Thesis/Project Final Defense Schedule
Join us as the School of STEM master’s degree candidates present their culminating thesis and project work. The 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
SUMMER 2025
Wednesday, June 25
ARJUN TANEJA
Chair: Dr. Michael Stiber
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Arjun Taneja’s Online Defense
Project: Spatiotemporal Analysis of Neuronal Avalanches in Self-Organized Criticality
Neural spike activity forms the fundamental basis of information processing and communication in the brain, exhibiting complex spatiotemporal dynamics. Recent advances in computational neuroscience have enabled high-resolution numerical simulations of large-scale neural networks, generating spike-time and location data that capture emergent phenomena such as neuronal avalanches and whole-network bursting. In the case of neuronal avalanches, prior analysis has almost exclusively focused on temporal information, ignoring the spatial information associated with spike data. This project presents an efficient algorithm that incorporates both spatial and temporal constraints for avalanche classification, moving beyond conventional spike-train analyses. Through systematic comparison of temporal-only and spatiotemporal methods, we investigate how the inclusion of spatial information affects avalanche identification and characterization. Finally, we examine how varying spatiotemporal constraints influence the detection and properties of whole-network bursting events, providing insight into the large-scale organization of neural activity.
Thursday, August 7
PANKTI BHASKAR SHAH
Chair: Professor Mark Kochanski
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Pankti Bhaskar Shah’s Online Defense
Project: Design and Implementation of a Unified Appointment Scheduling System for Canvas LMS
This project explores how instructor-student appointment scheduling can be integrated into a university’s Learning Management System (LMS), specifically Canvas, while enabling synchronization with external calendars such as Google and Outlook. Although Canvas centralizes academic workflows, it lacks built-in support for course-aware, role-sensitive scheduling. As a result, instructors rely on disjoint third-party tools that lack integration with course data and often lead to scheduling conflicts and increased administrative burden. This project implements a unified scheduling system that uses OAuth authentication, Canvas API integration and supports external calendar providers for event synchronization. Users can create and manage availability programs, manage appointments, and seamlessly sync events across their preferred calendars. The system was developed using agile practices, offering practical experience in scalable software design, modular architecture, and API integration. This solution addresses a clear gap in academic infrastructure and offers a scalable approach for improved user-experience and efficient scheduling for students, instructors, and administrators.
Friday, August 8
AATMAN RAJESHKUMAR PRAJAPATI
Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Aatman Rajeshkumar Prajapati’s Online Defense
Project: An Enhancement of Distributed Graph Queries in an Agent-Based Graph Database
Graph databases are increasingly employed in domains that demand efficient data-modelling and querying of highly interconnected data. This project enhances an agent-based graph database system built on the MASS (Multi-Agent Spatial Simulation) Java library, which adopts the property graph model to support dynamic schemas and rich relationship semantics in distributed environments. Unlike traditional graph systems, this implementation leverages autonomous agents to navigate and manipulate in-memory data across multiple computing nodes, enabling scalable and parallel graph operations.
This work focuses on extending the system’s query capabilities by integrating support for the Cypher WHERE clause, a critical feature for filtering and refining data retrieval. A modular approach was adopted to implement this functionality—beginning with an abstract syntax tree (AST) for parsing, followed by a dynamic evaluation mechanism for efficient constraint resolution. The enhancements improve the expressiveness and performance of read operations, while preserving the system’s core agent-based execution model. This development not only broadens the practical utility of the system but also establishes a foundation for future support of more complex query patterns and mutation operations.
Monday, August 11
RAVITEJA TANIKELLA
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Raviteja Tanikella’s Online Defense
Thesis: Emotionally Intelligent Voice Language Models For Mental Health Therapy
Conversational assistants for mental health therapy primarily rely on text-based models or cascaded architectures that first transcribe speech to text, a process that discards crucial paralinguistic information. This information bottleneck limits the AI’s ability to perceive critical emotional cues and broader psychological states, hindering its capacity to reason over human voice and provide effective therapy. This thesis details the development of an emotionally intelligent voice language model designed to overcome these limitations. The process began with a systematic evaluation of heuristic-based approaches and end-to-end model architectures, where automated benchmarking and a double-blind human study confirmed that large audio language models provided the most effective foundation for voice understanding and reasoning. Building on these findings, we propose and implement policy optimization methods to fine-tune this base voice language model on therapy data. The resulting aligned model demonstrated improved performance in benchmark evaluations, exhibiting emotional intelligence and generating therapeutically relevant responses. By presenting a complete development framework, from architectural validation to targeted alignment, this research establishes a clear and proven roadmap for creating the next generation of efficient and adaptive voice language models for mental health therapy and multimodal conversational AI.
KAUSHIK REDDY MITTA
Chair: Dr. Marc Dupuis
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Kaushik Reddy Mitta’s Online Defense
Project: Demographic Disparities in Cybersecurity: Analyzing Victimization, Tool Adoption, and Awareness Across Ethnicity and Region
Cybersecurity disparities across different demographic groups and regions have become a growing concern, as certain populations face disproportionate risks in terms of cyber victimization, tool adoption, and security awareness. These disparities are often overlooked in conventional cybersecurity research, which tends to simplify the relationship between demographic factors and cyber preparedness. This study analyzes these disparities by examining how ethnicity and geographic region influence cybersecurity outcomes in the United States. Using survey data from 470 participants collected by Professor Marc Dupuis, the research employs comprehensive statistical methods including correlation analysis, ANOVA, Kruskal-Wallis tests, and logistic regression to explore patterns across ethnic groups and urban, suburban, and rural settings. The study focuses on four key areas: cyber victimization, cybersecurity tool adoption, cyber incident experiences, and levels of cybersecurity awareness. The findings reveal significant disparities that challenge conventional assumptions about cybersecurity preparedness and risk exposure, highlighting the complex interactions between technology adoption, socioeconomic factors, and the strategies of threat actors targeting specific groups. The study calls for culturally competent interventions to address the unique vulnerability profiles of different demographic groups.
MANPREET KAUR
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Manpreet Kaur’s Online Defense
Project: A Multimodal AI System for Mental Health Support Using Emotion Recognition
Emotion‑aware conversational agents have the potential to transform mental health support by providing accessible, empathetic and context‑aware interactions. This project enhances the iCare Carebot by expanding it beyond a text‑only interface to a multimodal system that integrates text, audio and visual cues to better infer and respond to user emotions. We develop dedicated pipelines for each modality and benchmark both unimodal and multimodal emotion‑recognition models, fusing their outputs through cutting‑edge foundation models. For visual emotion recognition, we evaluate several vision‑language models including Phi‑4, Qwen2.5‑VL‑7B and Qwen2.5‑Omni‑7B and find that Qwen2.5‑VL‑7B offers the best balance of accuracy and inference efficiency. Across multimodal tasks, instruction‑tuned models consistently outperform zero‑shot and supervised‑fine‑tuned baselines. The system’s performance is assessed via the Multimodal Language Analysis benchmark and complemented by a user survey, which indicates broad receptiveness to a multimodal chatbot provided privacy concerns are addressed. Comparative evaluation using the Multimodal Language Analysis benchmark reveals that, among these models, Phi-4-multimodal-instruct provides the most balanced and effective performance across tasks. This work delivers a complete end-to-end framework from emotion signal extraction to context-aware response generation and marks a significant step toward making iCare a more empathetic and emotionally perceptive mental health support tool.
Tuesday, August 12
SWANAND WAGH
Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Swanand Wagh’s Online Defense
Project: Designing a User-Centered Digital Experience for the Entomon Institute
In the digital era, a strong online presence is essential for educational institutions to effectively engage with their audiences. However, typical institute websites for Zoology often suffer from poor accessibility, suboptimal UI/UX design, excess resources cluttered altogether, and inadequate adaptability, hindering their effectiveness. This project asks: how can I design a digital platform that meaningfully enhances public interaction with zoology & entomology?
To answer this, I partnered with the Entomon Institute to develop a cutting-edge, user-centric web platform to address these issues. The envisioned website serves as a dynamic resource hub, offering personalized materials on zoology and entomology, facilitating collaboration among institutes and research labs, and managing events such as insect hunts and ant colony explorations. Key features include interactive blogs, streamlined event management & proper user & admin dashboards. By leveraging modern web technologies, the platform aims to enhance educational outreach for zoology & entomology, fostering an engaging community, and provide up-to-date information in an accessible and interactive format.
At its core, this project is about making an institutional website feel less like a brochure and more like a space people actually want to visit. The result is a fast, accessible, and visually engaging platform that finally brings the Entomon Institute into the modern digital era.
HARI PRIYA DHANASEKARAN
Chair: Dr. Michael Stiber
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Hari Priya Dhanasekaran’s Online Defense
Thesis: Understanding Burst Patterns Through Graph Neural Network Explainability in Simulated Neuronal Networks
Spontaneous bursting activity in neural networks represents a fundamental mode of information processing in the brain, yet the mechanisms triggering these synchronized events remain poorly understood. While graph-based representations of neural networks are established, discovering the specific connectivity and activity patterns that predict burst initiation remains a significant challenge. This work leverages graph neural networks (GNNs) to classify and explain burst initiation in simulated cortical networks generated by the Graphitti simulator, advancing beyond conventional spike-train analysis to incorporate the rich relational structure of neural connectivity. By representing neural populations as graphs where nodes encode individual neurons with their temporal firing statistics and edges capture the synaptic connections, this work naturally integrates both activity patterns and network architecture. However, accurate prediction alone provides limited scientific insight. To move beyond black-box classification, we applied GNNExplainer to identify the minimal neural connectivity patterns driving model predictions. This explainability analysis revealed which specific neurons and synaptic connections the model deemed most critical for each prediction. This work demonstrates how explainable AI can transform our understanding of complex neural dynamics, providing insights that pure predictive modeling cannot offer. By combining the representation power of graph neural networks with explainability techniques, we bridge the gap between prediction and understanding. Our findings challenge prevailing views of burst initiation as a localized phenomenon, instead revealing the role of distributed precursor patterns in driving network-wide synchronization. This methodology opens new avenues for investigating emergent behaviors in complex networks.
VICTOR LONG
Chair: Dr. David Socha
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Victor Long’s Online Defense
Project: Building Continuous Integration Tools for Luna mHealth
The Luna mHealth group is a graduate research group building a medical education application for use in low-connectivity areas of the world. Developing good quality code in a larger code base with other developers is a difficult and complex task. Industry professionals turn towards toolsets and processes, like continuous integration, to provide a robust framework for teams to develop quality code. This project implements a continuous integration and continuous delivery toolset to automate a variety of quality gates that help propel Luna developers toward best practices in every part of the development cycle. By using automated testing and linting tools, developers’ code gets checked for testing issues and best-practice deviations before getting merged with the whole project. This project enhanced the student development experience and team consistency by providing a containerized environment. Such an environment allows students to develop on the same version of tools and dependencies. By developing with these continuous integration and continuous delivery tools, students are introduced to the tooling used in many industry settings and experience best practices for building good quality code, and the code quality has risen dramatically.
Friday, August 15
RUOXI SU
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Ruoxi Su’s Online Defense
Project: Emotion-Adaptive Retrieval-Augmented Chatbot: Elevating Mindfulness-Based Mental-Health Conversations with Lightweight LLM Reasoning
Large-language models (LLMs) have begun to transform mental-health support, yet most systems still ignore the user’s moment-to-moment affect. We present an emotion-adaptive retrieval-augmented generation (RAG) pipeline that grounds counseling responses in a curated mindfulness corpus while dynamically tailoring both retrieval and language style to the client’s emotional state. At each dialogue turn, a few-shot light-weighted LLM classifier assigns one of 13 clinically salient emotions and produces a ≤ 25-word situation summary; this lightweight front-end attains 83\% accuracy on a balanced 100-scenario test set. The two signals seed a MiniLM-L6 vector index built over 600-token chunks from 10 expert-reviewed articles, and the top-4 passages are merged with the chat history before generation. This design contracts the average context to $\sim 800$ tokens and trims retrieval latency to $\approx$ 1800 ms per turn while preserving semantic completeness.
We benchmark the system against an otherwise identical, emotion-agnostic RAG baseline. On a 100-dialogue test set, the emotion-aware front-end consistently improves quality over an otherwise identical RAG baseline. With GPT-4o-mini, human ratings rise for Empathy (+0.61 on a 0–4 scale; 2.35→2.96), Topical Relevance (+0.40 on 0–3; 1.98→2.38), and Helpfulness (+0.19 on 1–3; 2.07→2.26), while Safety is unchanged (2.70→2.73; 0/100 unsafe). With Llama-3 8B, gains are smaller but consistent—Empathy +0.06 (3.53→3.59), Relevance +0.17 (2.39→2.56), Helpfulness +0.22 (2.38→2.60)—with Safety stable at 2.95. The emotion classifier itself achieves Macro-F1 = 0.81 (AUROC ≈ 0.91) without fine-tuning. Together, these results indicate that a lightweight emotion-classification and situation-summary layer can sharpen topical fit and increase empathic/helpful tone without compromising safety.
SHRISTI SRIVASTAVA
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Shristi Srivastava’s Online Defense
Thesis: AutismCarebot: An Empathy-Enhanced and Retrieval-Augmented Chatbot for Autistic Users
Autism Spectrum Disorder (ASD) typically requires specialized communication strategies, tailored emotional understanding, and personalized resources – areas commonly overlooked by general mental health chatbots. This thesis introduces AutismCarebot, an empathy-enhanced, retrieval-augmented conversational AI built upon the LLaMA-3.2 (3B) Instruct model, designed explicitly for autistic users. Initially fine-tuned on empathetic dialogue datasets (Empathetic Dialogues, Amod Mental Health Counseling Conversations, Psych8k, ExTES), AutismCarebot was further specialized through fine-tuning on autism-specific data (TASD), enabling nuanced recognition and appropriate responses to autistic communication styles. The chatbot employs keyword-based heuristics to detect emotional cues such as anxiety, sadness, and overwhelm, responding with clear, empathetic validation and tailored reassurance. Retrieval-Augmented Generation (RAG) ensures accuracy by embedding evidence-based advice from credible autism-related resources, transparently cited within responses. Additionally, proactive crisis detection identifies self-harm indicators, immediately connecting users to global crisis support resources. Usability testing and qualitative feedback from autistic individuals, caregivers, and educators demonstrated favorable usability, enhanced empathy, emotional responsiveness, and increased user trust. AutismCarebot provides a replicable, ethical, and effective approach to enhancing emotional support and crisis safety for autistic users, highlighting its practical value in therapeutic, educational, and peer-support environments.
Tuesday, August 19
JANYA BYSANI
Chair: Dr. Geethapriya Thamilarasu
Candidate: Master of Science in Computer Science & Software Engineering
12:00 P.M.; Join Janya Bysani’s Online Defense
Project: Low-Latency Packet-Processing Pipeline for Anomaly Detection in IoMT Networks Using
The adoption of Internet-of-Medical-Things (IoMT) devices has turned IoMT networks into
dense, latency sensitive fabrics that relay vast quantities of protected health information. To
safeguard this traffic, this project develops an edge based intrusion prevention system that
combines a Data Plane Development Kit (DPDK) fast path with a machine learning inference
engine. Packets are captured in zero copy, kernel bypass mode and streamed through a
feature extraction stage before being classified by a LightGBM model that delivers sub-500
µs inference latency.
This pipeline further introduces a privacy preserving adaptation loop that uses federated
learning. Each gateway retrains the classifier on its local traffic and transmits the model to a
custom aggregator. The aggregator evaluates incoming models and selects the candidate
with the lowest loss as the new global model, which is then redistributed asynchronously.
This approach retains patient data locality, prevents raw packet exposure, and enables
continuous improvement of detection accuracy without disrupting clinical workflows.
Master of Science in Cybersecurity Engineering
SUMMER 2025
Thursday, August 14
BENARD BIRUNDU
Chair: Dr. Marc Dupuis
Candidate: Master of Science in Cybersecurity Engineering
11:00 A.M.; Join Benard Birundu’s Online Defense
Project: Exploring the Impact of Previous Experience and Threats Awareness on influencing Regular Information Backup Among University Students
Cybersecurity has gained momentum in the past decade as cyberthreats revolutionize the sophistication and deployment of artificial intelligence (AI) to launch cyberattacks. Technical solutions have been the first line of defense in cybersecurity for a while. But the focus has lately shifted to human security solutions as cyberattacks target individuals to achieve their goals. Moreover, humans are majorly considered as the weakest link in cybersecurity, which positions university students as most vulnerable due to their constant use of the internet. This study focused on exploring the impact of threat awareness and past experience on influencing information backup among university students in the USA. Protection Motivation Theory (PMT) was referenced, where a survey questionnaire was used to collect data from respondents. Correlation statistical analysis was deployed to conduct data analysis enabling correlation comparison between variables. The findings will be very instrumental in improving cybersecurity among students and the university computing environment.
Keywords: Cybersecurity, Protection Motivation Theory, threats awareness, past experience, information backup, university students,
Master of Science in Electrical & Computer Engineering
SUMMER 2025
Wednesday, August 13
SRIVAISHNAVI JAMALAPURAPU
Chair: Dr. Seungkeun Choi
Candidate: Master of Science in Electrical & Computer Engineering
8:45 A.M.; Discovery Hall Room 464
Thesis: Characterization of a Sneak Path Current Effect in a PEDOT: PSS-based ReRAM Crossbar Array
This thesis presents an experimental characterization of Cu/PEDOT: PSS/Ag crossbar ReRAM devices fabricated on glass substrates, with a particular focus on understanding the impact of sneak-path currents on the device performances. Resistive memory cells, particularly in crossbar configurations, are widely considered as promising memory technology due to their scalability, high density, non-volatility, and low power consumption. However, despite these advantages, they are prone to sneak-path currents—unintended leakage through unselected cells—which pose a significant challenge to performance and reliability in dense memory arrays.
In this work, we investigate how a ReRAM cell in a crossbar array responds to prolonged electrical stress by applying low-voltage cycling corresponding to a sneak-path conduction. The device has a PEDOT: PSS as a switching layer sandwiched between Cu bottom electrode and Ag top electrode. The width of the electrodes is 10 µm and the crossbar array space is 60 µm. This research elaborates how a resistive switching memory cell in a crossbar array degrades its performance under various biasing conditions.
Three categories of electrical testing were conducted. First, cycling measurements under repeated ±2 V sweeps were used to assess endurance until hysteresis degradation. Devices showed stable switching behavior for up to 121 cycles, with well-defined LRS, HRS, and consistent Vset, Vreset values before breakdown. Second, voltage sweep experiments were designed to compare switching behaviors during an initial ±2 V sweep versus a final ±2 V sweep, following intermediate low-voltage steps from ±0.5 V to ±1.9 V. The results demonstrated that cumulative sneak-path conduction led to subtle hysteresis collapse and reduced switching margins.
Finally, narrow-to-broad sweep testing evaluated whether limited low-voltage cycling could condition the device and influence future switching dynamics. Devices exposed only to narrow ranges remained non-switching, but subsequent full-range sweeps revealed altered I–V characteristics, confirming that sneak-path effects accumulate even in the absence of complete switching events.
Overall, the findings highlight that while selector-less resistive memory cells offer structural simplicity and potential scalability, their performance degrades under repeated low-voltage stress because of sneak-path current. This study provides experimental insights into how cumulative leakage conduction paths affect long-term device reliability, informing future strategies for robust ReRAM integration in compute-in-memory and neuromorphic architectures.