I2S Masters/ Doctoral Theses


All students and faculty are welcome to attend the final defense of I2S graduate students completing their M.S. or Ph.D. degrees. Defense notices for M.S./Ph.D. presentations for this year and several previous years are listed below in reverse chronological order.

Students who are nearing the completion of their M.S./Ph.D. research should schedule their final defenses through the EECS graduate office at least THREE WEEKS PRIOR to their presentation date so that there is time to complete the degree requirements check, and post the presentation announcement online.

Upcoming Defense Notices

Arya Hadizadeh Moghaddam

Learning Personalized and Robust Patient Representations across Complex Structures in Electronic Health Records

When & Where:


Eaton Hall, Room 2001B

Degree Type:

PhD Dissertation Defense

Committee Members:

Zijun Yao, Chair
Fengjun Li
Bo Luo
Han Wang
Xinmai Yang

Abstract

Electronic health records (EHRs) contain medical codes and clinical notes collected over multiple visits. This dissertation studies how to learn patient representations from these records through three related aspects problems:

The first aspect concerns relationships within a patient’s history. TPGT models changing dependencies among medical codes within and across visits, and ARCI separates temporal patterns associated with different medical intents. They account for interacting clinical events and concurrent treatment goals.

When patient histories are limited, these patterns are harder to learn. The second aspect is addressed by MetaDrug, which adapts to patients with sparse histories using their own records and those of similar patients, while filtering uncertain samples.

The third aspect concerns incorporating clinical notes and large language models into patient representations. RePrompT uses cohort-trained representations and recurrent soft prompts to preserve longitudinal context. RASPER trains a note summarizer through downstream prediction feedback. CERE reasons over notes conditioned on structured codes to represent the additional evidence they provide. These studies connect structured histories with clinical text to support prediction.

Experiments on the KUMC acute kidney injury cohort, eICU, MIMIC-III, and MIMIC-IV show improvements over the respective baselines in clinical prediction and medication recommendation.


Shelby Jones

Measuring LLM Susceptibility to Stylistic Perturbations in Social Media Text

When & Where:


Nichols Hall, Room 246 (Executive Conference Room)

Degree Type:

MS Thesis Defense

Committee Members:

Jennifer Lohoefener, Chair
Perry Alexander
John Symons


Abstract

Large Language Models (LLMs) are becoming increasingly integrated into important domains such as social media and politics. This makes it essential that we understand their susceptibility to superficial text variations. In this thesis, I investigated whether small stylistic perturbations in social media posts influence how an LLM perceives a post's political leanings. To do this, I systematically manipulated punctuation and capitalization across both political and apolitical social media posts. I then used VADER sentiment analysis to measure the changes in semantic intensity to quantify the text manipulation. Finally, I prompted each LLM to provide its perceived political leanings of each given post. I used linear regression to assess the VADER score correlation with the LLMs' political alignment ratings. While there was no statistically significant relation between perceived political extremity and VADER scores, category-level analysis revealed that the stylistic perturbations cause significant inconsistencies in model outputs. Furthermore, in posts with neutral semantic content, the stylistic perturbations introduce a right-leaning bias. These findings add to the growing body of literature on LLM instability under prompt perturbation and highlight risks associated with automated content analysis. 


Connor Sullivan

Memory QoS Mechanisms for Predictable and Performant Real-Time Systems

When & Where:


Eaton Hall, Room 2001B

Degree Type:

PhD Comprehensive Defense

Committee Members:

Heechul Yun, Chair
Zitao Chen
Tamzidul Hoque
Prasad Kulkarni
Kenneth Fischer

Abstract

Commercial-off-the-shelf (COTS) multicore processors are increasingly used in safety-critical real-time systems due to their higher performance and improved size, weight, and power (SWaP) characteristics. However, modern platforms are designed for average-case performance, which works in direct opposition to the worst-case timing guarantees required by safety-critical systems.

In particular, unregulated sharing of the memory hierarchy across cores can cause severe and unpredictable interference. When multiple cores concurrently access shared memory resources, their requests contend with one another, degrading application performance and undermining timing guarantees. Hardware quality-of-service (QoS) mechanisms aim to manage this contention. Partitioning these resources in space alone does not guarantee temporal isolation. Bandwidth regulation can protect latency-critical tasks from such interference, but it trades system throughput for isolation. Current solutions throttle co-running tasks far more than necessary, offering system designers a poor isolation-throughput tradeoff.

Addressing this challenge, this thesis focuses on QoS mechanisms that improve the balance between throughput and isolation. Shared memory resources such as the last-level cache (LLC) and main memory (DRAM) have parallel, banked structures, yet existing regulation treats them as monolithic. This thesis shows that contention in both arises at the bank level and proposes per-bank bandwidth regulation for the LLC and DRAM, which preserves isolation for latency-critical tasks while recovering throughput for best-effort tasks. Finally, the thesis aims to coordinate regulation across the levels of the memory hierarchy, adapting it dynamically at runtime. It will also explore matching the control mechanism to the root cause of contention, for example by controlling the number of outstanding requests, as an alternative or cooperative means to bandwidth regulation. Together, these efforts work toward a better balance between system throughput and isolation guarantees in multicore real-time systems.


Fairuz Shadmani Shishir

Efficient and Privacy-Preserving Biomedical AI: From Precision Therapeutics Design to Private Clinical Prediction

When & Where:


Eaton Hall, Room 2001B

Degree Type:

PhD Dissertation Defense

Committee Members:

Sumaiya Shomaji, Chair
Tamzidul Hoque
Cuncong Zhong
Bishnu Sarker
Michael Hageman

Abstract

Accurate protein characterization, precision therapeutics design, and privacy-preserving clinical modeling are important challenges in biomedical artificial intelligence (AI). Addressing these challenges requires computational frameworks that are not only accurate and scalable but also capable of supporting reliable decision-making. This dissertation develops efficient, scalable, and reliable computational frameworks across three areas: Computational characterization of proteins, precision therapeutics design, and privacy-aware clinical representation learning. The first part of this dissertation focuses on efficient protein characterization at both the sequence and residue levels. GPCR-SLM, a knowledge-distilled small protein language model, classifies G-protein-coupled receptors (GPCRs), a family targeted by approximately 35% of FDA-approved drugs. Across 86 families, GPCR-SLM achieves 99% accuracy, outperforming BLAST (86.4%) and HMMER (91%), with a 33.5-fold speedup over large protein language models. Extending characterization to the residue level, a protein-metal-ion binding site prediction framework evaluates five protein language models and incorporates positional encoding to capture long-range dependencies. Under 10-fold cross-validation, it achieves a Matthews correlation coefficient of 0.89, with precision, recall, and F1 scores exceeding 95% across six metal ions.

Building on these protein characterization methods, the second part advances precision therapeutics design through uncertainty quantification and generative learning for therapeutic antibodies. NbBayesLM combines protein language model embeddings and physicochemical descriptors in a Bayesian neural network to predict nanobody thermostability. Evaluated on 10,630 VHH sequences, it achieves a mean absolute error of 1.89C and an R2 of 0.67 while estimating epistemic and aleatoric uncertainty to support candidate prioritization. CIgFlow employs classifier-free guidance to generate de novo, antigen-conditioned antibody sequences without fixed scaffolds or paired structural data. Generated sequences achieve a median OASis humanness score of 0.90 and mean predicted local distance difference test (pLDDT) score of 85.0, demonstrating promising novelty and diversity. The third part addresses privacy-aware clinical modeling using electrocardiograms (ECGs), which encode diagnostic information and sensitive demographic attributes. A variational autoencoder with dual discriminators suppresses demographic information while preserving clinically relevant representations.

Collectively, this dissertation advances efficient protein representation learning, computational antibody design, and privacy-preserving clinical AI, contributing methodological foundations for trustworthy biomedical applications.


Past Defense Notices

Dates

Yoganand Pitta

Insightful Visualization: An Interactive Dashboard Uncovering Disease Patterns in Patient Healthcare Data

When & Where:


Eaton Hall, Room 2001B

Degree Type:

MS Project Defense

Committee Members:

Zijun Yao, Chair
Prasad Kulkarni
Hongyang Sun


Abstract

As Electronic Health Records (EHRs) become more available, there is increasing interest in discovering hidden disease patterns by leveraging cutting-edge data visualization techniques, such as graph-based knowledge representation and interactive graphical user interfaces (GUIs). In this project, we have developed a web-based interactive EHR analytics and visualization tool to provide healthcare professionals with valuable insights that can ultimately improve the quality and cost-efficiency of patient care. Specifically, we have developed two visualization panels: one for the intelligence of individual patients and the other for the relevance among diseases. For individual patients, we capture the similarity between them by linking them based on their relatedness in diagnosis. By constructing a graph representation of patients based on this similarity, we can identify patterns and trends in patient data that may not be apparent through traditional methods. For disease relationships, we provide an ontology graph for the specific diagnosis (ICD10 code), which helps to identify ancestors and predecessors of a particular diagnosis. Through the demonstration of this dashboard, we show that this approach can provide valuable insights to better understand patient outcomes with an informative and user-friendly web interface.


Michael Cooley

Machine Learning for Navel Discharge Review

When & Where:


Eaton Hall, Room 1

Degree Type:

MS Project Defense

Committee Members:

Prasad Kulkarni, Chair
David Johnson
Jerzy Grzymala-Busse


Abstract

This research project aims to predict the outcome of the Naval Discharge Review Board decision for an applicant based on factors in the application, using Machine Learning techniques. The study explores three popular machine learning algorithms: MLP, Adaboost, and KNN, with KNN providing the best results. The training is verified through hyperparameter optimization and cross fold validation.

Additionally, the study investigates the ability of ChatGPT's API to classify the data that couldn't be classified manually. A total of over 8000 samples were classified by ChatGPT's API, and an MLP model was trained using the same hyperparameters that were found to be optimal for the 3000 size manual sample.The model was then tested on the manual sample. The results show that the model trained on data labeled by ChatGPT performed equivalently, suggesting that ChatGPT's API is a promising tool for labeling in this domain.


Sarah Johnson

Formal Analysis of TPM Key Certification Protocols

When & Where:


Nichols Hall, Room 246

Degree Type:

MS Thesis Defense

Committee Members:

Perry Alexander, Chair
Michael Branicky
Emily Witt


Abstract

Development and deployment of trusted systems often require definitive identification of devices. A remote entity should have confidence that a device is as it claims to be. An ideal method for fulfulling this need is through the use of secure device identitifiers. A secure device identifier (DevID) is defined as an identifier that is cryptographically bound to a device. A DevID must not be transferable from one device to another as that would allow distinct devices to be identified as the same. Since the Trusted Platform Module (TPM) is a secure Root of Trust for Storage, it provides the necessary protections for storing these identifiers. Consequently, the Trusted Computing Group (TCG) recommends the use of TPM keys for DevIDs. The TCG's specification TPM 2.0 Keys for Device Identity and Attestation describes several methods for remotely proving a key to be resident in a specific device's TPM. These methods are carefully constructed protocols which are intended to be performed by a trusted Certificate Authority (CA) in communication with a certificate-requesting device. DevID certificates produced by an OEM's CA at device manufacturing time may be used to provide definitive evidence to a remote entity that a key belongs to a specific device. Whereas DevID certificates produced by an Owner/Administrator's CA require a chain of certificates in order to verify a chain of trust to an OEM-provided root certificate. This distinction is due to the differences in the respective protocols prescribed by the TCG's specification. We aim to abstractly model these protocols and formally verify that their resulting assurances on TPM-residency do in fact hold. We choose this goal since the TCG themselves do not provide any proofs or clear justifications for how the protocols might provide these assurances. The resulting TPM-command library and execution relation modeled in Coq may easily be expanded upon to become useful in verifying a wide range of properties regarding DevIDs and TPMs.


Anna Fritz

Negotiating Remote Attestation Protocols

When & Where:


Nichols Hall, Room 246

Degree Type:

PhD Comprehensive Defense

Committee Members:

Perry Alexander, Chair
Alex Bardas
Drew Davidson
Fengjun Li
Emily Witt

Abstract

During remote attestation, a relying party prompts a target to perform some stateful measurement which can be appraised to determine trust in the target's system. In this current framework, requested measurement operations must be provisioned by a knowledgeable system user who may fail to consider situational demands which potentially impact the desired measurement. To solve this problem, we introduce negotiation: a framework that allows the target and relying party to mutually determine an attestation protocol that satisfies both the target's need to protect sensitive information and the relying party's desire for a comprehensive measurement. We designed and verified this negotiation procedure such that for all negotiations, we can provably produce an executable protocol that satisfies the targets privacy standards. With the remainder of this work, we aim to realize and instantiate protocol orderings ensuring negotiation produces a protocol sufficient for the relying party. All progress is towards our ultimate goal of producing a working, fully verified negotiation scheme which will be integrated into our current attestation framework for flexible, end-to-end attestations.