足彩app哪个是正规的 system integrates guardrailed prompt orchestration, response structuring, and ethical conversational constraints to encourage supportive guidance rather than harmful dependency or unsafe advice generation. In addition, the platform incorporates multimodal wellness tools such as guided breathing exercises, calming sensory interactions, and curated soothing media experiences to provide users with real-time emotional regulation support beyond text-based conversation.

足彩app哪个是正规的 application further emphasizes accessibility, emotional safety, and human-centered design through a calming interface tailored to reduce cognitive overload and anxiety during use. By combining retrieval-augmented reasoning, conversational AI, multimodal interventions, and ethical guardrails, SafeSpace AI transforms digital mental wellness support from a passive chatbot interaction into an adaptive, supportive, and accessible emotional assistance platform.

Friday, June 5

Ethan Davis

Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Discovery Hall (DISC) 464
足彩app哪个是正规的sis: Benefits of Being Bayesian: Motor Imagery Electroencephalogram Classification

Brain-computer interfaces (BCI) based on electroencephalogram (EEG) pattern recognition have demonstrated clinical value in motor rehabilitation and neuroprosthetics, yet accurate classification of EEG signals remains challenging due to poor signal-to-noise ratio and intrinsic nonstationarity. Bayesian machine learning offers a principled framework for uncertainty quantification that may address these limitations, though prior comparisons with frequentist methods have been limited to informal evaluations on single datasets. This thesis presents a large-scale meta-analysis of Bayesian versus frequentist machine learning for motor imagery EEG classification across 20 benchmark datasets. Six top-performing frequentist pipelines spanning spatial filtering, Riemannian geometry, and deep learning approaches were benchmarked against pairwise Bayesian variants. Pooled effects were estimated using a three-level meta-analytic model accounting for heterogeneity both within and between datasets. Results yielded statistically significant improvements in calibration metrics — expected calibration error and maximum calibration error — for Bayesian models, while discrimination metrics including AUROC and MCC showed no significant difference. Computational cost analysis further suggests that Bayesian methods are economically viable for future BCI research. 足彩app哪个是正规的se findings motivate a hypothesis that the primary advantage of Bayesian learning lies in long-term adaptability through sequential model updating and transferability across subjects, with probabilistic resolution and reliability proposed as key indicators for sustaining high-performing BCI systems.

Ahmed Bera Pay

Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Commons Hall (UW2) 327
足彩app哪个是正规的sis: A Benchmark of C++ Cluster-Computing Libraries: MASS C++, HPX, and PM2

足彩app哪个是正规的 selection of a distributed C++ runtime for high-performance cluster applications entails significant performance and programmability trade-offs, yet existing evaluations of higher-level runtimes remain siloed within each runtime’s own application domain, precluding workload-diverse, controlled cross-runtime comparison. This thesis presents a benchmark suite of five computationally distinct patterns—a 3D stencil kernel (Heat3D), dense matrix multiplication (DGEMM), graph motif search, a phased financial graph simulation (Bail-In/Bail-Out), and an agent-based model (Reproductive SugarScape)—implemented equivalently across MASS C++, HPX, and PM2 from runtime-neutral algorithmic specifications. Runtime behavior is characterized along two dimensions: performance, measured through strong and weak scaling experiments, and programmability, assessed through a unified frame-work of quantitative and qualitative metrics. This work constitutes the first algorithmically equivalent cross-runtime characterization of MASS C++, HPX, and PM2, yielding empirically grounded, workload-specific guidance for distributed C++ runtime selection.

Qingran Shao

Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
5:45 P.M.; Join Qingran Shao’s online defense
足彩app哪个是正规的sis: A Multimodal Framework for Integrating EEG and Full-Body Motion Using Real-Time Pose Estimation

Electroencephalography (EEG) provides high temporal resolution for measuring brain activity and has long been a valuable tool for diagnosing and monitoring neurological conditions. However, interpreting EEG data can be challenging when it is used as the sole source of information. This is particularly challenging when studying general human body movement because of weak, noisy signals and strong dependency on the specific actions’ context. This project proposes a strategy to address this limitation, by developing a multimodal framework  that integrates EEG signals with real-time full-body 3D-pose representations, which can be used to map changes in body-movements to variations in EEG signals. 足彩app哪个是正规的 software developed to support this study, implements pipelines for data processing, visualizing, storing and maintaining input data and results through a basic Graphical User Interface. 足彩app哪个是正规的 EEG data is modeled using 336 engineered features, while the image data is represented through 99-dimensional landmark vectors derived from 33 body reference points. 足彩app哪个是正规的 resulting representations specific to each modality are temporally synchronized and indexed into a vectorized retrieval framework that facilitates similarity-based analysis and comparisons. To test the framework, we conduct multiple experiments where EEG and body-landmark data is collected before and after consistent exercise sessions, with the objective of identifying variation patterns in the EEG representations.  In addition, FFT-based spectral plots and event-clip embedding visualizations, illustrate how the software system can display channel-level EEG frequency changes and time-directed vector-database trajectories to help with data analysis and classification.  Preliminary results indicate that the use of the used features can be used for identifying changes in EEG signals. 足彩app哪个是正规的se findings suggest that body motion representation provides helpful behavioral context for EEG analysis based on a proof-of-concept study, which showed sensitivity to deviations from an individual’s baseline. Furthermore, the proposed system provides a framework for reproducible multimodal EEG-body-movement analysis, similarity-based retrieval, and also serves as a building block for future research involving EEG analysis.  

Master of Science in Cybersecurity Engineering

SPRING 2026

Tuesday, May 26

Suryanarayana Putrevu

Chair: Dr. Geethapriya Thamilarasu
Candidate: Master of Science in Cybersecurity Engineering
11:00 A.M.; Commons Hall (UW2) 327
Project: LLM-Based IoT Malware Detection via Similarity-Grounded Context

足彩app哪个是正规的 rapid growth of Internet-of-Things (IoT) devices has expanded the attack surface for network-based malware, creating demand for detection systems that are both accurate and interpretable. Machine learning classifiers achieve strong detection performance but provide limited insight into their decisions. Large Language Models (LLMs) offer structured reasoning capabilities, yet applying them directly to numeric network telemetry consistently fails — and the reasons for this failure have not been systematically studied.

This work introduces a reproducible, geometry-aware benchmark framework that investigates why LLMs succeed or fail at IoT malware detection, and presents the first LLM evaluation on the CIC IoT-DIAD 2024 dataset across both packet-level and flow-level traffic domains. Rather than treating Retrieval-Augmented Generation (RAG) as a performance tool, the framework identifies the class composition of the FAISS (Facebook AI Similarity Search) index — the pool of historical examples the LLM consults as the primary factor governing classification reliability. A controlled 2×2 experimental design isolates the effects of feature domain and class distribution independently, enabling clean attribution of performance changes to retrieval geometry rather than to model or prompt differences.

足彩app哪个是正规的 central finding is that retrieval geometry, not prompt design or model capability, governs classification reliability. When real-world traffic is heavily imbalanced, a standard FAISS index becomes geometrically corrupted, causing consistent misclassification — not because the LLM reasons poorly, but because the examples it retrieves are misleading. This work introduces NatBal (Natural-Balanced Index Conditioning), a correction that rebuilds the FAISS index from balanced training data regardless of test distribution, restoring reliable performance across all evaluation conditions without any model training or fine-tuning. 足彩app哪个是正规的 corrected framework approaches the detection performance of a fully supervised classifier while additionally producing human-readable, neighbor-grounded explanations of each decision.

足彩app哪个是正规的se results reframe LLM-based intrusion detection as a geometry-sensitive reasoning problem, and provide a fully reproducible reference benchmark for researchers evaluating LLM behavior in network security applications.

Wednesday, May 27

Harsh Makarand Jannawar

Chair: Dr. Min Chen
Candidate: Master of Science in Cybersecurity Engineering
9:30 A.M.; Join Harsh Makarand Jannawar’s online defense
足彩app哪个是正规的sis: AI Security Compliance and Testing Framework for Large Language Model Systems

Large Language Models are being integrated into enterprise workflows at a pace that has outrun the security frameworks designed to protect them. Conventional compliance standards such as SOC 2 and ISO 27001 provide no coverage for LLM-specific vulnerabilities including prompt injection, sensitive information disclosure, and system prompt leakage. 足彩app哪个是正规的 OWASP LLM Top 10 defines the relevant threat taxonomy, but no unified automated pipeline exists to translate those controls into repeatable, evidence-based test cases. This research investigates whether automated, systematically constructed adversarial testing can reliably surface exploitable vulnerabilities across LLM applications of varying hardness, and whether evolutionary attack strategies can reach attack surfaces that static prompt libraries cannot anticipate. To address these questions, this research employs a Design Science Research methodology. A 279-prompt library was constructed through three-source triangulation, drawing from CTF competition wins, industry AI red-teaming competition data, and peer-reviewed literature, grounding every technique in documented real-world effectiveness. Three target configurations were designed with isolated independent variables to evaluate detection rates across a baseline system, a hardened system, and a RAG-augmented system. An evolutionary attack engine implementing the SPE-NL genetic algorithm was developed and evaluated across all three configurations. Judge reliability and inter-rater agreement were validated through independent assessment by two practicing cybersecurity professionals.

Following this research design, AegisLLM was implemented as an automated security testing suite operationalizing six OWASP LLM Top 10 controls. Empirical evaluation demonstrates that targets resistant to the full static library fall to SPE-NL-evolved payloads within three to five generations, confirming that adaptive evolutionary testing reaches attack surfaces that curated static libraries cannot anticipate. 足彩app哪个是正规的 LLM-as-a-judge classification pipeline achieved 94.5% inter-rater agreement with zero crossover errors between SUCCESS and NO_SUCCESS labels. This thesis contributes to the field in three respects. First, it provides an empirically validated, open-source prompt library mapped explicitly to the OWASP LLM Top 10, sourced from ecologically valid real-world adversarial data. Second, it demonstrates the viability of evolutionary prompt mutation as a structured research method for LLM security evaluation, not merely as an engineering technique. Third, it establishes a replicable evaluation framework combining automated semantic judgment with human inter-rater validation, offering a methodological foundation for future LLM security research.

Saniya Bhaladhare

Chair: Dr. Min Chen
Candidate: Master of Science in Cybersecurity Engineering
11:00 A.M.; Join Saniya Bhaladhare’s online defense
足彩app哪个是正规的sis: AI Security Compliance and Risk Assessment Framework for Large Language Model Systems

足彩app哪个是正规的 rapid integration of Large Language Models into organizational workflows has outpaced the governance frameworks designed to oversee them. Standards such as NIST AI RMF 1.0 and ISO/IEC 42001 provides high-level principles for responsible AI, but lacks the operationalized, testable controls required for consistent compliance auditing of deployed LLM systems. This thesis designs, implements, and empirically evaluates an AI-powered compliance assessment framework that operationalizes these standards into a structured, interactive audit system.

足彩app哪个是正规的 framework is grounded in a Design Science Research methodology. Its core artifact is an AI audit agent backed by a 30-control library spanning six risk domains, a 0-to-5 maturity scoring model anchored to the NIST SP 800-53A evidence hierarchy, and a rule-based adaptive selection layer that tailors the control set to the deployment context without sacrificing reproducibility. A key research finding is that NIST AI RMF 1.0 contains no dedicated subcategories for three OWASP LLM Top 10 (2025) risk categories: System Prompt Leakage (LLM07), Vector and Embedding Weaknesses (LLM08), and Unbounded Consumption (LLM10). This thesis constructs three composite controls to close this gap, a finding independently corroborated by NIST AI 600-1 (July 2024).

足彩app哪个是正规的 agent is evaluated across three synthetic deployment scenarios representing low, moderate, and high organizational maturity, producing compliance scores of 23 percent, 33 percent, and 71 percent respectively. Two independent human assessors validated all 90 control assessments, producing an inter-assessor agreement rate of 72.2 percent and an LLM-to-human consensus agreement rate of 81.1 percent, confirming calibration within the expected range for AI-assisted assessment instruments.

This thesis contributes to the field in four respects. First, it provides the first operationalized, evidence-requesting 30-control compliance library that achieves full coverage of the OWASP LLM Top 10 (2025) with explicit standard citations to NIST AI RMF, ISO/IEC 42001, and ISO/IEC 27001. Second, it identifies and formally documents a structural gap in NIST AI RMF 1.0 through three composite controls whose necessity is corroborated by NIST AI 600-1. Third, it demonstrates a replicable adaptive selection architecture that separates deterministic compliance logic from LLM-assisted language generation. Fourth, it establishes a validated empirical baseline characterizing AI compliance tool calibration behavior across the full maturity range, with two specific calibration gaps confirmed by independent human assessors for future scoring model refinement.

Friday, May 29

Samarth Mahadev Devkar

Chair: Dr. Min Chen
Candidate: Master of Science in Cybersecurity Engineering
1:15 P.M.; Join Samarth Mahadev Devkar’s online defense
足彩app哪个是正规的sis: Adaptive AI-Driven Honeypot for Evolving Network Threats

Traditional SSH honeypots are effective for collecting brute-force attempts and post-login shell activity, but their research value is often limited by three connected challenges: restricted interaction realism, limited threat-intelligence extraction from attacker interactions and limited analyst-facing interpretation of captured data. Many conventional SSH honeypots rely on predefined filesystems, scripted command handlers, and static logging workflows. As a result, they may fail to sustain meaningful interaction when attackers issue commands outside the expected behavior of the decoy, and they often leave defenders with raw logs that require substantial manual analysis.

To address the above limitations, this thesis investigates how an SSH honeypot can be extended from a passive command-logging mechanism into an adaptive threat-intelligence workflow. 足彩app哪个是正规的 central contribution of this thesis is a research approach for connecting adaptive SSH interaction, structured behavioral interpretation, and analyst-facing visualization.

足彩app哪个是正规的 research contribution is threefold: a hybrid interaction approach for improving SSH honeypot interaction continuity, a novel enrichment layer for converting raw shell activity into structured threat intelligence, and an analyst-facing workflow for presenting enriched telemetry through live visualization. To validate the proposed approach, an AI-enhanced SSH honeypot was designed, implemented, and evaluated. 足彩app哪个是正规的 system maintains a controlled virtual shell environment, handles common commands through deterministic emulation, uses language-model assistance for selected fallback responses, and exposes enriched telemetry through a backend API and SOC-style dashboard. 足彩app哪个是正规的 dashboard supports live monitoring, severity triage, IOC inspection, and source-centric investigation.

足彩app哪个是正规的 evaluation includes a comparison with Cowrie in a conventional emulated-shell configuration and an assessment of the enrichment pipeline using a manually labeled evaluation set. 足彩app哪个是正规的 results show that the proposed system maintains interaction quality comparable to a mature SSH honeypot baseline while adding built-in intelligence enrichment and dashboard-based interpretation. 足彩app哪个是正规的 enrichment evaluation further shows that the system can produce useful behavior, risk, and IOC outputs for analyst-facing triage. Overall, this thesis contributes a research approach for combining adaptive SSH interaction, structured threat-intelligence enrichment, and live visualization into a single workflow for improving the practical value of honeypot telemetry.

Monday, June 1

Khang Tran

Chair: Dr. Geethapriya Thamilarasu
Candidate: Master of Science in Cybersecurity Engineering
1:15 P.M.; Discovery Hall (DISC) 464
Project: ZK-ARCHE: Zero-Knowledge Authentication for Resource-Constrained Heterogeneous Environment

IoT devices are becoming widely recognized as the cornerstones of distributed systems. However, limitations related to constrained computational capability, heterogeneity in architecture, and deployment in untrusted environments pose strong impediments to the secure authentication process. Password-based access and digital certificates are not applicable in such a setting owing to their reliance on user interaction, trusted key management, and high computational requirements. As a consequence of the growing interest in creating a lightweight, self-sufficient authentication schemes for the resources constraints IoT devices

足彩app哪个是正规的 work presents ZK-ARCHE, which is a zero-knowledge-based framework designed for use in heterogeneous systems with resource constraints. ZK-ARCHE makes use of Schnorr-like zero-knowledge proofs of Ristretto255 to allow devices to provide proof of holding credentials without compromising the secrets held. Mutual authentication, ephemeral Diffie-Hellman key agreement, key agreement through HKDF, transcript binding, replay attack resistance, and role- and attribute-based private mutual authentication have been supported by the ZK-ARCHE framework. 足彩app哪个是正规的 protocol was assessed under a client-server authentication scenario, with comparisons made with other schemes, including mTLS and EDHOC.

From the results obtained, ZK-ARCHE provides practical and secure mutual authentication and proof of possession even in resource-constrained platforms such as Raspberry Pi IoT. 足彩app哪个是正规的 work shows that zero-knowledge-based authentication can be a feasible approach for heterogeneous IoT systems characterized by credential protection and interoperability issues.

Wednesday, June 3

Shlok Amit Kshirsagar

Chair: Dr. Min Chen
Candidate: Master of Science in Cybersecurity Engineering
11:00 A.M.; Join Shlok Amit Kshirsagar’s online defense
足彩app哪个是正规的sis: Enhancing Web Application Security Through Active and Passive Reconnaissance Methods: A Comparative Framework Study Against Single-Method Approaches

Web application security assessment depends on effective reconnaissance to identify externally exposed assets, services, and vulnerabilities. Current reconnaissance practice relies on fragmented command-line tools that operate in isolation, produce unstructured outputs requiring substantial manual correlation, and apply context-independent vulnerability scoring that cannot reflect deployment-specific risk. 足彩app哪个是正规的 Common Vulnerability Scoring System provides no mechanism for automatically adjusting severity based on whether an affected service is internet-accessible or whether the host carries elevated asset value. 足彩app哪个是正规的se limitations reduce coverage, slow analyst workflows, and lead to systematic mis prioritization of remediation effort. This research investigates whether integrating passive and active reconnaissance within a unified pipeline, combined with cross-module analytical models, can produce security insights that isolated tools cannot generate, and whether a visualization-driven interface can deliver measurable workflow improvements over command-line operations.

Following a Design Science Research methodology, this thesis presents a three-module reconnaissance framework combining subdomain enumeration, port scanning, and vulnerability identification within a unified pipeline. Four original analytical algorithms are introduced: Shannon Entropy anomaly detection for identifying algorithmically generated subdomains, the Service Exposure Classification engine for quantifying port-level exposure risk, the Contextual Vulnerability Priority Score for context-aware vulnerability re-prioritization using cross-module deployment data, and the Attack Surface Risk Score for synthesizing a composite risk metric from all three scanning phases. Each algorithm is presented with theoretical justification, mathematical specification, and an explicit statement of originality. 足彩app哪个是正规的 framework is integrated with a graphical user interface providing single-action scan execution, real-time progress feedback, and structured result visualization.

Experimental evaluation demonstrates that the combined approach improves asset discovery coverage and reduces false negatives compared to passive-only methods, while the visualization-driven interface enhances analyst efficiency. Furthermore, the integration of context-aware models enables more precise vulnerability prioritization. Overall, this research presents a comprehensive and scalable solution that advances the effectiveness of web application reconnaissance.

This thesis contributes four original analytical algorithms that produce qualitatively new categories of security insight requiring data from all three scanning phases simultaneously, demonstrating that integrated, context-aware reconnaissance surfaces actionable findings that fragmented tools systematically miss.

Thursday, June 4

Yash Mahesh Malpathak

Chair: Dr. Min Chen
Candidate: Master of Science in Cybersecurity Engineering
1:15 P.M.; Join Yash Mahesh Malpathak’s online defense
足彩app哪个是正规的sis: Enhancing Technology Fingerprinting Through Human-Generated OSINT: A Comparative Study Against Tool-Only Reconnaissance

Technology fingerprinting, the identification of software frameworks, cloud platforms, programming languages, and infrastructure components used by an organization, is a foundational stage of cybersecurity reconnaissance. Automated scanning tools such as Nmap, WhatWeb, and Subfinder are widely used for this purpose. However, these tools share a structural limitation: they primarily detect technologies that produce externally observable signals at the network perimeter, while application-layer frameworks, backend infrastructure, and internal development tooling may remain invisible to tool-based reconnaissance.

This thesis investigates whether human-generated open-source intelligence (OSINT), specifically job postings, LinkedIn employee profiles, and GitHub public repositories, can serve as a complementary signal class for improving technology fingerprinting. An empirical study was conducted across twelve purposively selected organizations. Three integration methods were designed and evaluated: a union-based model for maximum recall, a source-strength weighted model using empirically derived reliability values, and a rule-based evidence-tier model requiring no manually assigned numeric scores.

Results show that the average Jaccard similarity between tool-detected and OSINT-detected technology sets is 0.005, with zero overlap in ten of twelve organizations. This confirms that the two signal classes are largely complementary rather than redundant. Human-generated OSINT contributed 857 organization-level detections absent from the tool-only baseline, representing an average coverage gain of 94.1%. 足彩app哪个是正规的 dominant OSINT-only categories were programming languages at 34.66% and application frameworks at 17.74%. All three integration methods produced substantially richer fingerprints than tool-only reconnaissance, with integration coverage gains ranging from 53.85% to 96.35%. Only five technologies across the full dataset achieved cross-source validation between tools and OSINT.

足彩app哪个是正规的se findings demonstrate that human-generated OSINT provides a quantifiably valuable complement to active scanning in technology fingerprinting workflows.

Kevin Lee

Chair: Dr. William Erdly
Candidate: Master of Science in Cybersecurity Engineering
3:30 P.M.; Discovery Hall (DISC) 464
Project: NIADS: A Non-Intrusive Anomaly Detection System for Detecting Account Misuse in Online Games Through Behavioral Analysis

Online game accounts accumulate significant monetary and competitive value, making them frequent targets for misuse. However, there is a lack of privacy-preserving systems for identifying users without sensitive information such as IP addresses or hardware details. Existing identification security measures rely on credential verification at login, and provide no additional mechanism for detecting a different person playing during an active session. Other anti-cheats, such as system-level monitoring software, partially address this gap but also introduce privacy concerns and require elevated system access. This project investigates whether behavioral gameplay data can serve as a reliable, privacy-preserving signal for continuous identity verification.

This project presents the NIADS, a behavioral biometric system that detects account misuse through gameplay data alone. NIADS collects mouse and keyboard dynamics, aiming patterns, reaction time, performance metrics, and user configuration settings from a custom-built data collection game. Using an Isolation Forest model trained on owner sessions, it constructs a behavioral profile and flags deviating sessions as anomalous.

足彩app哪个是正规的 model was trained on 98 owner sessions and evaluated against 133 other-participant sessions. Results exceeded the 80% accuracy threshold across all classification metrics, with strong precision and recall. 足彩app哪个是正规的 false positive rate narrowly missed the 5% target, due to natural behavioral variation across sessions. 足彩app哪个是正规的se results demonstrate that gameplay behavior is a viable, non-intrusive signal for continuous identity verification, with practical applications for game developers and platform operators seeking to enforce account integrity without invasive monitoring.

Master of Science in Electrical & Computer Engineering

SPRING 2026

Friday, May 8

Xiameng Zhang

Chair: Dr. Madhava Vemuri
Candidate: Master of Science in Electrical & Computer Engineering
10:00 A.M.; Discovery Hall (DISC) 464
足彩app哪个是正规的sis: A Study of Synchronous and Asynchronous Circuits in Monolithic 3D Integration

Monolithic three-dimensional integration (M3D) has emerged as a promising pathway for extending integrated-circuit scalability beyond conventional two-dimensional (2D) technology. By sequentially stacking active device layers and connecting them through fine-grained metal interlayer vias (MIVs), M3D can improve device density, reduce interconnect length, and enhance energy efficiency. This thesis investigates M3D from both application-driven and layout-methodology perspectives.

While M3D offers density and interconnect benefits, its sequential fabrication and vertical stacking introduce reliability concerns related to process variation, thermal effects, and timing uncertainty. To address these challenges, we first studied the quasi delay insensitive asynchronous circuits based on Null Conventional Logic (NCL). 足彩app哪个是正规的 asynchronous circuits address these challenges by eliminating the global clock and using local handshaking, making them robust to timing variations. To explore the complementary benefits of M3D and QDI design, this work proposes a transistor-level M3D methodology for static NCL threshold gates. Results show that M3D-NCL substantially reduces area while improving delay and power over 2D implementations.

足彩app哪个是正规的 second part studies the MIV placement opportunities and design consideration which affect the area, delay, skew, and power of M3D standard-cell designs. A methodology is proposed to study and compare conventional 2D and M3D standard cells in terms of power, performance, and area (PPA). Using this methodology, standard cells are implemented in both 2D and M3D, with different MIV placement strategies considered for the M3D case. Results show that the proposed designs achieve large area reduction with favorable delay, skew, and power trends.