Maryland Shared Open Access Repository

MD-SOAR is a shared digital repository platform for twelve colleges and universities in Maryland. It is currently funded by the University System of Maryland and Affiliated Institutions (USMAI) Library Consortium (usmai.org) and other participating partner institutions. MD-SOAR is jointly governed by all participating libraries, who have agreed to share policies and practices that are necessary and appropriate for the shared platform. Within this broad framework, each library provides customized repository services and collections that meet local institutional needs. Please follow the links below to learn more about each library's repository services and collections.

Browse

Submit

Submit item to MD-SOAR

Institutions in MD-SOAR

Select a community to browse its collections.

Bowie State University

Frostburg State University

Goucher College

Hood College

Loyola Notre Dame Library

Morgan State University

Salisbury University

Stevenson University

St. Mary's College of Maryland

Towson University

University of Baltimore

University of Maryland, Baltimore County (UMBC)

University of Maryland Eastern Shore

Recent Submissions

Network Traffic Data Preprocessing: An Agentic AI Framework
(2025-11-14) MacDowell, Christopher; Jim, Carol; Salem, Ahmed; Hood College Computer Science and Information Technology; Information Technology
The application of machine learning (ML) to power modern Intrusion Detection Systems (IDS) is critically dependent on the quality of network traffic data. However, the data preprocessing stage—which transforms complex, "dirty" raw data into a clean, ML-ready format—remains a time-consuming, manual bottleneck that relies heavily on domain expertise. This research addresses this gap by proposing and validating a novel, holistic framework using agentic Generative AI (GenAI) to fully automate the end-to- end data preprocessing pipeline. The core of this framework is a sophisticated, multi-step "prompt-chain" that compels a Large Language Model (LLM) to act as an expert data scientist. This agentic process forces the AI to move beyond simple code generation; it must first perform rigorous exploratory data analysis, construct a feature selection plan, design a methodologically sound preprocessing strategy (preventing data leakage and handling class imbalance), generate the code, and validate its own work through iterative debugging and "hostile code" reviews. This three-phase agentic framework was experimentally validated by comparing the performance of three state-of-the-art GenAI reasoning models (DeepSeek V3, Google Gemini 2.5 Pro, and OpenAI GPT-5) against a human-derived manual baseline. The evaluation was conducted on three distinct network traffic datasets of increasing complexity: the curated UNSW-NB15 (as a control), the raw IDSIoT2024, and the highly complex, "dirty" VNFCYBERDATA. The resulting data artifacts were evaluated using four standard ML classifiers: K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), and Gaussian Naïve Bayes (GNB). The results comprehensively validate the hypothesis. While the framework's application on the already-curated UNSW-NB15 dataset led to "over-cleaning" and a slight performance degradation, its performance on the two raw datasets was definitively superior to the manual baseline. The GenAI framework consistently and significantly outperformed the manual method on the IDSIoT2024 and VNFCYBERDATA datasets. Notably, the GenAI-processed data enabled sensitive classifiers like GNB to function, whereas the manual baseline caused them to fail catastrophically. Furthermore, the framework proved definitively superior in preparing the data for the critical task of minority class (rare attack) detection, where the manual baseline failed. This research demonstrates that a prompt-chain-driven GenAI framework is not merely a viable alternative but a more robust, comprehensive, and powerful method than traditional manual preprocessing for raw, real-world network traffic data.
FRACTAL MAP GENERATORS: DEEP STRUCTURES FOR MULTI-SCALE TILE MAPS
(2025-11-14) Curran, Matthew J.; Li, Jiang; Hood College Computer Science and Information Technology; Computer Science
The evolution from flat square-tile games to flat hex-tile games was an enormous step forward for computer gaming. Transitioning to flat maps with hierarchical hidden structure and/or to deep maps with multi-scalar surface characteristics could be equally significant. Fractal map generators provide a procedural way to produce both. This paper presents the key algorithms for the challenging problem of neighbor-finding in hierarchical coordinate systems. Code and examples are provided in a sequence of increasing difficulty, for Fractal Map Generators with branching-factors (aperture) of 2, 3, 4, 9, and 7 (in that order). This project demonstrates that the rotational drift for fractal hexagonal tiling at aperture seven is 1/3 radians (~ 19.09859 degrees). High resolution fractal hex maps can be generated from low resolution hand-crafted maps, allowing for the combination of recognizable features at the macro scale, and re-playability on the micro scale. Potential multi-scalar game play is built into a single tree data structure. High-interest areas can be represented in unlimited detail, while low-interest areas stay at a lower level of detail, minimizing computational demands. When applied at the interaction level, multi-scalar tiles may improve the UX by enhancing focus on areas of higher relative importance. Key Words Fractal Map, Map Generator, Iterated Function System, Region-of-Interest (ROI) rendering, foveation, multi-resolution tiling, multi-scale FEM, replayability, GIS and games, quadtree, bi-tree, tri-tree, nine-tree, hex-tree, Level-of-Detail (LOD) Management
EQUILIBRIUM: SEEKING BALANCE IN GROWTH AND DECAY THROUGH CLAY
(n/a, 2025) Nachlas, Samantha; Kormeluk, Natalia; Graduate School; M.F.A in Ceramics Art
For millennia, the observation and understanding of the natural world has served as a meditative tool to find spiritual balance. This study uses sculpted clay forms and repetitive making processes as a case study on the process of finding balance to conflicting and disparate opposites like growth and decay in nature or control and chaos. This study outlines a number of ways humans seek balance. It also addresses the perceived control on these balances. Each sculpture in the exhibition–"Equilibrium”–is dedicated to a particular aspect in nature found within the context of growth and decay of plants. The need for balance and control is addressed by psychologists, educators and artists, arguing that the balance is not found in between two extremes but instead in the knowledge of the coexistence of perceived extremes in tandem.
Aerial Insect Biodiversity Responses to Prescribed Fire in an Eastern Grassland Habitat
(2025-11-11) Radin, Allison Qing; Landsman, Andrew; Annis, Eric; Hood College Biology; Hood College Biomedical and Environmental Science
Grasslands in the Eastern United States are a biodiverse, but quickly vanishing, habitat type. Public land managers are beginning to incorporate prescribed fire into these fire-adapted systems to achieve cultural and natural resource conservation goals. While the effects of fire on plants are more widely documented, knowledge regarding the effects of fire on insect communities remains sparse. Following a prescribed burn in western Maryland, USA, no changes in community assemblage, species richness, or species diversity were found, but a significant decline in insect abundance was found. Insect species richness and abundance followed common growing season trends, peaking in mid-summer. Although these results follow general trends supported by global meta-analysis of insect community response to fire, the site and habitat specific responses of taxa make it difficult for public land managers to make species-specific management decisions without further detailed research.
Reflections of Her: Responding to Objectification of Women through Music, Art, and Identity
(2025-11-10) Marshall, Sarah; Hoffman, Karen; Hood College Arts and Humanities; Humanities
This introductory essay argues that this objectification of women is not a relic of the past, but an evolving system that adapts to new cultural contexts, while perpetually reinforcing long-standing inequities. At the same time, this introduction will also reveal the complexity and ambiguity inherent in the concept of objectification, making it hard to arrive at a singular definition and, therefore, underscoring the need for its critical interrogation. This essay will also explore the consequences of objectifying women—taking into consideration the limitations of efforts to disrupt this cycle—while also exploring the possibilities for resistance, redefinition, and the need to center women’s voices in cultural narratives.