Computer Sciences Commons^™

Fair And Explainable Educational Recommendations With A Hybrid Graph-Gru Framework, Edmund Evangelista, Syed M.Salman Bukhari

All Works

Artificial Intelligence (AI) recommender systems are increasingly used in education to personalize learning and help students navigate large collections of digital learning resources. However, many existing approaches emphasize predictive accuracy over fairness, robustness, diversity, and transparency. This creates an important educational challenge. The students with limited participation histories may receive less reliable support, while highly popular resources may dominate recommendation lists and limit access to other useful learning materials. To address this challenge, this study aims to develop and evaluate a responsible educational recommender framework that supports personalized learning resource navigation while making recommendation behavior more fair, stable, diverse, and …

Design And Evaluation Of A Code-Switching-Aware Multilingual Conversational Ai System Using Advanced Rag Architectures, Ashutosh Juvale

Master’s Dissertations

Conversational artificial intelligence has become the primary interface through which hundreds of millions of users in India seek information and customer support. Yet the way these users actually write and speak is fundamentally at odds with the monolingual assumptions baked into most retrieval and generation systems: they code-switch, fluidly mixing one or more of the twenty-two scheduled languages of India with English, frequently typing Indic words in the Roman script ("mera refund kab tak aayega"). Standard Retrieval-Augmented Generation (RAG) pipelines silently fail on such input — the retriever returns off-topic passages because the query and the knowledge base live in …

Accurate Diagnosis Of Diseases By A Novel Ai Pipeline Based On Feature Extraction, Feature Ranking, And Feature Selection From Medical Images, Tuğba Nur Bozkurt, Mehmet Emi̇n Yüksel

Turkish Journal of Electrical Engineering and Computer Sciences

The rapid growth of the global population has led to a substantial increase in the number of patients, while the availability of healthcare professionals has not expanded at a comparable rate. This imbalance highlights the urgent need for efficient and reliable computer-aided decision support systems that can reduce clinical workload while maintaining high diagnostic accuracy. In this study, a novel and systematically integrated artificial intelligence-based pipeline is proposed for medical image classification, combining statistical significance-driven feature ranking with evolutionary feature selection in a unified framework. The proposed pipeline consists of four sequential stages: feature extraction, ranking, selection, and classification. Features …

Aircraft Fault Detection Via Weight And Bias Analysis Of A Custom First Neural Network Layer, George Harrison Chen

Theses and Dissertations

Fault detection in aircraft is traditionally handled through redundant hardware and comparison algorithms to detect failures. Alternatives like model-based residual generation and data-driven approaches such as supervised fault classification and unsupervised anomaly detection have been explored, but they suffer from practical limitations; model-based methods require accurate system models, and data-driven methods have large constraints on the data limiting scalability and adaptability. This work presents a purely data-driven neural network architecture featuring a custom first layer designed for real-time fault detection where the weights and biases of this layer are used to detect faults. The network requires zero supervision and complements …

You Can’T Spell Audit Without Ai: The Current Uses Of Artificial Intelligence In Audit, Jena Perkins

Senior Honors Theses

The accounting profession continuously adapts to the innovations provided by the broader context in which it exists. Artificial intelligence (AI) is a forerunner among tools used to enhance and optimize auditing services within the accounting profession. The realm of AI offers advancements to procedures used within an audit to detect misstatements. Based on the proprietary platforms developed by Big 4 accounting firms, AI is a key component in maintaining an advanced approach towards auditing.

Material Reconstruction From Single Image Combining Neural Networks With Singular Value Decomposition, Zhiqiang Li, Xukun Shen, Yong Hu, Xueyang Zhou, Yifan Chen

Journal of System Simulation

Abstract: The tabulated BRDFs (bidirectional reflectance distribution function) can realistically reproduce the surface appearance of objects. However, due to their high-dimensional characteristics and the fact that a single planar image contains limited reflectance information and small differences, methods for estimating tabulated BRDFs typically require complex equipment or the capture of multiple images. To address this issue, a method is proposed for reconstructing material properties from a single image by combining neural networks with singular value decomposition. The singular value decomposition is introduced to compress the material into a lower-dimensional space. The task of solving the tabulated BRDFs is simplified to …

Online Lifelong Optimal Adaptive Control Of Partially Uncertain Strict Feedback Discrete-Time Systems With Application To Quadrotor Uavs, Maxwell Geiger, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This article considers the infinite time horizon optimal adaptive tracking control of partially uncertain strict feedback discrete-time (DT) systems with application to quadrotor uncrewed aerial vehicles (UAVs). First, the strict feedback DT system is transformed into an equivalent affine nonlinear DT system in terms of the tracking error dynamics. The optimal adaptive tracking control problem is solved using an augmented system approach, where a horizon of future bounded reference trajectory points is used in the augmented state, when compared to using a single point. It is assumed that the internal dynamics of the strict feedback system are unknown, but the …

Maxgrnet: A Multi-Axis Vision Transformer With Improved Generalization For Eye Disease Classification Using Explainable Ai With Insertion-Deletion Operations On Fundus Images, Md Mehedi Hasan Santo, Fuyad Hasan Bhoyan, Fuad Ibne Jashim Farhad, Fahmid Al Farid, Sovon Chakraborty, Md Humaion Kabir Mehedi, Jia Uddin, Hezerul Bin Abdul Karim

Computer Science Faculty Publications

Eye diseases, including diabetic retinopathy (DR), glaucoma, and cataracts, represent a major global health concern and can lead to severe visual impairment or blindness if not identified in a timely manner. This study proposes a novel eye disease classification framework based on a multi-axis vision transformer (MaxViT) applied to color fundus images with Explainable Artificial Intelligence (XAI) techniques to enhance model transparency. The proposed architecture integrates transformer-based attention mechanisms with Global Response Normalization (GRN)-based multi-layer perceptron (MLP) layers to capture complex spatial and contextual relationships within fundus images effectively. The model was evaluated on a publicly available eye disease classification …

Explainable Convolutional Neural Network Model Provides An Alternative Genome-Wide Association Perspective On Mutations In Sars-Cov-2, Parisa C. Hatami, Richard Annan, Luis Miranda, Jane L. Gorman, Mengjun Xie, Letu Qingge, Hong Qin

Computer Science Faculty Publications

Identifying informative genomic features in SARS-CoV-2 can help clarify patterns of viral evolution. In this study, we developed an explainable convolutional neural network (CNN) model to classify SARS-CoV-2 genomic sequences into the WHO-designated Variants of Concern (VOCs), Alpha, Beta, Gamma, Delta, and Omicron. Using a balanced dataset of genomes, the classification CNN achieved 99.96% accuracy on the held-out test set. To interpret the model’s predictions, we applied SHapley Additive exPlanations (SHAP) to estimate the contribution of each nucleotide position to VOC-label prediction and compared aggregated attributions with a chi-square GWAS baseline applied to the same categorical labels. SHAP prioritized several …

Image Captioning Through The Lens Of The Gricean Maxims: Generating Meaningful And Relevant Image Descriptions, Annika Lindh

Doctoral

Image captioning models enable us to automatically generate natural language image descriptions for previously unseen images. It combines the two fields of computer vision and natural language generation, allowing models to interpret the con tent of an image and communicate that knowledge through natural language text.

Research into image captioning has the potential benefit of reducing the gap in digital information availability between fully sighted individuals and those who are visually impaired. However, automatically generated captions often fail to provide the required level of detail and specificity to achieve this goal. Furthermore, current standard evaluation methods are insufficient at measuring …

Synergistic Modeling Of Hydrogel Gelation Via Time-Delay Dynamics And Machine Learning Algorithms, Mine Babaoglu, Dipesh ., Pankaj Kumar, Jagjit Singh Dhatterwal, Mansoor Alsulami

Mathematical Modelling and Numerical Simulation with Applications

This paper presents an integrated framework in which delay differential equation (DDE) modeling and machine learning (ML) approaches are coupled to study hydrogel formation kinetics, with emphasis on delayed crosslinker addition. Conventional mechanistic models disclose many physical and kinetic complexities of reacting mixtures; they seldom depict the nonlinear and time-evolving complexities inherent in developing polymer networks. To address this, a mathematical model is developed that examines how the insertion of crosslinkers affects system stability and equilibrium. Analytical and numerical results show that delays nearing critical levels cause bifurcation behavior with substantial implications on gelation kinetics. Sophisticated machine learning systems, including …

Intelligence Architectures And Machine Learning Applications In Contemporary Spine Care, Rahul Kumar, Conor Dougherty, Kyle Sporn, Akshay Khanna, Puja Ravi, Pranay Prabhakar, Nasif Zaman

SKMC Student Presentations and Publications

The rapid evolution of artificial intelligence (AI) and machine learning (ML) technologies has initiated a paradigm shift in contemporary spine care. This narrative review synthesizes advances across imaging-based diagnostics, surgical planning, genomic risk stratification, and post-operative outcome prediction. We critically assess high-performing AI tools, such as convolutional neural networks for vertebral fracture detection, robotic guidance platforms like Mazor X and ExcelsiusGPS, and deep learning-based morphometric analysis systems. In parallel, we examine the emergence of ambient clinical intelligence and precision pharmacogenomics as enablers of personalized spine care. Notably, genome-wide association studies (GWAS) and polygenic risk scores are enabling a shift from …

Relightable Neural Radiance Fields For Novel View Synthesis, Malena I. Mahoney

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

This paper describes relighting neural radiance fields for novel view synthesis. View synthesis is the problem of using input images with corresponding camera angles to produce a photorealistic 3D model of an environment and its objects. Neural radiance fields (NeRFs) were created as a solution to view synthesis. Neural radiance field models work well for generating realistic 3D models from 2D image inputs; how-ever, they do not support changing the lighting or placing the objects from the input images into different environments. The problem comes from the fact that NeRFs rely on a neural network that is essentially overfitted to …

Toward A Simplified Framework For Sequential Character Recognition, Nicholas Howe

Computer Science: Faculty Publications

This paper proposes a novel approach to handwritten charac- ter recognition using convolutional non-recurrent deep neural networks. Such a network can run in parallel at every point of a document, offer- ing potential advantages in speed over recurrent approaches. The net- work’s output feeds into a beam search optimization for final decoding. Preliminary quantitative results show that the framework can achieve bootstrap training from labeled word images. It provides an alternative to sequential models that rely on connectionist temporal classification for alignment.

Multi-Modal Emotion Appraisals Using Large Language Models, Carlos Guerrero Alvarez

Computer Science Senior Theses

This thesis investigates the capabilities of large language models (LLMs), specifically GPT4 and GPT4o, in appraising human emotional responses within strategic social scenarios. Building on the work of Houlihan et. al[7], we evaluate LLMs using a dataset of human emotion ratings from game-theoretic situations, later extending the experimental paradigm to include both text and multimodal (image and profession) inputs. Our methodology introduces novel prompting techniques for the experiment at hand, and we compare the performance of these techniques with expert perspectives to assess how different prompts influence model predictions. Results show that LLMs can approximate human emotional appraisals, with the …

Enabling Automatic Solar Pv Array Identification Using Big Satellite Imagery, Qi Li, Keyang Yu, Carson Snow, Dong Chen

Computer Science Faculty Research and Publications

Recently, there has been a growing interest in automatically collecting distributed solar photovoltaic (PV) installation information in smart grid systems, including the quantity and locations of solar PV deployments, as well as their profiling information across a given geospatial region. Most recent approaches are still suffering low detection accuracy due to insufficient sample and principal feature learning when building their models and also separation of rooftop object segmentation and identification during their detection processes. In addition, they cannot report accurate multi-deployment results. To address these problems, we design a new system-SolarDetector+, which can automatically and accurately detect and profile distributed …

Hierarchical Log Bayesian Neural Network For Enhanced Aorta Segmentation, Delin An, Pan Du, Pengfei Gu, Jian-Xun Wang, Chaoli Wang

Computer Science Faculty Publications

Accurate segmentation of the aorta and its associated arch branches is crucial for diagnosing aortic diseases. While deep learning techniques have significantly improved aorta segmentation, they remain challenging due to the intricate multiscale structure and the complexity of the surrounding tissues. This paper presents a novel approach for enhancing aorta segmentation using a Bayesian neural network-based hierarchical Laplacian of Gaussian (LoG) model. Our model consists of a 3D U-Net stream and a hierarchical LoG stream: the former provides an initial aorta segmentation, and the latter enhances blood vessel detection across varying scales by learning suitable LoG kernels, enabling self-adaptive handling …

Computational Complexity Of Soundness Verification For Neural Networks, Scott Sirri

McKelvey School of Engineering Graduate Student Theses & Dissertations

Neural networks are an increasingly ubiquitous tool in systems of varying complexity across a range of domains. While these tools can be used to learn and predict complex functions, their opaque nature limits the scope of their acceptable applications. In particular, a lack of performance guarantees means that they are unsuitable for safety-critical applications such as self-driving cars and scheduling systems. Neural networks trained to solve NP-complete problems, in particular, are unlikely to be able to solve the problem exactly. However, a weaker soundness guarantee may be sufficient for some systems, e.g., that positive instances of the problem may be …

Identification Of Subtypes Of Post-Stroke And Neurotypical Gait Behaviors Using Neural Network Analysis Of Gait Cycle Kinematics, Andrian Kuch, Nicolas Schweighofer, James M. Finley, Alison Mckenzie, Yuxin Wen, Natalia Sánchez

Physical Therapy Faculty Articles and Research

Gait impairment post-stroke is highly heterogeneous. Prior studies classified heterogeneous gait patterns into subgroups using peak kinematics, kinetics, or spatiotemporal variables. A limitation of this approach is the need to select discrete features in the gait cycle. Using continuous gait cycle data, we accounted for differences in magnitude and timing of kinematics. Here, we propose a machine-learning pipeline combining supervised and unsupervised learning. We first trained a Convolutional Neural Network and a Temporal Convolutional Network to extract features that distinguish impaired from neurotypical gait. Then, we used unsupervised time-series k-means and Gaussian Mixture Models to identify gait clusters. We tested …

Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca

Theses and Dissertations

Missing data is pervasive in healthcare, where incomplete observations commonly arise from patient dropout, sensor failures, or privacy constraints. This research presents an investigation into handling such data, focusing on (1) Missingness-Aware Dynamic Ensemble Weighting (MDEW), (2) feature selection under varying missing rates, (3) autoencoder-based imputation (ODAE), and (4) a meta-feature analysis guiding pipeline selection. We evaluate our experiments on four diverse datasets, Cleveland Heart Disease, Diabetic Retinopathy, Breast Cancer Wisconsin, EEG Eye State. Our research shows that MDEW adaptively selects imputer classifier pipelines, outperforming single model and uniform averaging baselines at moderate to high missingness 10% to 50%. Filter …

A Robust Rf Fingerprinting Approach Using Physics-Informed Neural Networks, Jozef Dusenka

Graduate Theses and Dissertations

Radio frequency (RF) fingerprints, caused by unique imperfections in communication hardware, offer a promising solution for zero-trust security. However, existing RF fingerprinting techniques, which aim to extract these signatures from transmitters to uniquely identify devices, often struggle with robustness in the face of temporal and spatial variations in real-world, time-varying wireless environments. For example, a neural network trained on RF signals collected on Day 1 can experience a significant performance drop when tested with data from Day 2.

To address this challenge, we propose a novel, robust RF fingerprinting method based on Physics-Informed Neural Networks (PINNs). Rather than training the …

Reinforcement Learning-Based Nonlinear Optimal Discrete-Time Control Of Power Systems, Vijay Kumar Singh, Behzad Farzanegan, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a partially model-free adaptive optimal tracking control method for power systems, specifically targeting a synchronous generator connected through a reactive transmission line. By integrating the tracking error dynamics with reference trajectory dynamics, an augmented system is created. A discounted performance function is introduced to address the nonlinear tracking problem optimally. Unlike traditional methods that compute feedforward and feedback terms separately, the proposed approach calculates both simultaneously by minimizing the discounted performance function. The discrete-time tracking Bellman and Hamilton-Jacobi-Bellman (HJB) equations are derived, and a reinforcement learning (RL)-based technique is employed to solve the optimal policy online without …

Predicting Human Steering From Optic Flow Using Deep Convolutional Neural Networks, Katie E. Bernard

Honors Theses

Human driving is a complex visuomotor task and the specific visual clues that guide it remain under investigation. While prior research has emphasized gaze-based strategies such as the Tangent Point and Future Path hypotheses, recent evidence highlights the potential role of optic flow, the visual motion pattern perceived during self-movement, as critical to steering ability. This thesis explores whether raw optic flow alone can support accurate predictions of human steering behavior. We trained a convolutional neural network to map optic flow vector fields to steering angles in a virtual reality driving simulation. The dataset, collected by Giguere et al., included …

Long-Term Traffic Prediction Using Deep Learning Long Short-Term Memory, Ange-Lionel Toba, Sameer Kulkarni, Wael Khallouli, Timothy Pennington

School of Cybersecurity Faculty Publications

Traffic conditions are a key factor in our society, contributing to quality of life and the economy, as well as access to professional, educational, and health resources. This emphasizes the need for a reliable road network to facilitate traffic fluidity across the nation and improve mobility. Reaching these characteristics demands good traffic volume prediction methods, not only in the short term but also in the long term, which helps design transportation strategies and road planning. However, most of the research has focused on short-term prediction, applied mostly to short-trip distances, while effective long-term forecasting, which has become a challenging issue …

Secure Federated Learning Via Neural Cryptography With Homomorphic Operations, Espen Sele, Ferhat Ozgur Catak, Jungwon Seo, Murat Kuzlu

Engineering Technology Faculty Publications

This study examines neural cryptography with homomorphic operations as an alternative secure aggregation method for federated learning (FL). It proposes a novel neural cryptographic system supporting homomorphic addition on fixed-point encrypted data, and consisting of three networks, namely (1) an encryption network (Alice), (2) a homomorphic network (HO), and (3) a decryption network (Bob), along with an adversarial Eve network. Using the MNIST dataset, the proposed Neural Homomorphic Operation System (NHOS) is evaluated against a plaintext baseline and the CKKS scheme, a widely used public-key homomorphic encryption method. The results show that the proposed NHOS approach offers a satisfying performance, …

Skinrisk Ai, Spencer Simms

Williams Honors College, Honors Research Projects

SkinRisk AI is an exploration of the opportunities for implementing machine learning (ML) and artificial intelligence (AI) in the medical technology field, specifically in the early detection of skin cancer. This project presents the design, development, and evaluation of a mobile application that allows users to capture images of skin lesions and receive a machine learning assisted risk assessment. The system combines a convolutional neural network (CNN) for image analysis with an intuitive mobile app built using Flutter, FastAPI, and Supabase to deliver real time screening.

Motivated by the rising skin cancer rates and importance of early detection, SkinRisk AI …

Subjective Readiness Forecasting Using Supervised Machine Learning And Wearable Device Data, Nathaniel Michael Weiland

Browse all Theses and Dissertations

Recent advances in wearable technology allow continuous monitoring of physiological and behavioral data, opening new opportunities for real-time assessments of readiness and well-being. However, creating predictive models that generalize across diverse users remains challenging, especially in high-stakes settings like the military, where preventable injuries, illnesses, and stress-related performance declines are frequent. This research assesses the feasibility of using supervised machine learning models trained on wearable device data to predict subjective readiness indicators—recovery, stress, injury, and illness. Data from over 10,000 users in the OHWS (Optimizing the Human Weapons System) program combined daily check ins with physiological metrics from Garmin, Polar, …

Enhancing The Accuracy Of Image Classification For Degenerative Brain Diseases With Cnn Ensemble Models Using Mel-Spectrograms, Sang-Ha Sung, Michael Pokojovy, Do-Young Kang, Woo-Yong Bae, Yeon-Jae Hong, Sangjin Kim

Mathematics & Statistics Faculty Publications

Alzheimer’s disease (AD) and Parkinson’s disease (PD) are prevalent neurodegenerative disorders among the elderly, leading to cognitive decline and motor impairments. As the population ages, the prevalence of these neurodegenerative disorders is increasing, providing motivation for active research in this area. However, most studies are conducted using brain imaging, with relatively few studies utilizing voice data. Using voice data offers advantages in accessibility compared to brain imaging analysis. This study introduces a novel ensemble-based classification model that utilizes Mel spectrograms and Convolutional Neural Networks (CNNs) to distinguish between healthy individuals (NM), AD, and PD patients. A total of 700 voice …

Key Brain Region Identification In Obesity Prediction With Structural Mri And Probabilistic Uncertainty Aware Model, Walia Farzana, Megan A. Witherow, Ahmed Temtam, Liangsuo Ma, Melanie Bean, F. Gerry Moeller, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Objectives/Goals: Predictive performance alone may not determine a model’s clinical utility. Neurobiological changes in obesity alter brain structures, but traditional voxel-based morphometry is limited to group-level analysis. We propose a probabilistic model with uncertainty heatmaps to improve interpretability and personalized prediction. Methods/Study Population: The data for this study are sourced from the Human Connectome Project (HCP), with approval from the Washington University in St. Louis Institutional Review Board. We preprocessed raw T1-weighted structural MRI scans from 525 patients using an automated pipeline. The dataset is divided into training (357 cases), calibration (63 cases), and testing (105 cases). Our probabilistic model …

Adaptive Fusion Neural Networks For Sparse-Angle X-Ray 3d Reconstruction, Shaoyong Hong, Bo Yang, Yan Chen, Hao Quan, Shan Liu, Minyi Tang, Jiawei Tian

Electrical & Computer Engineering Faculty Publications

3D medical image reconstruction has significantly enhanced diagnostic accuracy, yet the reliance on densely sampled projection data remains a major limitation in clinical practice. Sparse-angle X-ray imaging, though safer and faster, poses challenges for accurate volumetric reconstruction due to limited spatial information. This study proposes a 3D reconstruction neural network based on adaptive weight fusion (AdapFusionNet) to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images. To address the issue of spatial inconsistency in multi-angle image reconstruction, an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion, thereby improving …