Digital Commons Network^™

Seg-Swin: A Dual-Attention Transformer Model For Advanced Amd Classification And Lesion Detection Using Color Fundus Imaging, Niveen Nasr El-Den, Mohamed Elsharkawy, Ibrahim Saleh, Ali H. Mahmoud, Mohammed Ghazal, Ashraf Khalil, Ashraf Sewelam, Hani Mahdi, Ayman El-Baz

All Works

Age-related macular degeneration (AMD) is a prevalent retinal disorder in the elderly, often leading to significant vision impairment. The diagnosis of AMD is confirmed through various medical imaging modalities, with color fundus photography (CFP) being a primary tool. The detection and staging of AMD-severity depend on several factors, including the number and size of drusen, the presence of pigmentary changes, geographic atrophy, and neovascularization, all of which are identifiable through CFP. In this study, we introduce an innovative dual-vision transformer-based network designed to automatically detect AMD and classify its severity into either dry AMD or wet AMD using CFP. Early …

Climate Change Adaptation Through Economic Democracy, Shriraksha Mohan

Best Integrated Writing

Mohan investigates and combines three different areas of literature and social movements to discuss the problem of climate change and economic adaptation. The value of this work is that it can be used to communicate among three independent types of social movements and inquiries. This can strengthen and connect dispersed yet overlapping efforts in addressing work issues, resource utilization, economic governance and participation, and ecological problems economies face today.

Gc-074 Real-Time Object Detection, Rohit Malik

C-Day Computing Showcase

This project explores the implementation of real-time object detection using the You Only Look Once (YOLO) architecture. Leveraging its speed and accuracy, we developed a system capable of identifying and localizing multiple objects within live video streams. Our implementation focused on optimizing YOLO's performance for real-time applications, specifically addressing the trade-off between speed and accuracy. We employed a pre-trained YOLO model and fine-tuned it on a custom dataset tailored to specific object classes. This fine-tuning process aimed to enhance the model's ability to recognize objects in our target environment. The system was implemented using Python and the OpenCV library, enabling …

Uc-136 Foster Ai Interview And Biography Generation, Joshua Crawford, Katlin Lahr, Mikayla Haigh, Brittany Payne, Daria Morhun

C-Day Computing Showcase

This capstone project presents a proof of concept for a mobile and web-based application designed to streamline communication between foster caregivers and the Angels Among Us Pet Rescue team. The application addresses critical inefficiencies in generating pet biographies and coordinating photography efforts, which are essential components in increasing adoption rates. Leveraging cutting-edge technologies such as Twilio, Retell AI, and OpenAI, the app implements a bio generation workflow that conducts foster interviews via phone calls, transcribes responses using AI-powered voice-to-text, analyzes sentiment, and produces structured, engaging pet bios for platforms like Petfinder. Additionally, the system automates email workflows to coordinate photography …

Uc-023 Bathtub Racing Game, Sasha Melbourne, Sulaiman Bah, Damari Brown, Deylin Ealy, Adam Calo

C-Day Computing Showcase

The Virtual Bathtub Racing Game is a capstone project that uses an interactive 3D digital experience to preserve and modernize the long-standing bathtub racing tradition at Southern Polytechnic State University (SPSU). With real-world physics, adjustable features, and multiplayer capabilities, the Unity-developed game recreates the famous event where students raced imaginatively designed bathtub carts. Since stakeholder input influences the creation of tracks, sound profiles, and gameplay elements that replicate the original races, alumni involvement is crucial in determining the authenticity of the game. In order to provide a captivating user experience for both new players and past SPSU students, the project …

Uc-026 Pet Matchmaker, Victoria Davis, Colton Baldwin, Edward Sadler

C-Day Computing Showcase

Angel Among Us is a non-profit organization that saves animals from high-killing rate shelters in Georgia. Their goal is to find homes for homeless pets. To increase their efforts, they are developing a web-based application to help improve adoption processes. The goal is to increase adoption rates and be able to provide adopters with information about pets and overall reduce the number of pet returns. This will be accomplished by using adopters’ information and preferences from the web-based application to find long-term compatibility with their recommended pets. The objective is to create a web application interface that includes many core …

Uc-029 Graphbat: Subterranean Data Visualizer, Caroline Roberson, Abdalla Ugas, Nathan Karg, Hayden Harper

C-Day Computing Showcase

GraphBat is a desktop data visualization application designed for speleology and similar fields that bundles common graph types with a unique heatmap tool which few comparable apps provide. It was developed in Python and is intended as an open-source tool available for use and extension by the scientific community. The heatmaps offer two data interpolation methods—inverse distance weighting and linear interpolation—to visualize the spread of data across a space using a real-world map and sensor data relative to the space. GraphBat aims to expediate scientific analysis and facilitate the presentation of results across many fields of subterranean study.

Uc-046 Cat Classification Of 20 Distinct Breeds, Tabitha Washington, Ashley Nestor

C-Day Computing Showcase

Cat breed classification algorithms have been made time and time before due to cats being such a popular and beloved animal. As such, classification algorithms aim to identify their breeds for veterinary pursuits and wildlife tracking which necessitates accurate classification. Our classification algorithm identifies 20 different CFA-recognized pedigreed cat breeds utilizing TensorFlow with the MobileNetV3 Large model as the base for training. Our preliminary results over 25 initial epochs and 25 fine tuning epochs resulted in a model with a test accuracy of 65%. In the future, we plan to add more techniques to prevent overfitting and experimenting with a …

Uc-085 Berry And Carrot - A 2.5d Unity Platformer Game, Everett Joiner, Rin Egl, Carter Griffin, Kcyana Redmon

C-Day Computing Showcase

In Berry and Carrot, you play as two stuffed animals, a bear and a bunny, who are trying to escape from a claw machine that they have been trapped in for years. Each character has different strengths, and the player must use these skills strategically by switching between the two characters to solve puzzles themed around the inner workings of the claw machine featuring screws, springs, levers, and more.

Uc-130 Some Kind Of Tundra Escape, Tiffany Field, Patrynna Mensah, Tahjir Beene, Daniel Worrel

C-Day Computing Showcase

Some Kind of Tundra Escape is an action-adventure game where you play as a penguin trying to escape a vast, walled-in tundra. As you explore, you’ll rescue other penguins scattered throughout the area. Your goal is to gather all the penguins and escape together, but the journey is far from easy. The tundra is full of danger, including snowmen who ambush you and ice golems who patrol certain areas. You'll need to avoid these monsters and set traps to stay safe while rescuing your fellow penguins. As your group grows, so does the challenge—more penguins means more obstacles to overcome. …

Ur-018 Towards Bounding The Behavior Of Deep Neural Networks, Aidan Boyce

C-Day Computing Showcase

Recent advances in Artificial Intelligence (AI) have unlocked many new possibilities but have also brought with it many new challenges. While modern AI systems have been continuously exceeding expectations, our ability to interpret and understand their behavior lags behind. For example, an AI model trained to detect pneumonia from X-rays may fail in new hospitals because it learned to recognize hospital logos instead of medical patterns. Why do some succeed while others fail? Do they truly understand their tasks, or are they relying on patterns that may not always hold? To enumerate the most informative explanations of a neuron’s behavior, …

Leveraging Attention Mechanism To Unlock Gene And Protein Attributes, Ala Jararweh

Computer Science ETDs

Advancing personalized medicine depends on effectively integrating and interpreting the vast, heterogeneous landscape of biological data, from genomic sequences and transcriptomics to the insights embedded in scientific literature. Current machine learning models often focus on single data modalities, limiting their capacity to capture the multifaceted nature of biological systems. We address this gap by developing three attention-based machine-learning models integrating diverse data modalities. Firstly, DeepVul is a multi-task model that leverages cancer transcriptome data to predict genes critical for cancer survival and their corresponding drugs. Subsequently, LitGene refines gene representations by integrating textual information from the scientific literature. Finally, Protein2Text …

Preservation And Integrity Of Laboratory Solutions: Understanding The Impact Of Storage Practices On Chemical Stability And Experimental Accuracy, Azza Al Jahdhami

Honors Theses

Chemical storage methods represent a key matter ignored within labs, educational sites, workplaces, and even households. Many people, including various students and instructors within the chemistry field, are unaware of the proper methods for storing and disposing of common chemicals. This study aims to understand the effects of storage practices on chemical stability and experimental accuracy, dealing with the following questions: What kind of effects result from improper chemical disposal? How can improper storage affect the overall chemical effectiveness? Why is sink disposal of many solutions discouraged, and why is waste container disposal always necessary?

Through a literature review, this …

Development Of Isoscapes For Hong Kong Freshwater Streams As A Basis For Ecological Studies, Hon Tim Yip

Lingnan Theses (MPhil & PhD)

Applications of isoscapes in terrestrial and marine ecosystems have grown notably as a tool for studying animal movement. However, isoscapes are rarely used in freshwater ecosystem because current iterations of isoscapes commonly model baseline distributions of bulk stable isotope analysis (SIA) data, which may be inadequate for providing the necessary resolution for fine spatial scale stream environments. This issue could potentially be addressed using compound specific stable isotope analysis, a new method that measures the isotopic composition of individual compounds to provide more comprehensive information than bulk SIA. My study focuses on δ¹³C of essential amino acids (EAA-δ …

Using Trail Cameras To Detect Small Mammals, S. Nicole Frey

All Current Publications

Traditional methods to detect wildlife, including nuisance animals, are not often successful at detecting small mammals. By modifying the deployment of trail cameras, including using a portable tunnel, we have successfully developed a "small mammal method" that has been used to inventory animals at Zion National Park and Cedar Breaks National Monument. We provide details on how to modify simple trail camera deployment. We also provide detailed instructions on how to create a portable small mammal tunnel to improve species detection and identification.

Bird Observations Across Belmont's Campus, Jeremy T. Little, Josiah C. Mustaleski

SPARK Symposium Presentations

Over the course of 10 weeks our team collected data about bird sightings on Belmont’s campus. Sessions were recorded using eBird and Merlin Bird ID to correctly identify the birds and record accurate numbers. We conducted sessions at 3 different spots on campus, each with differing types and amounts of vegetation and human presence. These sessions were 20 minutes in duration and were conducted twice a week at each location. The data gathered was used to gain a better understanding of the bird trends and demographics on campus. This data was also used for WellCore events in conjunction with the …

Ahr Activation At The Air-Blood Barrier Alters Systemic Microrna Release After Inhalation Of Particulate Matter Containing Environmentally Persistent Free Radicals, Ankit Aryal, Ashlyn C. Harmon, Alexandra Noël, Qingzhao Yu, Kurt J. Varner, Tammy R. Dugas

School of Public Health Faculty Publications

Particulate matter containing environmentally persistent free radicals (EPFRs) is formed when organic pollutants are incompletely burned and adsorb to the surface of particles containing redox-active metals. Our prior studies showed that in mice, EPFR inhalation impaired vascular relaxation in a dose- and endothelium-dependent manner. We also observed that activation of the aryl hydrocarbon receptor (AhR) in the alveolar type-II (AT-II) cells that form the air-blood interface stimulates the release of systemic factors that promote endothelial dysfunction in vessels peripheral to the lung. AhR is a recognized regulator of microRNA (miRNA) biogenesis, and miRNA control diverse signaling pathways. We thus hypothesized …

Applications Of Clustered Regularly Interspaced Short Palindromic Repeats In Food Security And Nutraceuticals, Rukayat Abiodun Oyegoke, Jahswill Toluwanimi Osifade, Adenike Temidayo Oladiji

Al-Bahir

The CRISPR/Cas9 system is a revolutionary genome-editing tool that enables precise and inheritable modifications, transforming plant genetic engineering. Previous literature has indicated that, in agriculture, CRISPR has improved crop yield, biofortification, and resistance to environmental stressors, fostering resilient and high-yielding crops essential for sustaining a growing global population. In nutraceuticals, CRISPR has enhanced the biosynthesis of bioactive compounds such as anthocyanins, flavonoids, and omega-3 fatty acids, improving the nutritional and therapeutic value of crops.

Despite its immense potential, CRISPR technology faces technical, ethical, and regulatory challenges, including off-target effects, accessibility concerns, and public acceptance. Addressing these issues is crucial for …

Heavy Metals In Healthy Water Samples Used By Newborn In Al-Najaf Governorate, Iraq, Ban Hussein Ali, Ali Abid Abojassim

Al-Bahir

Water is essential for life, so monitoring water quality is important. This research focuses on measuring heavy metals (Lead, Pb; Cadmium, Cd; Chromium, Cr (in 14 healthy water samples of two types; bottled water and filtered water used by newborn children in Al-Najaf governorate, Iraq. Atomic absorption spectroscopy (AA-7000, Japan) was used to conduct the experimental analysis. Also, health risks parameters (non-carcinogenic and carcinogenic) due to Pd, Cd, and Cr concentrations were calculated. The results of Pb, Cd, and Cr concentrations in mg/L for bottled water samples were ranged 0.03-0.83, 0.01-0.69, and 0.01-0.76, respectively, while the range values for filter …

Effect Of Adding Nano Silica On Some Structural And Thermal Properties Of Aluminum, Salih Y. Darweesh, Ghazi F. Mahal

Al-Bahir

The powder metallurgy method was employed to fabricate aluminum-based composite samples reinforced with nano silica at varying weight fractions of 2, 4, 6, 8, and 10 wt.%. The powders were mixed, dried, and compacted using a hydraulic press at 7 tons of pressure for one minute, followed by thermal sintering in an oven at 600°C for two hours. Structural characterization was conducted using scanning electron microscopy (SEM) and X-ray diffraction (XRD), while thermal analysis included thermal conductivity, heat capacity, thermal diffusivity, thermal flux, and thermal resistance. The results revealed that the optimal nano silica reinforcement ratio was 10%, yielding notably …

Grassland For Our World, F Riveros

IGC Proceedings (1977-2023)

The present-day role of grasslands and fodder is reviewed with respect agriculture, animal production and environmental concerns. The world 's grazing lands are a finite resource nnd, overall, are being badly mnnaEed; in most developing countries action is required now, before it is too lnte. They will continue to be a major source of animal feed for the foreseeable future; encroachment from cropping will con

Effect Of Irrigation On Vegetation Succession And Forage Regerneration, Fu Jing-Yan

IGC Proceedings (1977-2023)

No abstract provided.

On The Cultivation And Utilization Of Floret Silvergrass (Miscanthus Floridulus) In The Southern Area Of China, Zhu Bangchang

IGC Proceedings (1977-2023)

The plant genus Miscanthus (silvergrass) includes eight species and one variety in China. In the tropical and subtropi­cal area of south China, the silvergrass distributed widely includes the following seven species : Floret silvergrass ( Miscanthus floridulus), Chinese silvergrass ( M. sinensis), Sugary silvergrass ( M. sacchariflorus), Short-hair silvergrass ( M. brevipilus j, Eulalia silver grass ( M. eulalioides), Szechuan silvcrgrass ( M. szechuanensis), Nepal silvergrass ( M. nepalen�� sis). One of them, Floret silvergrass, is the widest in distri­bution and the highest in economical value, and plays a most important role in …

Herbage Dynamics And Plant-Animal Performance On Altered Northern Great Plains Rangelands, P O. Currie, D C. Adams, J D. Volesky

IGC Proceedings (1977-2023)

Mechanical, chemical, and seeding treatments have been used on rangeland to increase herbage production (Griffith et al., 1985). These treatments are generally applied to rangelands in a low serial stage of succession. Improving these rangelands is of major economic importance to livestock producers attempting lo increase the efficiency of their operations. Our study evaluated 5 range improvement treatments for improving herbage and ani­mal production efficiency

Methodology To Determine Planting Time In King Grass (Pennisetum Sp.) Using Historical Climatic Indices, J R. Ayala, M Sistachs, R S. Herrera

IGC Proceedings (1977-2023)

The determination of planting time by field trials has various disadvantages. These trials should be repeated at least for 3 years comparing different months and the extension of the results is limited. The analysis of the climatic effects would allow a greater generalization with correlations between cli­matic and establishment indices. The season of the year in which the highest number of correlations with monthly histori­cal climatic values are fulfilled is required so as to determine planting time. The objective of the present methodology is to select planting time by using correlations between climatic and establishment indices and the monthly characterization …

Methods For The Establishment Of Leucaena Leucocoephala In Cuba, T E. Ruiz, G Febles, N Sistachs, L E. Diaz, G Bernal, J J. Leon

IGC Proceedings (1977-2023)

Studies in tropical and sub-tropical regions of the world on the factors influencing the establishment and early manage­ment of legume swards as pure cultures have not been carried out integrally. Thus, the objective of the present study was to define the best options of the main components so as to develop a technology for establishing Leucaena leucocephala under our conditions.

Studies On Seed Storage And Sowing Time Of Leucaena Leucocphala In Cuba, T E. Ruiz, G Febles

IGC Proceedings (1977-2023)

Germination of stored seeds and sowing time are essential factors that must be known when a technology for pasture utili­zation is required (Febles and Ruiz, 1986; Ruiz and Febles, 1986). Thus, these experiments were set out to learn the per­formance of the seed quality of Leucaena leucocephala cv Peru stored under different conditions and to determine the influence of the sowing time of this species during the rainy season.

Factors Influencing Pasture Establishment And Persistence In The Mid-Altitude Zone, Yunnan, Southern China, Kui Jia-Xiang, R N. Glencross, Ai Hongxin, Chen Xiong

IGC Proceedings (1977-2023)

The mid-altitude zone in Yunnan Province of SW China ranges from 1500-2500 m in altitude and has a climate inter­grading between sub-tropical and temperate with a mean temp. of 7-10°C in the coldest month and 19-22 °C in the hottest month. The annual rainfall ranges from 800-1200 mm with 80 % falling in the monsoon period, May to September. About 80 % of the total 39.4 m ha of the province is in this very hilly mid-altitude zone. (He et al., 1982) Native grassland vegetation is dominated by Themeda trianda, Arundinella radoli, Imperata cylindrica and some other grasses such as …

Obtention Of King Grass (Pennisetum Purpureum) Clones From Tissue Culture. Selection And Evaluation Of Mutants, R O. Martinez, M Monzote, R S. Herraera, R Cruz, V Torres

IGC Proceedings (1977-2023)

King grass (2n = 28) is widely used in Cuba for forage pro­duction. The increase in the variability of this species is there­fore of special interest in agriculture. Tissue culture as a tech­nique to produce and select somaclones from the king grass donor was used to obtain variability. These were obtained when the apical meristems were cultivated in MS medium with 3 mg/I of 2,4 D to regenerate the plants with different hormonal combinations. Those of 0.1 mg/! of kinetine (Martinez, 1986) were prominent. The variability in the selection and evaluation processes is exposed in this paper.

The Efficacy Of A High Magnesium Italian Ryegrass Cultivar In Alleviating Hypomagnesamia, G Moseley, D M. Baker, D H. Hides

IGC Proceedings (1977-2023)

Hypomagnesaemia continues to cause serious economic losses in grazing livestock and recent evidence suggests that its incidence may be increasing. The disease is characterised by a drop in the concentration of magnesium in extracellular fluid and occurs in two forms, chronic and acute. Both forms give rise to classical clinical symptoms which may either result in death or drastically reduced levels of production. The body does not contain a major source of labile magnesium nor does it have a homeostatic mechanism for controlling the level of magnesium in extracellular fluid. The maintainance of normal levels therefore depends almost entirely on …