Defense Notices
All students and faculty are welcome to attend the final defense of EECS 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
Masoud Ghazikor
Distributed Optimization and Control Algorithms for UAV Networks in Unlicensed Spectrum BandsWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
Morteza Hashemi, ChairVictor Frost
Prasad Kulkarni
Abstract
UAVs have emerged as a transformative technology for various applications, including emergency services, delivery, and video streaming. Among these, video streaming services in areas with limited physical infrastructure, such as disaster-affected areas, play a crucial role in public safety. UAVs can be rapidly deployed in search and rescue operations to efficiently cover large areas and provide live video feeds, enabling quick decision-making and resource allocation strategies. However, ensuring reliable and robust UAV communication in such scenarios is challenging, particularly in unlicensed spectrum bands, where interference from other nodes is a significant concern. To address this issue, developing a distributed transmission control and video streaming is essential to maintaining a high quality of service, especially for UAV networks that rely on delay-sensitive data.
In this MSc thesis, we study the problem of distributed transmission control and video streaming optimization for UAVs operating in unlicensed spectrum bands. We develop a cross-layer framework that jointly considers three inter-dependent factors: (i) in-band interference introduced by ground-aerial nodes at the physical layer, (ii) limited-size queues with delay-constrained packet arrival at the MAC layer, and (iii) video encoding rate at the application layer. This framework is designed to optimize the average throughput and PSNR by adjusting fading thresholds and video encoding rates for an integrated aerial-ground network in unlicensed spectrum bands. Using consensus-based distributed algorithm and coordinate descent optimization, we develop two algorithms: (i) Distributed Transmission Control (DTC) that dynamically adjusts fading thresholds to maximize the average throughput by mitigating trade-offs between low-SINR transmission errors and queue packet losses, and (ii) Joint Distributed Video Transmission and Encoder Control (JDVT-EC) that optimally balances packet loss probabilities and video distortions by jointly adjusting fading thresholds and video encoding rates. Through extensive numerical analysis, we demonstrate the efficacy of the proposed algorithms under various scenarios.
Ganesh Nurukurti
Customer Behavior Analytics and Recommendation System for E-CommerceWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairPrasad Kulkarni
Han Wang
Abstract
In the era of digital commerce, personalized recommendations are pivotal for enhancing user experience and boosting engagement. This project presents a comprehensive recommendation system integrated into an e-commerce web application, designed using Flask and powered by collaborative filtering via Singular Value Decomposition (SVD). The system intelligently predicts and personalizes product suggestions for users based on implicit feedback such as purchases, cart additions, and search behavior.
The foundation of the recommendation engine is built on user-item interaction data, derived from the Brazilian e-commerce Olist dataset. Ratings are simulated using weighted scores for purchases and cart additions, reflecting varying degrees of user intent. These interactions are transformed into a user-product matrix and decomposed using SVD, yielding latent user and product features. The model leverages these latent factors to predict user interest in unseen products, enabling precise and scalable recommendation generation.
To further enhance personalization, the system incorporates real-time user activity. Recent search history is stored in an SQLite database and used to prioritize recommendations that align with the user’s current interests. A diversity constraint is also applied to avoid redundancy, limiting the number of recommended products per category.
The web application supports robust user authentication, product exploration by category, cart management, and checkout simulations. It features a visually driven interface with dynamic visualizations for product insights and user interactions. The home page adapts to individual preferences, showing tailored product recommendations and enabling users to explore categories and details.
In summary, this project demonstrates the practical implementation of a hybrid recommendation strategy combining matrix factorization with contextual user behavior. It showcases the importance of latent factor modeling, data preprocessing, and user-centric design in delivering an intelligent retail experience.
Srijanya Chetikaneni
Plant Disease Prediction Using Transfer LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairPrasad Kulkarni
Han Wang
Abstract
Timely detection of plant diseases is critical to safeguarding crop yields and ensuring global food security. This project presents a deep learning-based image classification system to identify plant diseases using the publicly available PlantVillage dataset. The core objective was to evaluate and compare the performance of a custom-built Convolutional Neural Network (CNN) with two widely used transfer learning models—EfficientNetB0 and MobileNetV3Small.
All models were trained on augmented image data resized to 224×224 pixels, with preprocessing tailored to each architecture. The custom CNN used simple normalization, whereas EfficientNetB0 and MobileNetV3Small utilized their respective pre-processing methods to standardize the pretrained ImageNet domain inputs. To improve robustness, the training pipeline included data augmentation, class weighting, and early stopping.
Training was conducted using the Adam optimizer and categorical cross-entropy loss over 30 epochs, with performance assessed using accuracy, loss, and training time metrics. The results revealed that transfer learning models significantly outperformed the custom CNN. EfficientNetB0 achieved the highest accuracy, making it ideal for high-precision applications, while MobileNetV3Small offered a favorable balance between speed and accuracy, making it suitable for lightweight, real-time inference on edge devices.
This study validates the effectiveness of transfer learning for plant disease detection tasks and emphasizes the importance of model-specific preprocessing and training strategies. It provides a foundation for deploying intelligent plant health monitoring systems in practical agricultural environments.
Ahmet Soyyigit
Anytime Computing Techniques for LiDAR-based Perception In Cyber-Physical SystemsWhen & Where:
Nichols Hall, Room 250 (Gemini Room)
Committee Members:
Heechul Yun, ChairMichael Branicky
Prasad Kulkarni
Hongyang Sun
Shawn Keshmiri
Abstract
The pursuit of autonomy in cyber-physical systems (CPS) presents a challenging task of real-time interaction with the physical world, prompting extensive research in this domain. Recent advances in artificial intelligence (AI), particularly the introduction of deep neural networks (DNN), have significantly improved the autonomy of CPS, notably by boosting perception capabilities.
CPS perception aims to discern, classify, and track objects of interest in the operational environment, a task that is considerably challenging for computers in a three-dimensional (3D) space. For this task, the use of LiDAR sensors and processing their readings with DNNs has become popular because of their excellent performance However, in CPS such as self-driving cars and drones, object detection must be not only accurate but also timely, posing a challenge due to the high computational demand of LiDAR object detection DNNs. Satisfying this demand is particularly challenging for on-board computational platforms due to size, weight, and power constraints. Therefore, a trade-off between accuracy and latency must be made to ensure that both requirements are satisfied. Importantly, the required trade-off is operational environment dependent and should be weighted more on accuracy or latency dynamically at runtime. However, LiDAR object detection DNNs cannot dynamically reduce their execution time by compromising accuracy (i.e. anytime computing). Prior research aimed at anytime computing for object detection DNNs using camera images is not applicable to LiDAR-based detection due to architectural differences. This thesis addresses these challenges by proposing three novel techniques: Anytime-LiDAR, which enables early termination with reasonable accuracy; VALO (Versatile Anytime LiDAR Object Detection), which implements deadline-aware input data scheduling; and MURAL (Multi-Resolution Anytime Framework for LiDAR Object Detection), which introduces dynamic resolution scaling. Together, these innovations enable LiDAR-based object detection DNNs to make effective trade-offs between latency and accuracy under varying operational conditions, advancing the practical deployment of LiDAR object detection DNNs.
Rahul Purswani
Finetuning Llama on custom data for QA tasksWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairDrew Davidson
Prasad Kulkarni
Abstract
Fine-tuning large language models (LLMs) for domain-specific use cases, such as question answering, offers valuable insights into how their performance can be tailored to specialized information needs. In this project, we focused on the University of Kansas (KU) as our target domain. We began by scraping structured and unstructured content from official KU webpages, covering a wide array of student-facing topics including campus resources, academic policies, and support services. From this content, we generated a diverse set of question-answer pairs to form a high-quality training dataset. LLaMA 3.2 was then fine-tuned on this dataset to improve its ability to answer KU-specific queries with greater relevance and accuracy. Our evaluation revealed mixed results—while the fine-tuned model outperformed the base model on most domain-specific questions, the original model still had an edge in handling ambiguous or out-of-scope prompts. These findings highlight the strengths and limitations of domain-specific fine-tuning, and provide practical takeaways for customizing LLMs for real-world QA applications.
Rithvij Pasupuleti
A Machine Learning Framework for Identifying Bioinformatics Tools and Database Names in Scientific LiteratureWhen & Where:
LEEP2, Room 2133
Committee Members:
Cuncong Zhong, ChairDongjie Wang
Han Wang
Zijun Yao
Abstract
The absence of a single, comprehensive database or repository cataloging all bioinformatics databases and software creates a significant barrier for researchers aiming to construct computational workflows. These workflows, which often integrate 10–15 specialized tools for tasks such as sequence alignment, variant calling, functional annotation, and data visualization, require researchers to explore diverse scientific literature to identify relevant resources. This process demands substantial expertise to evaluate the suitability of each tool for specific biological analyses, alongside considerable time to understand their applicability, compatibility, and implementation within a cohesive pipeline. The lack of a central, updated source leads to inefficiencies and the risk of using outdated tools, which can affect research quality and reproducibility. Consequently, there is a critical need for an automated, accurate tool to identify bioinformatics databases and software mentions directly from scientific texts, streamlining workflow development and enhancing research productivity.
The bioNerDS system, a prior effort to address this challenge, uses a rule-based named entity recognition (NER) approach, achieving an F1 score of 63% on an evaluation set of 25 articles from BMC Bioinformatics and PLoS Computational Biology. By integrating the same set of features such as context patterns, word characteristics and dictionary matches into a machine learning model, we developed an approach using an XGBoost classifier. This model, carefully tuned to address the extreme class imbalance inherent in NER tasks through synthetic oversampling and refined via systematic hyperparameter optimization to balance precision and recall, excels at capturing complex linguistic patterns and non-linear relationships, ensuring robust generalization. It achieves an F1 score of 82% on the same evaluation set, significantly surpassing the baseline. By combining rule-based precision with machine learning adaptability, this approach enhances accuracy, reduces ambiguities, and provides a robust tool for large-scale bioinformatics resource identification, facilitating efficient workflow construction. Furthermore, this methodology holds potential for extension to other technological domains, enabling similar resource identification in fields like data science, artificial intelligence, or computational engineering.
Vishnu Chowdary Madhavarapu
Automated Weather Classification Using Transfer LearningWhen & Where:
Nichols Hall, Room 250 (Gemini Room)
Committee Members:
David Johnson, ChairPrasad Kulkarni
Dongjie Wang
Abstract
This project presents an automated weather classification system utilizing transfer learning with pre-trained convolutional neural networks (CNNs) such as VGG19, InceptionV3, and ResNet50. Designed to classify weather conditions—sunny, cloudy, rainy, and sunrise—from images, the system addresses the challenge of limited labeled data by applying data augmentation techniques like zoom, shear, and flip, expanding the dataset images. By fine-tuning the final layers of pre-trained models, the solution achieves high accuracy while significantly reducing training time. VGG19 was selected as the baseline model for its simplicity, strong feature extraction capabilities, and widespread applicability in transfer learning scenarios. The system was trained using the Adam optimizer and evaluated on key performance metrics including accuracy, precision, recall, and F1 score. To enhance user accessibility, a Flask-based web interface was developed, allowing real-time image uploads and instant weather classification. The results demonstrate that transfer learning, combined with robust data preprocessing and fine-tuning, can produce a lightweight and accurate weather classification tool. This project contributes toward scalable, real-time weather recognition systems that can integrate into IoT applications, smart agriculture, and environmental monitoring.
RokunuzJahan Rudro
Using Machine Learning to Classify Driver Behavior from Psychological Features: An Exploratory StudyWhen & Where:
Eaton Hall, Room 1A
Committee Members:
Sumaiya Shomaji, ChairDavid Johnson
Zijun Yao
Alexandra Kondyli
Abstract
Driver inattention and human error are the primary causes of traffic crashes. However, little is known about the relationship between driver aggressiveness and safety. Although several studies that group drivers into different classes based on their driving performance have been conducted, little has been done to explore how behavioral traits are linked to driver behavior. The study aims to link different driver profiles, assessed through psychological evaluations, with their likelihood of engaging in risky driving behaviors, as measured in a driving simulation experiment. By incorporating psychological factors into machine learning algorithms, our models were able to successfully relate self-reported decision-making and personality characteristics with actual driving actions. Our results hold promise toward refining existing models of driver behavior by understanding the psychological and behavioral characteristics that influence the risk of crashes.
Md Mashfiq Rizvee
Energy Optimization in Multitask Neural Networks through Layer SharingWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairTamzidul Hoque
Han Wang
Abstract
Artificial Intelligence (AI) is being widely used in diverse domains such as industrial automation, traffic control, precision agriculture, and smart cities for major heavy lifting in terms of data analysis and decision making. However, the AI life- cycle is a major source of greenhouse gas (GHG) emission leading to devastating environmental impact. This is due to expensive neural architecture searches, training of countless number of models per day across the world, in-field AI processing of data in billions of edge devices, and advanced security measures across the AI life cycle. Modern applications often involve multitasking, which involves performing a variety of analyzes on the same dataset. These tasks are usually executed on resource-limited edge devices, necessitating AI models that exhibit efficiency across various measures such as power consumption, frame rate, and model size. To address these challenges, we introduce a novel neural network architecture model that incorporates a layer sharing principle to optimize the power usage. We propose a novel neural architecture, Layer Shared Neural Networks that merges multiple similar AI/NN tasks together (with shared layers) towards creating a single AI/NN model with reduced energy requirements and carbon footprint. The experimental findings reveal competitive accuracy and reduced power consumption. The layer shared model significantly reduces power consumption by 50% during training and 59.10% during inference causing as much as an 84.64% and 87.10% decrease in CO2 emissions respectively.
Fairuz Shadmani Shishir
Parameter-Efficient Computational Drug Discovery using Deep LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairTamzidul Hoque
Hongyang Sun
Abstract
The accurate prediction of small molecule binding affinity and toxicity remains a central challenge in drug discovery, with significant implications for reducing development costs, improving candidate prioritization, and enhancing safety profiles. Traditional computational approaches, such as molecular docking and quantitative structure-activity relationship (QSAR) models, often rely on handcrafted features and require extensive domain knowledge, which can limit scalability and generalization to novel chemical scaffolds. Recent advances in language models (LMs), particularly those adapted to chemical representations such as SMILES (Simplified Molecular Input Line Entry System), have opened new ways for learning data-driven molecular representations that capture complex structural and functional properties. However, achieving both high binding affinity and low toxicity through a resource-efficient computational pipeline is inherently difficult due to the multi-objective nature of the task. This study presents a novel dual-paradigm approach to critical challenges in drug discovery: predicting small molecules with high binding affinity and low cardiotoxicity profiles. For binding affinity prediction, we implement a specialized graph neural network (GNN) architecture that operates directly on molecular structures represented as graphs, where atoms serve as nodes and bonds as edges. This topology-aware approach enables the model to capture complex spatial arrangements and electronic interactions critical for protein-ligand binding. For toxicity prediction, we leverage chemical language models (CLMs) fine-tuned with Low-Rank Adaptation (LoRA), allowing efficient adaptation of large pre-trained models to specialized toxicological endpoints while maintaining the generalized chemical knowledge embedded in the base model. Our hybrid methodology demonstrates significant improvements over existing computational approaches, with the GNN component achieving an average area under the ROC curve (AUROC) of 0.92 on three protein targets and the LoRA-adapted CLM reaching (AUROC) of 0.90 with 60% reduction in parameter usage in predicting cardiotoxicity. This work establishes a powerful computational framework that accelerates drug discovery by enabling both higher binding affinity and low toxicity compounds with optimized efficacy and safety profiles.
Soma Pal
Truths about compiler optimization for state-of-the-art (SOTA) C/C++ compilersWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Prasad Kulkarni, ChairEsam El-Araby
Drew Davidson
Tamzidul Hoque
Jiang Yunfeng
Abstract
Compiler optimizations are critical for performance and have been extensively studied, especially for C/C++ language compilers. Our overall goal in this thesis is to investigate and compare the properties and behavior of optimization passes across multiple contemporary, state-of-the-art (SOTA) C/C++ compilers to understand if they adopt similar optimization implementation and orchestration strategies. Given the maturity of pre-existing knowledge in the field, it seems conceivable that different compiler teams will adopt consistent optimization passes, pipeline and application techniques. However, our preliminary results indicate that such expectation may be misguided. If so, then we will attempt to understand the differences, and study and quantify their impact on the performance of generated code.
In our first work, we study and compare the behavior of profile-guided optimizations (PGO) in two popular SOTA C/C++ compilers, GCC and Clang. This study reveals many interesting, and several counter-intuitive, properties about PGOs in C/C++ compilers. The behavior and benefits of PGOs also vary significantly across our selected compilers. We present our observations, along with plans to further explore these inconsistencies in this report. Likewise, we have also measured noticeable differences in the performance delivered by optimizations across our compilers. We propose to explore and understand these differences in this work. We present further details regarding our proposed directions and planned experiments in this report. We hope that this work will show and suggest opportunities for compilers to learn from each other and motivate researchers to find mechanisms to combine the benefits of multiple compilers to deliver higher overall program performance.
Nyamtulla Shaik
AI Vision to Care: A QuadView of Deep Learning for Detecting Harmful Stimming in AutismWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairBo Luo
Dongjie Wang
Abstract
Stimming refers to repetitive actions or behaviors used to regulate sensory input or express feelings. Children with developmental disorders like autism (ASD) frequently perform stimming. This includes arm flapping, head banging, finger flicking, spinning, etc. This is exhibited by 80-90% of children with Autism, which is seen in 1 among 36 children in the US. Head banging is one of these self-stimulatory habits that can be harmful. If these behaviors are automatically identified and notified using live video monitoring, parents and other caregivers can better watch over and assist children with ASD.
Classifying these actions is important to recognize harmful stimming, so this study focuses on developing a deep learning-based approach for stimming action recognition. We implemented and evaluated four models leveraging three deep learning architectures based on Convolutional Neural Networks (CNNs), Autoencoders, and Vision Transformers. For the first time in this area, we use skeletal joints extracted from video sequences. Previous works relied solely on raw RGB videos, vulnerable to lighting and environmental changes. This research explores Deep Learning based skeletal action recognition and data processing techniques for a small unstructured dataset that consists of 89 home recorded videos collected from publicly available sources like YouTube. Our robust data cleaning and pre-processing techniques helped the integration of skeletal data in stimming action recognition, which performed better than state-of-the-art with a classification accuracy of up to 87%
In addition to using traditional deep learning models like CNNs for action recognition, this study is among the first to apply data-hungry models like Vision Transformers (ViTs) and Autoencoders for stimming action recognition on the dataset. The results prove that using skeletal data reduces the processing time and significantly improves action recognition, promising a real-time approach for video monitoring applications. This research advances the development of automated systems that can assist caregivers in more efficiently tracking stimming activities.
Alexander Rodolfo Lara
Creating a Faradaic Efficiency Graph Dataset Using Machine LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Zijun Yao, ChairSumaiya Shomaji
Kevin Leonard
Abstract
Just as the internet-of-things leverages machine learning over a vast amount of data produced by an innumerable number of sensors, the Internet of Catalysis program uses similar strategies with catalysis research. One application of the Internet of Catalysis strategy is treating research papers as datapoints, rich with text, figures, and tables. Prior research within the program focused on machine learning models applied strictly over text.
This project is the first step of the program in creating a machine learning model from the images of catalysis research papers. Specifically, this project creates a dataset of faradaic efficiency graphs using transfer learning from pretrained models. The project utilizes FasterRCNN_ResNet50_FPN, LayoutLMv3SequenceClassification, and computer vision techniques to recognize figures, extract all graphs, then classify the faradaic efficiency graphs.
Downstream of this project, researchers will create a graph reading model to integrate with large language models. This could potentially lead to a multimodal model capable of fully learning from images, tables, and texts of catalysis research papers. Such a model could then guide experimentation on reaction conditions, catalysts, and production.
Amin Shojaei
Scalable and Cooperative Multi-Agent Reinforcement Learning for Networked Cyber-Physical Systems: Applications in Smart GridsWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
Morteza Hashemi, ChairAlex Bardas
Prasad Kulkarni
Taejoon Kim
Shawn Keshmiri
Abstract
Significant advances in information and networking technologies have transformed Cyber-Physical Systems (CPS) into networked cyber-physical systems (NCPS). A noteworthy example of such systems is smart grid networks, which include distributed energy resources (DERs), renewable generation, and the widespread adoption of Electric Vehicles (EVs). Such complex NCPS require intelligent and autonomous control solutions. For example, the increasing number of EVs introduces significant sources of demand and user behavior uncertainty that can jeopardize grid stability during peak hours. Traditional model-based demand-supply controls fail to accurately model and capture the complex nature of smart grid systems in the presence of different uncertainties and as the system size grows. To address these challenges, data-driven approaches have emerged as an effective solution for informed decision-making, predictive modeling, and adaptive control to enhance the resiliency of NCPS in uncertain environments.
As a powerful data-driven approach, Multi-Agent Reinforcement Learning (MARL) enables agents to learn and adapt in dynamic and uncertain environments. However, MARL techniques introduce complexities related to communication, coordination, and synchronization among agents. In this PhD research, we investigate autonomous control for smart grid decision networks using MARL. First, we examine the issue of imperfect state information, which frequently arises due to the inherent uncertainties and limitations in observing the system state.
Second, we focus on the cooperative behavior of agents in distributed MARL frameworks, particularly under the central training with decentralized execution (CTDE) paradigm. We provide theoretical results and variance analysis for stochastic and deterministic cooperative MARL algorithms, including Multi-Agent Deep Deterministic Policy Gradient (MADDPG), Multi-Agent Proximal Policy Optimization (MAPPO), and Dueling MAPPO. These analyses highlight how coordinated learning can improve system-wide decision-making in uncertain and dynamic environments like EV networks.
Third, we address the scalability challenge in large-scale NCPS by introducing a hierarchical MARL framework based on a cluster-based architecture. This framework organizes agents into coordinated subgroups, improving scalability while preserving local coordination. We conduct a detailed variance analysis of this approach to demonstrate its effectiveness in reducing communication overhead and learning complexity. This analysis establishes a theoretical foundation for scalable and efficient control in large-scale smart grid applications.
Asrith Gudivada
Custom CNN for Object State Classification in Robotic CookingWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
David Johnson, ChairPrasad Kulkarni
Dongjie Wang
Abstract
This project presents the development of a custom Convolutional Neural Network (CNN) designed to classify object states—such as sliced, diced, or peeled—in robotic cooking environments. Recognizing fine-grained object states is critical for context-aware manipulation yet remains a challenging task due to the visual similarity between states and the limited availability of cooking-specific datasets. To address these challenges, we built a lightweight, non-pretrained CNN trained on a curated dataset of 11 object states. Starting with a baseline architecture, we progressively enhanced the model using data augmentation, optimized dropout, batch normalization, Inception modules, and residual connections. These improvements led to a performance increase from ~45% to ~52% test accuracy. The final model demonstrates improved generalization and training stability, showcasing the effectiveness of combining classical and advanced deep learning techniques. This work contributes toward real-time state recognition for autonomous robotic cooking systems, with implications for assistive technologies in domestic and elder care settings.
Tanvir Hossain
Gamified Learning of Computing Hardware Fundamentals Using FPGA-Based PlatformWhen & Where:
Nichols Hall, Room 250 (Gemini Room)
Committee Members:
Tamzidul Hoque, ChairEsam El-Araby
Sumaiya Shomaji
Abstract
The growing dependence on electronic systems in consumer and mission critical domains requires engineers who understand the inner workings of digital hardware. Yet many students bypass hardware electives, viewing them as abstract, mathematics heavy, and less attractive than software courses. Escalating workforce shortages in the semiconductor industry and the recent global chip‑supply crisis highlight the urgent need for graduates who can bridge hardware knowledge gaps across engineering sectors. In this thesis, I have developed FPGA‑based games, embedded in inclusive curricular modules, which can make hardware concepts accessible while fostering interest, self‑efficacy, and positive outcome expectations in hardware engineering. A design‑based research methodology guided three implementation cycles: a pilot with seven diverse high‑school learners, a multiweek residential summer camp with high‑school students, and a fifteen‑week multidisciplinary elective enrolling early undergraduate engineering students. The learning experiences targeted binary arithmetic, combinational and sequential logic, state‑machine design, and hardware‑software co‑design. Learners also moved through the full digital‑design flow, HDL coding, functional simulation, synthesis, place‑and‑route, and on‑board verification. In addition, learners explored timing analysis, register‑transfer‑level abstractions, and simple processor datapaths to connect low‑level circuits with system‑level behavior. Mixed‑method evidence was gathered through pre‑ and post‑content quizzes, validated surveys of self‑efficacy and outcome expectations, focus groups, classroom observations, and gameplay analytics. Paired‑sample statistics showed reliable gains in hardware‑concept mastery, self‑efficacy, and outcome expectations. This work contributes a replicable framework for translating foundational hardware topics into modular, game‑based learning activities, empirical evidence of their effectiveness across secondary and early‑college contexts, and design principles for educators who seek to integrate equitable, hands‑on hardware experiences into existing curricula.
Hara Madhav Talasila
Radiometric Calibration of Radar Depth Sounder Data ProductsWhen & Where:
Nichols Hall, Room 317 (Richard K. Moore Conference Room)
Committee Members:
Carl Leuschen, ChairPatrick McCormick
James Stiles
Jilu Li
Leigh Stearns
Abstract
Although the Center for Remote Sensing of Ice Sheets (CReSIS) performs several radar calibration steps to produce Operation IceBridge (OIB) radar depth sounder data products, these datasets are not radiometrically calibrated and the swath array processing uses ideal (rather than measured [calibrated]) steering vectors. Any errors in the steering vectors, which describe the response of the radar as a function of arrival angle, will lead to errors in positioning and backscatter that subsequently affect estimates of basal conditions, ice thickness, and radar attenuation. Scientific applications that estimate physical characteristics of surface and subsurface targets from the backscatter are limited with the current data because it is not absolutely calibrated. Moreover, changes in instrument hardware and processing methods for OIB over the last decade affect the quality of inter-seasonal comparisons. Recent methods which interpret basal conditions and calculate radar attenuation using CReSIS OIB 2D radar depth sounder echograms are forced to use relative scattering power, rather than absolute methods.
As an active target calibration is not possible for past field seasons, a method that uses natural targets will be developed. Unsaturated natural target returns from smooth sea-ice leads or lakes are imaged in many datasets and have known scattering responses. The proposed method forms a system of linear equations with the recorded scattering signatures from these known targets, scattering signatures from crossing flight paths, and the radiometric correction terms. A least squares solution to optimize the radiometric correction terms is calculated, which minimizes the error function representing the mismatch in expected and measured scattering. The new correction terms will be used to correct the remaining mission data. The radar depth sounder data from all OIB campaigns can be reprocessed to produce absolutely calibrated echograms for the Arctic and Antarctic. A software simulator will be developed to study calibration errors and verify the calibration software. The software for processing natural targets and crossovers will be made available in CReSIS’s open-source polar radar software toolbox. The OIB data will be reprocessed with new calibration terms, providing to the data user community a complete set of radiometrically calibrated radar echograms for the CReSIS OIB radar depth sounder for the first time.
Christopher Ord
A Hardware-Agnostic Simultaneous Transmit And Receive (STAR) Architecture for the Transmission of Non-Repeating FMCW WaveformsWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
Rachel Jarvis, ChairShannon Blunt
Patrick McCormick
Abstract
With the increasing congestion of the usable RF spectrum, it is increasingly necessary for communication and radar systems to share the same frequencies without disturbing one another. To accomplish this, research has focused on designing a class of non-repeating radar waveforms that appear as noise at the receiver of uncooperative systems, but the peak power from high-power pulsed systems can still overwhelm nearby in-band systems. Therefore, to minimize peak power while maximizing the total energy on target, radar systems must transition to operating at a 100% duty cycle, which inherently requires Simultaneous Transmit and Receive (STAR) operation.
One inherent difficulty when operating monostatic STAR systems is the direct path coupling interference that can saturate a number of components in the radar’s receive chain, which makes digital processing methods that remove this interference ineffective. This thesis proposes a method to reduce the self-interference between the radar’s transmitter in receiver prior to the receiver’s sensitive components to increase the power that the radar can transmit at. By using a combination of tests that manipulate the timing, phase, and magnitude of a secondary waveform that is injected into the radar just before the receiver, upwards of 35.0 dB of self-interference cancellation is achieved for radar waveforms with bandwidths of up to 100 MHz at both S-band and X-band in both simulation and open-air testing.
Past Defense Notices
RANJITH SOMPALLI
Implementation of Invertebrate Paleontology Knowledge base using Integration of Textual Ontology & Visual FeaturesWhen & Where:
2001B Eaton Hall
Committee Members:
Bo Luo, ChairJerzy Grzymala-Busse
Richard Wang
Abstract
The Treatise on Invertebrate Paleontology is the most authoritative compilation of the invertebrate fossil records. The quality of studies in paleontology, in particular depends on the accessibility of fossil data. Unfortunately, the PDF version of Treatise currently available is just a scanned copy of the paper publications and the content is in no way organized to facilitate search and knowledge discovery. This project builds an Information Retrieval based system, to extract the fossil descriptions, images and other available information from Treatise. This project is divided into two parts. The first part deals with the extraction of the text and images from the Treatise, organize the information in a structured format and store in a relational database, build a search engine to browse fossil data. Extracting text requires identifying common textual patterns and a text parsing algorithm is developed to identify the patterns and organize the information in a structural format. Images are extracted using the image processing techniques like image segmentation, morphological operations etc., and then associated with the corresponding textual descriptions. A Search engine is built to efficiently browse the extracted information and also the web interface provides options to perform many useful tasks with ease. The second part of this research focuses on the implementation of Content Based Information Retrieval System. All images from treatise are grayscale fossil images and identifying the matching images based on the visual image features is a very difficult task. Hence, we employed an approach that integrates textual and visual features to identify matching images. Textual features are extracted from the description of the fossils and using statistical approaches and Parts of Speech tagging approaches, an ontology is generated, that forms attribute – property pairs explaining how a region looks like in each shell. Popular image features like SIFT, GIST, and HOG features are extracted from fossil images. Both the textual and image features are then integrated to extract the information related to the fossil image matching the query image.
NAGABHUSHANA GARGESHWARI MAHADEVASWAMY
How Duplicates Affect the Error Rate of Data Sets During ValidationWhen & Where:
2001B Eaton Hall
Committee Members:
Jerzy Grzymala-Busse, ChairPrasad Kulkarni
Bo Luo
Abstract
In data mining, duplicate data plays a huge role in deciding the set of rules. In this project, an analysis has been made on finding the impact of duplicates in the input data set on the rule set. The effect of duplicates is being analyzed using the error rate factor. Error rate is calculated by comparing the obtained rule set against the testing part of input data. The results of experiments have shown decrement of error rate with the increase of percentage of duplicates in the input data set, which demonstrates that the duplicate data plays a crucial role in validation process of machine learning. LEM2 algorithm and rule checker application have been implemented as a part of project. LEM2 algorithm is used to induce the rule set for the given input data set and rule checker application is used to calculate the error rate.
GOWTHAM GOLLA
Developing Novel Machine Learning Algorithms to Improve Sedentary Assessment for Youth Health EnhancementWhen & Where:
2001B Eaton Hall
Committee Members:
Luke Huan, ChairJerzy Grzymala-Busse
Jordan Carlson
Abstract
Sedentary behavior of youth is an important determinant of health. However, better measures are needed to improve understanding of this relationship and the mechanisms at play, as well as to evaluate health promotion interventions. Even though wearable devices like accelerometers (e.g. activPAL) are considered as the standard for assessing physical activity in research, the machine learning algorithms that we propose will allow us to re-examine existing accelerometer data to better understand the association between sedentary time and health in various populations. In order to achieve this, we collected two datasets, one is laboratory-controlled dataset and second is free-living dataset. We trained machine learning classifiers on both datasets and compared their behaviors on these datasets. The classifiers predict five postures: sit, stand, sit-stand, stand-sit, and stand\walk. We have also compared manually constructed Hidden Markov model(HMM) with automated HMM from existing software on both datasets to better understand the algorithm and existing software. When we tested on the laboratory-controlled dataset and the free-living dataset, the manually constructed HMM gave more F1-Macro score.
RITANKAR GANGULY
Graph Search Algorithms and Their ApplicationsWhen & Where:
2001B Eaton Hall
Committee Members:
Man Kong, ChairNancy Kinnersley
Jim Miller
Abstract
Depth- First Search (DFS) and Breadth- First Search are two of the most extensively used graph traversal algorithms to compile information about the graph in linear time. These two graph traversal mechanisms overlay a path to explore further the applications based on them that are widely used in Network Engineering, Web Analytics, Social Networking, Postal Services and Hardware Implementations. The difference between DFS and BFS results in the order in which they explore vertices and the implementation techniques for storing the discovered but un-processed vertices in the graph. BFS algorithm usually needs less time but consumes more computer memory than a DFS implementation. DFS algorithm is based on LIFO mechanism and is implemented using stack. BFS algorithm is based on FIFO technique and is realized using a queue. The order in which the vertices are visited using DFS or BFS can be realized with the help of a tree. The type of graph (directed or undirected) along with the edges of these trees form the basis of all the applications on BFS or DFS. Determining the shortest path between vertices of an un-weighted graph can be used in network engineering to transfer data packets. Checking for the presence of cycle can be critical in minimizing redundancy in telecommunications and is extensively used by social networking websites these days to analyse information as how people are connected. Finding bridges in a graph or determining the set of articulation vertices help minimize vulnerability in network design. Finding the strongly connected components in a graph can be used by model checkers in computer science. Determining an Euler circuit in a graph can be used by the postal service industries and the algorithm can be successfully implemented with linear running time using enhanced data structures. This survey project briefly defines and explains the basics of DFS and BFS traversal and explores some of the applications that are based on these algorithms.
MICHAEL BLECHA
Implementation of a 2.45GHz Power Amplifier for use in Collision Avoidance RadarWhen & Where:
2001B Eaton Hall
Committee Members:
Chris Allen, ChairGlenn Prescott
Jim Stiles
Abstract
The integration of a RF power amplifier into a Collision Avoidance Radar will increase the maximum detection distance of the radar. Increasing the maximum detection distance will allow a radar system mounted on an Unmanned Aircraft Vehicle to observe obstacles earlier and give the UAV more time to react. The UAVradars project has been miniaturized to support operation on an unmanned aircraft and could benefit from an increase in maximum detection distance.
The goal of this project is to create a one watt power amplifier for the 2.4GHz-2.5GHz band that can be integrated into the UAVradars project. The amplifier will be powered from existing power supplies in the radar system and must be small and lightweight to support operation on board the UAV in flight. This project will consist of the schematic and layout design, simulations, fabrication, and characterization of the power amplifier. The power amplifier will be designed to fit into the current system with minimal system modifications required.
HARSHUL ROUTHU
A Comparison of Two Decision Tree Generating Algorithms C4.5 and CART Based on Testing Datasets with Missing Attribute ValuesWhen & Where:
2001B Eaton Hall
Committee Members:
Jerzy Grzymala-Busse, ChairPrasad Kulkarni
Bo Luo
Abstract
In data mining, missing data are a common occurrence and can have a significant effect on the conclusions that can be drawn from the data. Classification of missing data is a challenging task. One of the most popular techniques for classifying missing data is decision tree induction.
In this project, we compare two decision tree generating algorithms CART and C4.5 with their original implementations on different datasets with missing attribute values, taken from University of California Irvine (UCI). The comparative analysis of these two implementations is carried out in terms of accuracy on training and testing data, and decision tree complexity based on its depth and size. Results from experiments show that there is statistically insignificant difference between C4.5 and CART in terms of accuracy on testing data and complexity of the decision tree. On the other hand, accuracy on training data is significantly better for CART compared to C4.5.
HADEEL ALABANDI
A Survey of Metrics Employed to Assess Software SecurityWhen & Where:
246 Nichols Hall
Committee Members:
Prasad Kulkarni, ChairAndy Gill
Heechul Yun
Abstract
Measuring and assessing software security is a critical concern as it is undesirable to develop risky and insecure software. Various measurement approaches and metrics have been defined to assess software security. For researchers and software developers, it is significant to have different metrics and measurement models at one place either to evaluate the existing measurement approaches, to compare between two or more metrics or to be able to find the proper metric to measure the software security at a specific software development phase. There is no existing survey of software security metrics that covers metrics available at all the software development phases. In this paper, we present a survey of metrics used to assess and measure software security, and we categorized them based on software development phases. Our findings reveal a critical lack of automated tools, and the necessity to possess detailed knowledge or experience of the measured software as the major hindrances in the use of existing software security metrics.
HARISH SAMPANGI
Delay Feedback Reservoir (DFR) Design in Neuromorphic Computing Systems and its Application in Wireless CommunicationsWhen & Where:
2001B Eaton Hall
Committee Members:
Yang Yi, ChairGlenn Prescott
Jim Rowland
Abstract
As semiconductor technologies continue to scale further into the nanometer regime, it is important to study how non-traditional computer architectures may be uniquely suited to take advantage of the novel behavior observed for many emerging technologies. Neuromorphic computing system represents a type of non-traditional architecture encompassing evolutionary. Reservoir computing, a computational paradigm inspired on neural systems, has become increasingly popular for solving a variety of complex recognition and classification problems. The traditional reservoir computing methods employs three different layers – the input layer, the reservoir and the output layer. The input layer feeds the input signals to the reservoir via fixed random weighted connections. These weights will scale the input that is given to the nodes, creating different input scaling for the input nodes. The second layer, which is called the reservoir, usually consists of a large number of randomly connected nonlinear nodes, constituting a recurrent network. Finally, the output weights are extracted from the output layer. Contrary to this traditional approach, the delayed feedback reservoir replaces the entire network of connected non-liner nodes just with a single nonlinear node subjected to delayed feedback. This approach does not only provide a drastic simplification of the experimental implementation of artificial neural networks for computing purposes, it also demonstrates the huge computational processing power hidden in even the simplest delay-dynamical system. Previous implementation of reservoir computing using the echo state network has been proven efficient for channel estimation in wireless Orthogonal Frequency-Division Multiplexing (OFDM) systems. This project aims at verifying the performance of DFR in channel estimation, by calculating its bit error rate (BER) and comparing it with other standard techniques like the LS and MMSE.
AUDREY SEYBERT
Analysis of Artifacts Inherent to Real-Time Radar Target EmulationWhen & Where:
246 Nichols Hall
Committee Members:
Chris Allen, ChairShannon Blunt
Jim Stiles
Abstract
Executing high-fidelity tests of radar hardware requires real-time fixed-latency target emulation. Because fundamental radar measurements occur in the time domain, real-time fixed latency target emulation is essential to producing an accurate representation of a radar environment. Radar test equipment is further constrained by the application-specific minimum delay to a target of interest, a parameter that limits the maximum latency through the target emulator algorithm. These time constraints on radar target emulation result in imperfect DSP algorithms that generate spectral artifacts. Knowledge of the behavior and predictability of these spectral artifacts is the key to identifying whether a particular suite of hardware is sufficient to execute tests for a particular radar design. This work presents an analysis of the design considerations required for development of a digital radar target emulator. Further considerations include how the spectral artifacts inherent to the algorithms change with respect to the radar environment and an analysis of how effectively various DSP algorithms can be used to produce an accurate representation of simple target scenarios. This work presents a model representative of natural target motion, a model that is representative of the side effects of digital target emulation, and finally a true HDL simulation of a target.
CHRISTOPHER SEASHOLTZ
Security and Privacy Vulnerabilities in Unmanned Aerial VehiclesWhen & Where:
246 Nichols Hall
Committee Members:
Bo Luo, ChairJoe Evans
Fengjun Li
Abstract
In the past few years, UAVs have become very popular amongst the average citizen. Much like their military counterpart, these UAVs provide the ability to be controlled by computers, instead of a remote controller. While this may not appear to be a major security issue, the information gained from compromising a UAV can be used for other malicious activities. To understand potential attack surfaces of various UAVs, this paper presents the theory behind multiple possible attacks, as well as implementations of a select number of attacks mentioned. The main objective of this project was to obtain complete control of a UAV while in flight. Only a few of the attacks demonstrated, or mentioned, provide this ability. The remaining attacks mentioned provide information that can be used in conjunction with others in order to provide full control, or complete knowledge, of a system. Once the attacks have been proven possible, measures for proper defense must be taken. For each attack described in this paper, possible countermeasures will be given and explained.