Digital Commons Network^™

Empowering Crisis Information Extraction Through Actionability Event Schemata And Domain-Adaptive Pre-Training, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint

Research Collection School Of Computing and Information Systems

One of the persistent challenges in crisis detection is inferring actionable information to support emergency response. Existing methods focus on situational awareness but often lack actionable insights. This study proposes a holistic approach to implementing an actionability extraction system on social media, including requirement gathering, selection of machine learning tasks, data preparation, and integration with existing resources, providing guidance for governments, civil services, emergency workers, and researchers on supplementing existing channels with actionable information from social media. Our solution leverages an actionability schema and domain-adaptive pre-training, improving upon the state-of-the-art model by 5.5% and 10.1% in micro and macro F1 …

Defending Federated Recommender Systems Against Untargeted Attacks: A Contribution-Aware Robust Aggregation Scheme, Ruicheng Liang, Yuanchun Jiang, Feida Zhu, Ling Cheng, Huiwen Liu

Research Collection School Of Computing and Information Systems

Federated recommender systems (FedRSs) effectively tackle the tradeoff between recommendation accuracy and privacy preservation. However, recent studies have revealed severe vulnerabilities in FedRSs, particularly against untargeted attacks seeking to undermine their overall performance. Defense methods employed in traditional recommender systems are not applicable to FedRSs, and existing robust aggregation schemes for other federated learning-based applications have proven ineffective in FedRSs. Building on the observation that malicious clients contribute negatively to the training process, we design a novel contribution-aware robust aggregation scheme to defend FedRSs against untargeted attacks, named contribution-aware Bayesian knowledge distillation aggregation (ConDA), comprising two key components for the …

The Effect Of Participation In A Place-Based Engineering Learning Experience On Engineering Career Aspiration Of Nebraska’S Rural Students: A Mixed Method Study, Samereh Soleimani Babadi

Department of Agricultural and Biological Systems Engineering: Masters Project Reports

This study investigates the influence of a place-based, hands-on engineering learning experience on rural middle school students' engineering career aspirations, using Social Cognitive Career Theory (SCCT) as a framework. Employing a mixed-methods approach, we explored how these localized learning experiences shape students' career goals through socio-cognitive factors such as self-efficacy, outcome expectations, goals, and interest. Quantitative analysis of pre- and post-activity surveys revealed significant increases in career aspiration scores, particularly among students from farming backgrounds and female students with initially lower expectations. Path analyses indicated that self-efficacy and interest were the strongest mediators between Place-based learning and engineering career aspirations. …

Transitive Pedagogy In Creative Teaching: The Lived Experiences Of K–6 Teachers Who Intentionally Adapt For Creativity, Rebekah Marie Andersen

Department of Teaching, Learning, and Teacher Education: Theses and Other Student Research

Creative pedagogy in the K–6 classroom is being increasingly recognized as an essential tool for increasing student engagement, practicing critical thinking, and fostering higher-order learning. However, research gaps in creative pedagogy are contextualized accounts of teacher thinking, planning, and enactment of strategies for student creativity. This study explored the lived experiences of teachers as they constructed and enacted creative lesson adaptations and how they identified and supported creative behaviors in students. An interpretative phenomenological analysis was employed, involving semi-structured think-aloud and stimulated recall interviews with five K–6 teachers who consistently adapt instruction to promote student creativity. Findings revealed that; (a) …

Tracing The Collective Endeavors: The Cultural Discourses Of Women Printmakers Throughout History, Ann Henrietta Bittl

CGU Theses & Dissertations

The purpose of the dissertation is to examine the women who paved the way for future generations of women printmakers by tracing the influences and practices of women printmakers throughout history within collective workshops. In the West, the concept of a collective endeavor began during the Middle Ages with monasteries and convents, where artisans created religious works of art as a way to teach illiterate audiences and also to adorn churches and cathedrals. However, during the fourteenth and fifteenth centuries, the concept of the collective workshop grew out of artist’s studios and ateliers. Artists were trained in the apprentice system, …

Equity For Multilingual Learners: An Analysis Of Long-Term English Learners’ Opportunities To Engage In Mathematical Discourse, Maria Teresa Granados

CGU Theses & Dissertations

This qualitative case study explored the opportunities provided to long-term English learners (LTELs) to engage in mathematical discourse in Algebra I classrooms. LTELs face persistent academic barriers, particularly in mathematics, where they demonstrate lower mathematic achievement, higher course repetition, and limited access to college-preparatory courses. This study addressed these equity concerns by examining how discourse practices in Algebra I can support both mathematical understanding and academic language development for LTELs. Guided by Vygotsky’s (1978) sociocultural theory and Moschkovich’s (2015) framework of academic literacy in mathematics, the study focused on discourse as a mediational tool for conceptual understanding and language acquisition. …

Geometric Dimensionality Reduction, Daniel Livschitz

CGU Theses & Dissertations

The emergence of AI models developed through computationally intensive training has resulted in a surge of research into dimensionality reduction techniques that spans across numerous mathematical disciplines. In this thesis we establish Geometric Dimensionality Reduction, a non-linear data compression technique that utilizes low dimensional manifolds embedded in dimensional spaces to form composite contraction-and-projection maps. Geometric Dimensionality Reduction is predominantly demonstrated through a novel algorithm entitled LGE (Livschitz-Gu-Eyunni) that utilizes Multicomplex rotation groups and polyspherical coordinates to define a single tuneable logarithmic map from ℝ 2푛 to ℝ 푛+1 with deterministic time complexity, geometric tunability, and semi-reversibility. Significant breakthroughs in the …

Unseen Journeying: Latinx Mothers’ Experiences And Navigation Of Pre-Referral Home-School Collaboration, Yoné Rodríguez

CGU Theses & Dissertations

Research has documented various home-school collaboration obstacles faced by Latinx mothers whose children receive special education services. However, minimal attention has focused on Latinx mothers of students in the pre-referral stage—the time when students facing significant academic difficulties may be struggling in the classroom but have not yet been referred to special education evaluation. Responding to this gap in the literature, this qualitative study investigated how Latinx mothers experienced and navigated pre-referral home-school collaboration, which was conceptualized as the dynamic process occurring between family members and school personnel working towards common goals related to student growth. In alignment with Chicana …

Ai And Tribal Court Practice, Matthew L.M. Fletcher

Articles

American Indian tribal court practice resides at the intersection of two difficult legal problems. First, because tribal justice systems are usually very young and dynamic, awareness and analysis of tribal law is underdeveloped. Second, because tribal nations are not governed by state or federal law, tribal law is culturally unique. Tribal court practitioners often find that even routine legal matters will involve questions of first impression in the jurisdiction. All of this is to say tribal court jurisprudence is intensely jurisgenerative.

Because tribal law is often unsettled or indeterminate, the costs of discovering and applying this law are occasionally high. …

Clinicians In The Loop Of Medical Ai, W. Nicholson Price Ii

Articles

As medical AI begins to mature as a health-care tool, the task of governance grows increasingly important. Ensuring that medical AI works, works where it’s used, and works for the patient in the moment is a challenging, multifaceted task. Some of this governance can be centralized—in review by FDA or by national accreditation labs, for instance. Some must be local, performed by the hospital or health system about to use the product in their own, unique environment. But a large amount of governance is left to the individual provider in the room, the human in the loop who presumably knows …

Do Specialized Medical Llms Demand A Radically New Approach Under The Eu's Medical Device Regulation, Hannah Louise Smith, W. Nicholson Price Ii

Articles

We examine the arguments made by Onitiu and colleagues concerning the need to adopt a “backward-walking logic” to manage the risks arising from the use of Large Language Models (LLMs) adapted for a medical purpose. We examine what lessons can be learned from existing multi-use technologies and applied to specialized LLMs, notwithstanding their novelty, and explore the appropriate respective roles of device providers and regulators within the ecosystem of technological oversight.

Predicting Superconducting Critical Temperature From Composition-Derived Features: A Transparent Linear And Regularized Regression Study, Md Ahiduzzaman

Data Science and Data Mining

We study prediction of superconducting critical temperature (Tc) from 81 composition-derived descriptors across 21,263 materials. To keep the analysis transparent and repro- ducible, we focus on linear models: Ordinary Least Squares (OLS), Ridge, Lasso, and Elastic Net (ENet). All models share a single evaluation protocol (5-fold cross-validation with standardized inputs) and are compared on RMSE, MAE, and R2. On this feature set, OLS attains the best cross-validated performance (RMSE = 17.6 K, MAE = 13.3 K , R2 = 0.735), with Lasso/ENet essentially tied next (RMSE ≈ 17.7 K , R2 ≈ 0.734); Ridge underperforms (RMSE = 18.9 K , …

Comparative Analysis Of Lasso, Ridge, And Elastic Net For Variable Selection In High-Dimensional Maize Data, Md Ahiduzzaman

Data Science and Data Mining

In high-dimensional genomic data analysis, traditional linear regression techniques often struggle due to the presence of a large number of predictor variables relative to observations. Penalized regression methods such as LASSO, Ridge, and Elastic Net have emerged as effective solutions by imposing regularization, which helps in managing multicollinearity and enhancing prediction accuracy. This study applies these techniques to the Maize dataset to model the time to male flowering, selecting relevant genetic markers as predictors. Our findings suggest that Elastic Net is particularly effective for high-dimensional data with correlated variables, achieving a balance between prediction accuracy and variable selection. The results …

Handwritten Digit Recognition Using Machine Learning Classifiers, Md Ahiduzzaman

Data Science and Data Mining

This project explores and compares the performance of various machine learning classifiers for handwritten digit recognition using the MNIST dataset. The classifiers include Logistic Regression, k-Nearest Neighbors, and Convolutional Neural Networks. Each classifier is evaluated based on accuracy, precision, recall, F1-score, and confusion matrix analysis.

Homomorphically Encrypted Faceted Values, Tanmay Singal

Master's Projects

Faceted values prevent the implicit flow of sensitive information by controlling the visibility of program data. They achieve this by maintaining two facets for each variable: a public facet, which is observable, and a private facet, which remains hidden. Although this method secures the flow of sensitive data, it can be leaked if the server storing the faceted values is compromised. While faceted values may be encrypted on the server, doing so would necessitate that the private facets be briefly decrypted during execution to allow arithmetic operations to be performed on them, creating an attack vector for information to be …

Retrieval-Augmented Generation (Rag) Chatbots: A Comparative Study Of Claude, Gpt-4o, Deepseek, And Llama, Kalindi Vijesh Parekh

Master's Projects

The use of Retrieval-augmented generation (RAG) in chatbot platforms has transformed academic spaces by significantly improving information accessibility. RAG has become a viable approach to upgrading Large Language Models (LLMs) with external knowledge access in real time. With the growing availability of advanced LLMs such as GPT, DeepSeek, Claude, Gemini, and Llama, there is a growing need to compare RAG systems based on different LLMs. This study compares the responses of four different RAG chatbots using popular LLMs against a uniquely designed evaluation dataset. Specifically, the study compares the responses and performance of closed-source (GPT-4o and Claude) and open-source models …

Augmenting Missing Sensor Data For Robust Human Activity Recognition, Suryakangeyan Kandasamy Gowdaman

Master's Projects

Applications of ubiquitous computing, including health monitoring, sports analytics, and ambient-assisted living, rely on Human Activity Recognition (HAR) using wearable sensors. However, model robustness is challenged by missing sensor values, class imbalance, inter-subject variability, and temporal noise. This work proposes a complete HAR pipeline that addresses these challenges through sampling, time-series augmentation, dynamic feature handling, and GAN-PCA-based imputation. Built on the DeepSense architecture, the model integrates convolutional feature extraction with bi-GRUs for temporal modeling. The system is evaluated using 5-fold cross-validation, subject-aware holdout, and LOSEO strategies on the Opportunity dataset. Results demonstrate consistent accuracy across folds and strong generalization to …

Phishing Detection Using Continual Learning And Large Language Models, Gopi Prajeev Battula

Master's Projects

Adaptive phishing detection remains crucial as the nature of cyber-attacks changes over time, which renders static models obsolete. This project extends phishing detection through the implementation of continual learning approaches, namely Elastic Weight Consolidation (EWC) and Learning Without Forgetting (LWF) with RoBERTa, a Large Language Model (LLM) and compares the results of these approaches against GPT-4o-mini, another LLM. Our approach begins with fine-tuning RoBERTa on multiple phishing datasets to establish an effective baseline. EWC is then implemented to preserve vital model parameters based on their importance measured by the Fisher Information Matrix, while LWF uses knowledge distillation to retain prior …

Mycelia: Cross-Chain Data Oracle Using Frost Signatures, Bala Komatireddy

Master's Projects

The interoperability of heterogeneous blockchain networks is the basis for the widespread application of blockchains in various fields. Cross-chain data oracles play a significant role in enabling distributed applications to exchange data and assets across different blockchains, thereby greatly enriching and expanding the application scenarios and use of blockchains. With the continuous advancement of blockchain technology, more and more researchers and industry participants have begun to focus on developing cross-chain data oracles. Current cross-chain data oracles face issues with trust, as they rely on centralized intermediaries or limited validator networks, increasing the risk of manipulation or single points of failure. …

On The Adversarial Robustness Of Quantized Neural Networks Against Common Adversaries In Time-Series Forecasting, Maanak Arora

Master's Projects

Real-world edge applications now use modern machine learning models which require both resource efficiency and robustness against adversarial threats. Deep neural networks which include time series forecasting models still face risks from adversarial perturbations while quantization techniques used for memory and compute efficiency create unpredictable robustness challenges. This project investigates the adversarial resistance of Long Short-Term Memory (LSTM) models after applying post-training quantization at three different precision levels: 16-bit floating point (FP16), 8-bit integer (INT8) and custom 4-bit quantization. The Jena Climate dataset serves as our main benchmark for training a fullprecision LSTM model followed by multiple quantization strategies which …

Rul Estimation Of N-Cmapss Turbofan Engines Using Deep Learning With Customized Penalty And Expanded Sensors, Prathmesh Pethkar

Master's Projects

Accurate prediction of Remaining Useful Life (RUL) for aircraft engines is important to enhance maintenance efficiency and flight safety. For this project, a solution to RUL prediction on NASA's N-CMAPSS data set, mimicking realistic engine degradation under simulated full-flight scenarios, is being proposed. For addressing the high-dimensional noisy sensor data challenge, a new feature engineering pipeline was utilized. Models trained on healthy data predict normal sensor behavior, and the discrepancy between these predictions—referred to as residual features—is a measure of degradation. To handle the size and computational demands of the dataset, training was conducted on Google Cloud Platform using GPU-supported …

Physiotrack: A Gamified Physiotherapy System, Pranavi Chaturvedula

Master's Projects

Traditional physiotherapy methods tend to be non-interactive and provide little to no personalized instruction, even though physiotherapy is critical to stroke recovery. This thesis explores a fully adaptive, sensor-based, feedback architecture intended for stroke patients which remotely supervises movement and personalizes exercises enabled by multimodal sensors. The system uses filtering and windowed segmentation of accelerometer and skeletal data to compute features like jerk, speed, and joint movement angular range. A game engine applies accelerometer and skeletal features together with optimized, lightweight ML models to drive adaptive feedback, scoring, and difficulty adjustment. The architecture supports responsive continuous sensor streaming within the …

Energy Considerations For Large Pre-Trained Neural Networks, Leo Mei

Master's Projects

In recent years, neural network models have achieved phenomenal performance due to the increasing parameters and complexity of model architectures. However, these advancements come with high environmental costs as they require massive computational resources and consume substantial amounts of electricity, leading to high carbon emissions. Previous studies have demonstrated that substantial redundancies exist in large pre-trained models, and reducing these redundancies through compression would not compromise model performance. While these studies focused on retaining comparable model performance, the direct impact of compression on energy consumption when training models appears to have received little attention. By quantifying the energy usage associated …

Optimization Of Permutation Flowshop Scheduling Using An Island Genetic Algorithm For Makespan Minimization, Sahil Salim

Master's Projects

The Permutation Flowshop Scheduling Problem is a well-known NP-hard combinatorial optimization problem that involves the sequencing of n jobs across m machines in the same order to minimize the total makespan value. This project proposes a Heterogeneous Island Genetic Algorithm framework (HIGA). Each island represents a group of solutions that evolve in parallel using different initialization heuristics, crossover and mutation operators, and adaptive parameters. A dynamic, stagnation-based migration strategy is proposed to maintain targeted communication between the islands. The proposed HIGA approach was compared against the basic Standard Genetic Algorithm (SGA) and a more advanced Niche-based Genetic Algorithm (NEH-NGA) on …

Enhancing Recommender Systems Using Graph Neural Networks, Long Short-Term Memory And Textual Embeddings, Tianxiang Chen

Master's Projects

Recommender systems surround us. They shape what we watch, how we buy, and even what our future might look like next. The Amazon Review Dataset and Movielens, those two datasets will help this project explore how to improve recommender systems through the user’s preferences. Two methods were combined: sequence-based models and graph-based models. Sequence models, such as LSTMs and Transformers, look at the order of user actions to find patterns by their sequence. On the other hand, Graphbased models focus on relationships between users, items, and their attributes. Textual embeddings added depth and context. Both methods offer something special, according …

Multimodal Deception Detection Via Audio-Text Fusion With Deep Learning And Asr, Xiangyi Li

Master's Projects

Emotion detection plays a crucial role in human-computer interaction, enabling machines to recognize and respond appropriately to human emotional states. This project explores a two-stage approach to emotion detection using multimodal data, first predicting dimensional values (Arousal, Valence, Dominance) from textual and audio inputs, then mapping these representations to discrete emotion categories. We compare this approach with direct categorical classification using transformer-based language models like BERT, RoBERTa, and DeBERTa for text processing, alongside various audio feature extraction methods, including MFCCs and spectrograms. Using the IEMOCAP dataset, we evaluate both approaches across text-only, audio-only, and multimodal configurations. Our findings reveal that …

Synthetic Malware Generation Using Generative Ai, Phanidhar Sai Sravan Chandana

Master's Projects

Malware grows in numbers and complexity, evading conventional signature-and anomaly-based defenses and worsening extreme data sparsity and class imbalance problems for machine learning based detection. Generative models, specifically GANs conditioned on contextual embeddings like BERT have proved effective augmenting training corpora to improve classifier accuracy, but these approaches have largely produced family-specific samples In this paper, we propose a generalized augmentation scheme for generating robust malware embeddings for various families. We begin by extracting opcode sequences from 13 malware families and encoding them into three embedding methods: CountVectorizer, TF-IDF, and BERT’s ‘[CLS]‘ vectors. We therefore train standard GANs and Wasserstein …

Performance Comparison Of Machine Learning Across Metal, Cuda, And Neuromorphic Frameworks, Ryan Saini

Master's Projects

Machine learning’s computational demands necessitate optimal performance and utilization. This research compares Apple Silicon M3 Pro with MPS, NVIDIA RTX 3070 GPU with CUDA, and neuromorphic computing for machine learning methods. We provide a cross-platform and cross-architecture performance analysis of machine learning methods to identify optimal configurations for training and inference scenarios. On traditional neural networks, Apple Silicon with MPS delivers superior energy efficiency at the cost of longer processing times for training and inference. NVIDIA with CUDA offers faster computation in training and inference at higher energy costs. Convolutional spiking neural networks perform competitively on event-based data, particularly on …

Malware Opcode Embedding And Quality Assessment Of Generative Sample Embeddings, Atishay Jain

Master's Projects

Malware is software used to damage and disrupt computer systems with the intent to cause damage to the victim. Malware detection and classification into malware families is a crucial problem for cybersecurity researchers. One of the major bottlenecks in improving these systems is the shortage of good quality labeled malware data, especially for malware families with scarce samples. Researchers have utilized generative models to generate malware data to address this issue. Malware embeddings encode patterns within a malware file, which can be used to detect and classify malware. Recently, encouraging results have been obtained in generating malware embeddings using generative …

Gen Ai For Malicious Network Data, Aneesh Maturu

Master's Projects

Though botnet attacks are on the rise, they also have become sophisticated and difficult to detect. Such a rising threat demands more and more sophisticated cybersecurity that leverages machine learning technology. Nevertheless, one of the biggest bottlenecks remains the unavailability of large and well-balanced datasets, particularly for malicious traffic, which hampers the efficacy of detection models. In an attempt to address this issue, our research utilizes Generative Adversarial Networks (GANs) to produce synthetic samples of botnet traffic from the CTU-13 dataset. While the majority of generative models have been targeting image data, we use GANs for a new application: generating …