Computer Sciences Commons^™

Research On Improving Design Efficiency Of Coaxial Magnetic Gear Based On Linear Model, Shuguang Zhao, Ce Chen, Xiaochang Xie, Fuping Li, Jin Han

Journal of System Simulation

Abstract: To address the issues of large model computation load and cumbersome magnetization direction setting during the simulation design of coaxial magnetic field modulation type magnetic gears, a simplified design method is proposed, which uses a linear model to replace the original conventional circular ring model. Based on the periodicity of the structure and magnetic field of each part of the magnetic gear, the modeling work is simplified and the computational load of the simulation analysis is reduced. The results show that compared with the circular ring structure, the number of magnetization coordinate system settings for the linear structure is …

Evaluating The Evaluation Matrices: Integrating Spatial Assessment In Geospatial Ai Model Training And Evaluation, Fangzheng Lyu

I-GUIDE Forum

This paper examines the limitations of current evaluation metrics in GeoAI. Through two case studies on deep learning models—a building detection classification problem and a remote sensing image fusion regression problem—this paper demonstrates how traditional statistical evaluation matrices alone can be misleading in geospatial problems. The findings indicate that traditional metrics (e.g., RMSE, MAE) used in current GeoAI models can have difficulty capturing the spatial dimensions inherent to geospatial problems. This paper suggests that the model evaluation process in GeoAI should move beyond traditional evaluation matrices by integrating spatial thinking throughout the modeling pipeline—not only incorporating spatial accuracy in model …

Expanding Access To Cybergis-Compute Through Support For Heterogeneous Workflows, Alexander C. Michels, Ian Zhang, Anand Padmanabhan, John Speaks, Rebecca Vandewalle, Shaowen Wang

I-GUIDE Forum

CyberGIS-Compute is a geospatial middleware tool designed to lower technical barriers to High-Performance Computing (HPC) resources. It provides end-users with a Graphical User Interface (GUI) for submitting models to HPC and allows model developers to contribute their workflows by adding a manifest to their repositories. However, the simplification of the user interface and streamlining of model contribution have unintentionally limited the scope of models that could be run on CyberGIS-Compute. In this paper, we discuss recent developments to the CyberGIS-Compute project that are aimed at supporting a wider variety of workflows including performance enhancements, supporting additional configuration options for jobs, …

Diversifying Cybersecurity: Evaluation Of An Internet Of Things (Iot)-Based Cybersecurity Training Course Designed To Bridge The Diversity Gap, Maureen Namukasa, Bhoomin B. Chauhan, Carlie Swords, Curtice Gough, Weronika Dymanus, Catherine Diresta, John Vitali, Vivek Sharma, T J. Oconnor, Meredith Carroll

Aeronautics Faculty Publications

This study aimed to evaluate the effectiveness of an eight-module Cybersecurity course at increasing the learning outcomes of middle and high school students with little to no experience, including underrepresented minorities (URMs) in Cybersecurity. Twice we administered and evaluated the Cybersecurity course, which included hands-on IoT-based activities, utilizing collaborative learning, scaffolding, and representation-based learning strategies. Using a quasi-experimental, within-subjects, repeated measures design, each participant experienced a pretest, the course, and a post-test to evaluate the impact on learners’ self-efficacy, interest, and knowledge. The results revealed that (1) at pre-test, female (p = .001) and in one course administration minority …

Texture Classification Through Deep Residual Networks And Feature Interpretability, Ankit Kumar

Master’s Dissertations

Texture classification plays a critical role in various real-world and industrial applications such as material recognition in manufacturing, medical image diagnostics, surface defect detection, and agricultural monitoring. The ability to distinguish textures reliably enables automation and enhances the precision of intelligent systems. Traditional methods like Local Binary Patterns (LBP), Gabor filters, and wavelet-based descriptors have been used extensively for texture analysis. While these techniques are effective under controlled conditions, they suffer from limited robustness to changes in illumination, scale, and viewpoint. Moreover, handcrafted features often fail to capture the intricate texture structures present in real-world surfaces. The KTH-TIPS2a dataset introduces …

Topic Shift Detection And Triggering In Natural Dialogue Systems: A Lightweight Approach, Rohith Perumandla

College of Computing and Digital Media Dissertations

This research address a key challenge in dialogue system: enabling the proactive, human-like shifting using lightweight approaching using MobileBERT (~25M) model was proposed and fine-tuned for topic shift detection, augmented with liguistic featuers for for topic trigger detection. Despite its smaller size (~25M parameters), the MobileBERT-based system achieved competitive results (F1 = 74.16%,) compared to the much larger XLNet model (~110M parameters, F1 = 79.95%), while offering greater efficiency. The topic trigger module, combining MobileBERT with linguistic features, further demonstrated effective performance (F1 = 71.61%).

A Systematic Evaluation Of Threaded Internode Communication In Hpc, William Pepper Marts

Computer Science ETDs

High Performance Computing (HPC) applications increasingly rely on both process and thread-level parallelism to maximize performance across complex, multi-node systems. However, conventional bulk synchronous communication strategies often leave both compute and network resources underutilized due to synchronization delays. This dissertation systematically evaluates the potential of fine-grained, threaded inter-node communication as a strategy for reducing these inefficiencies. To this end, I design and develop two tools: the MiniMod modular application framework and the Configurable Messaging Benchmark (CMB), which together enable empirical, reproducible assessment of communication performance across varying application behaviors, threading models, and communication granularities. Through experiments across multiple systems and …

Implications Of Neural Compression To Scientific Images, João Phillipe Cardenuto, Joshua Krinsky, Lucas Nogueira, Aparna Bharati, Daniel Moreira

Computer Science: Faculty Publications and Other Works

While neural compression has the potential to revolutionize image compression, recent studies have emphasized its ability to introduce subtle artifacts that could alter the image content. Concerned about the impact of such modifications on scientific images, this work explores the potential effects of neural compression on these images, focusing on two critical aspects: semantic understanding and forensic integrity. We use scientific image datasets to assess the performance of neural compression techniques on Visual Question Answering (VQA) and copy-move forgery detection tasks. Our findings indicate that the subtle changes introduced by neural ] compression do not significantly degrade the performance of …

Hierarchy Viz: A Visual Analytics Framework For Visualizing Hierarchical Data Using Machine Learning, Vinay Kumar Uppalapati

Theses and Dissertations

Automated visualization systems aim to generate visualizations directly from raw data with minimal user inputs. However, while existing systems focus on data visualizations mainly using line charts and scatter plots to explore the data patterns, they struggle with hierarchical data representation where data relationship is essential. Hierarchical visualization, crucial for understanding multi-level relationships, typically requires users to manually define hierarchies and have expertise in visualization tools to create meaningful representations. This makes the process complex, time-consuming, and reliant on domain knowledge. To address this, we propose HierarchyViz, an automated system that detects multiple hierarchies in raw datasets and generates intuitive …

Exploring Character-Level Attacks On Neural Ranking Models, Surjyanee Halder

Master’s Dissertations

Neural ranking models (NRMs) have achieved state-of-the-art performance in information retrieval, yet they remain highly susceptible to subtle adversarial inputs such as character-level typos. This project explores the robustness of such systems by introducing a reinforcement learning (RL)-based query perturbation framework. RL agents—PPO, DQN, and A2C—were trained to minimally modify user queries (e.g., through character deletions or swaps) with the goal of significantly altering the resulting document rankings, as measured by Kendall’s Tau. Experiments were conducted on the TREC DL 2019 and 2020 benchmarks using two different neural rankers: Mini LM and a fine-tuned Character BERT model. The perturbation attacks …

Explaining Query Expansion Algorithms, Aditya Dutta

Master’s Dissertations

Query Expansion (QE) techniques aim to mitigate vocabulary mismatch in Information Retrieval by augmenting user queries with related terms. However, their effectiveness varies across queries. This work investigates the explainability of QE by leveraging the concept of an Ideal Expanded Query (IEQ): a hypothetical query yielding near-perfect retrieval performance, measured via Average Precision (AP). We hypothesize that the closer an Expanded Query (EQ) variant is to the IEQ, the higher its AP. Our approach consists of three major components: (i) generating an IEQ, (ii) measuring the similarity between an EQ and an IEQ, and (iii) computing the correlation between the …

How’S It Growing? Tools For Observing Snow And Sea Ice In A Changing Arctic Ocean, Ian Alexander Raphael

Dartmouth College Ph.D Dissertations

September Arctic sea ice extent has diminished by roughly 50% in the 45 years since satellite observations began. The Arctic Ocean may experience ice-free summers within the next decade, with implications for habitat, resource extraction, geopolitics, and local and global climate change. To predict how Arctic sea ice will change in the future, we need to understand its behavior in the present. In situ sea ice mass balance measurements (snow accumulation, ice growth, snow and ice surface melt, and bottom melt) are essential for studying the processes driving rapid changes in the ice pack, and for validating remote sensing measurements …

Revitalization Of Endangered Languages With Ai, Ivory Yang

Dartmouth College Master’s Theses

The preservation and revitalization of endangered languages, particularly those with minimal digital presence, presents significant challenges for computational linguistics. This thesis addresses these challenges by proposing novel methods for language identification and data generation, focusing on underrepresented Indigenous languages, specifically Nüshu, Native American and Native Alaskan languages.

In the first study, a COLING 2025 paper, we present NüshuRescue, an AI-driven framework designed to facilitate the preservation of Nüshu, an endangered script used exclusively by Yao women in China. Using minimal seed data, we demonstrate how GPT-4-Turbo can generate new translations, expanding a publicly available Nüshu-Chinese corpus, achieving 48.69% accuracy in …

Deep Neural Networks For Particle Identification In Simulated Proton-Proton Collisions At Lhc And Rhic, Omar Mazhar Khalaf

Theses and Dissertations

Particle identification is an essential part of experimental high-energy physics, which allows the study of the most fundamental constituents of matter. This thesis explores the use of deep neural networks for identifying particles in simulated proton-proton collisions at the Large Hadron Collider (LHC) and the Relativistic Heavy Ion Collider (RHIC). The deep neural networks were trained on LHC datasets which have various momentum ranges including regions of high transverse momentum above 3 GeV/c. The key findings of thesis include achieving an accuracy of 99.99%, 98.3%, and 90.14% for 3-5 pt, 5-7 pt and above 7 pt regions respectively for the …

Cutting-Edge Methods For Analyzing Student Behavior In Educational Settings: A Review, Shatha Talib Rashid, Hasanen S. Abdullah

Journal of Soft Computing and Computer Applications

The ability to predict students' performance in educational settings like schools and universities is crucial. A key objective of this effort is to increase academic outcomes and prevent dropout rates, among other benefits. Automating student activities, encouraged by information collected from any technology-based learning tool, has an important role in the process here. Those big quantities of information ought to be completely studied theoretically and processed for gaining worthy insights concerning a student's background as well as interacting with scientific missions, facilitating the development of advanced ways and algorithms to predict students' performance. The current study reviews several contemporary mechanisms …

Blockchain-Based Physical Election Votes Digitally Secure Transfer, Mohanad A. Mohammed, Hala B. Abdul Wahab

Journal of Soft Computing and Computer Applications

Responsibility for maintaining election transparency over time and ensuring democratic values intact is held by the Iraqi Independent High Electoral Commission (IHEC). However, transferring physical election votes from election centers is a critical duty, where many challenges appear regarding accountability and security measures. This study proposes a system that utilizes blockchain technology to solve any challenges or difficulties and ensure an effective and improved election process by providing its highest trustworthiness and legitimacy and ensuring a decentralized security process. This system offers unique blockchain characteristics such as immutability, decentralization, and transparency, providing an extra level of security to the data …

Modern Face Recgognition Systems: A Review Of Methods And Empirical Findings, Zahraa Naji Razoqi, Raheem Ogla, Abdul Monem S. Rahma

Journal of Soft Computing and Computer Applications

The face recognition system is a biometric technique that replaces traditional passwords and personal identification. This research is dedicated to presenting a study of some facial recognition systems. Since it is unlikely to replicate and is more stable over time, the domain of facial feature extraction has proven to be more effective in attaining exact facial recognition, which is important, especially in intelligent security surveillance systems. Face recognition systems encounter several challenges, primarily related to pose variations, illumination conditions, and occlusions such as hair, glasses, and so on. To address these challenges, enhance performance, and boost the accuracy and speed …

Arson Event Detection Using Yolov9, Ali Abbas Abbod, Matheel E. Abdulmunimb, Ismail A. Mageed

Journal of Soft Computing and Computer Applications

Detecting event anomalies is crucial for surveillance systems, as it enables the identification of occurrences in videos, both temporally and spatially. It can identify deviations from patterns without requiring human oversight by learning from past information to distinguish normal behavior and pinpoint irregularities. Early detection of arson fires is critical to mitigating damage, public safety, property, and the environment, as well as saving lives and aiding in law enforcement investigations. The objective of this study is to evaluate a system for detecting events using the You Only Look Once version 9 (YOLOv9) model in surveillance videos with a focus on …

Enhancing Cybersecurity Based On Blockchain Technology: A Systematic Review, Sarah Mohammed Shareef, Rehab Flaih Hassan

Journal of Soft Computing and Computer Applications

Cybersecurity is a crucial component of the security system that guards against unauthorized access to digital transactions. Blockchain is a decentralized ledger used to securely exchange digital currencies and conduct trades and transactions. Blockchain technology has led to significant changes in electronic transactions. The enormous potential is being exploited in many areas such as financial services, real estate, supply chain, and the Internet of Things. Despite being a security system, it has suffered from security threats to sensitive data. Phishing and 51% attacks can circumvent blockchain security, highlighting the need for thorough user education and awareness. Additionally, blockchains based on …

Predicting Earthquake Location Using Convolutional Neural Network-Attention Mechanism Approach, Mohammed A. Jaleel Shaneen, Suhad M. Kadhem

Journal of Soft Computing and Computer Applications

In seismically active areas, earthquake prediction is essential for minimizing potential damages and preserving lives. However, precise forecasts are complicated to achieve because of seismic events’ complex and unpredictable nature. The current study presents an advanced prediction approach to address such issues, combining Convolutional Neural Networks (CNNs) and Attention Mechanism (AM). The primary goal is to improve the accuracy of the earthquake predictions and the generalizability across various mainland Chinese regions. AM layer emphasizes significant features for improving the prediction performance, whereas CNNs are utilized to extract spatial features of seismic data. The efficiency and effectiveness of the proposed approach …

Machine Learning: Neural Networking With Relu And Optimization, Aidan Redmond Brownell

Undergraduate Theses, Capstones, and Recitals

At its core, learning is an algorithmic process: it begins with input data, undergoes a series of transformations or computations, and yields an output intended to solve a specific task. This output is then compared against a target or desired result, and the internal mechanisms are updated based on how well the output aligns with expectations. While this feedback-driven process occurs almost effortlessly in humans, it is a far more structured, deliberate, and computationally intensive undertaking for machines.

Enhancing Water Scarcity Resilience In Egypt Through Machine Learning-Driven Phenological Crop Mapping And Water Use Efficiency Analysis, Surendra Maharjan, Wenzhao Li, Shahryar Fazli, Aqil Tariq, Rejoice Thomas, Cyril Rakovski, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Agriculture forms the backbone of Egypt’s economy, with the Nile Valley and Delta serving as key production zones for crops like wheat, rice, and clover. However, the sector faces mounting pressure from water scarcity, as it depends almost entirely on the Nile for irrigation, making it necessary to map major crops for assessing Water Use Efficiency (WUE) and informing agricultural planning. In this study, we used machine learning (ML) techniques—specifically Support Vector Machine (SVM) to time-series phenological data and optical indices (Enhanced Vegetation Index (EVI), Bare Soil Index (BSI), Land Surface Water Index (LSWI), Normalized Difference Vegetation Index (NDVI), and …

Basic Theory And Implementations Of Quantum Error Correction, Derek Rodriguez

Undergraduate Theses, Capstones, and Recitals

The introduction of quantum computing has presented algorithmic solutions to computationally difficult challenges that are far more efficient than those of classical computers. These algorithms leverage the properties of quantum mechanics to manipulate the quantum properties of subatomic particles, requiring immense precision and stability. Current quantum hardware, however, is too noisy and introduces too many errors for these algorithms to be useful in practice, necessitating the use of error correction algorithms. This field survey seeks to introduce various principles of quantum mechanics relevant to quantum computing and quantum error correction (QEC), detail the implementation and motivations of a basic QEC …

Integrating Iota Tangle And Artificial Intelligence (Ai) In Iot Network For Network Anomaly Detection, Saida Hafsa Rafique

Thesis/ Dissertation Defenses

The Internet of Things (IoT) ecosystem has advanced with the advent of Distributed Ledger Technology (DLT) and Artificial Intelligence (AI). Individually, DLT and AI have been explored for enhancement of data management, security, integrity and efficiency of IoT systems. In this thesis, the combined use to apply DLT and AI for network anomaly detection in IoT systems is considered. A framework is proposed to integrate IOTA Tangle, a DLT architecture with Machine Learning (ML)- Random Forest, Decision Trees, and LightGBM, to detect network anomalies in IoT systems. The proposed framework processes network traffic data from UNSW-NB15 dataset and categorizes it …

Multi-Label Classification Of Acoustic And Electronic Drum Sounds Using Machine Learning, Sean Perman

Electronic Theses and Dissertations

This paper presents a system for multi-class classification of drum sounds using audio signal processing and machine learning techniques. The project utilizes a diverse dataset of both acoustic and electronic drum samples and extracts ten distinct audio features to capture the timbral and temporal characteristics of each sound. The methodology includes signal preprocessing, feature extraction, and the application of supervised classification algorithms to distinguish between multiple drum classes. Experimental evaluations demonstrate that the selected features significantly enhance classification accuracy across a varied dataset. These findings underscore the effectiveness of combining traditional audio processing with modern machine learning, offering promising applications …

Enhancing Multi-Step Stock Price Forecasting With Social Media Sentiment And Engagement Metrics, Damilare Olaniyan

Electronic Theses and Dissertations

This thesis investigates whether social media sentiment can improve the accuracy of stock price prediction beyond traditional historical data. While financial markets have long relied on structured numerical indicators, the growing influence of public discourse on platforms like Twitter has introduced new opportunities for extracting market-relevant signals from unstructured text. The study focuses on four major technology firms and combines sentiment features derived from Twitter with historical stock prices in a hybrid machine learning framework. Engagement-weighted sentiment, linguistic complexity, and polarity intensity were extracted using natural language processing techniques and incorporated into classification and regression models. Results show that including …

Collaborative Federated Learning For Robots In Heterogeneous Environments, Karlan Schneider

Electronic Theses and Dissertations

This research investigates the performance of Federated Averaging (FedAvg) in simulated Federated Learning (FL) scenarios with varying degrees of environmental heterogeneity among robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset of agents encountered an unfamiliar environment. The results demonstrate that while FedAvg exhibits resilience to the introduction of new environmental data, it struggles to ensure both convergence and fairness in heterogeneous settings. Specifically, …

Optimizing Option Market Clearing, Juan Andrés Malaver Alvarado

Electronic Theses and Dissertations

Modern options markets clear each strike in isolation, leaving cross-strike arbitrage unexploited. This thesis applies a payoff-dominant clearing mechanism to realized trades—roughly 2 000 Cboe VIX option executions from June–November 2016—after classifying each trade’s side and bundling by expiration. Three optimization formulations are tested: a fractional linear program (LP), a mixed-integer LP, and a pure integer program. On a 10-core laptop every bundle solves in < 0.5 s. The LP captures the greatest surplus, yet the integer models recover nearly as much while filling whole contracts and holding only modest margin. Results reveal persistent, albeit small, inefficiencies in executed trades and demonstrate that an integral cross-strike auction could operate in real time. The accompanying C/Gurobi code is modular and readily extendable to early-exercise options. Trade-level evidence thus supports redesigning exchange clearing to consider the complete option book.

Object-Based Image Analysis And Artificial Intelligence Identification Of Anthropogenic Disturbance On Lesser Prairie Chicken Habitat In Cheyenne County, Colorado, Tara Hoelzer

Geography and the Environment: Graduate Student Capstones

Renewable energy projects often require extensive landcover for their operations. When one of these projects encroaches into territory of threatened species, such as Lesser Prairie Chickens, an analysis of habitat suitability and human disturbance is required to proceed. Traditionally, this involved manually reviewing aerial imagery within a 6-mile radius, digitizing features, and interpreting them using a human technician—an approach that was time-consuming and prone to human error. By using pretrained AI models within Model Builder™, the identification of roads and structures was automated, making the process faster and more consistent than manual visual analysis. As AI and technology continue to …

Degraded Document Binarisation, Miriyala Ajith

Master’s Dissertations

In this study, I explored degraded document binarization by reviewing two recent model frameworks and implementing their models using PyTorch. The first model is based on cGANs, specifically the DE-GAN [41] framework, which enhances degraded documents by restoring their quality prior to binarization. The second model employs vision transformers [40], inspired by the DocBinFormer architecture, which uses an autoencoder in both the encoder and decoder for effective binarization. Both models were evaluated on the ISI-Bengali dataset. Experimental results demonstrate that DE-GAN improved document quality by 4% compared to the degraded input, while the vision transformer model achieved a 14% improvement, …