119409 research outputs found
Sort by
An Advanced Machine Learning Framework and Multi-Label Heart Disease Classification with UNet-Based Nucleus Segmentation
No full textThe growing demand for accurate, rapid, and interpretable diagnostic tools in the medical field has spurred the integration of artificial intelligence into various healthcare applications. Acute Myocardial Infarction, which remains one of the primary causes of mortality in both developed and developing nations, requires timely and precise identification to prevent life-threatening complications. In response to the lack of interpretable AI models tailored to diagnosing AMI using hemogram parameters, this study presents a robust machine learning-based framework that explores the diagnostic potential of these parameters. By evaluating several machine learning techniques, the research establishes the superiority of boosting algorithms, particularly the Light Gradient Boosting Machine, in identifying AMI cases. The proposed model achieves a commendable accuracy of 85.31% and an Area Under the Curve score of 85.28%, signifying its high discriminative power between AMI patients and healthy individuals, while simultaneously offering transparency in decision-making—an essential factor in clinical applications.
Extending the application of AI in cardiovascular research, this study also addresses the critical challenge of predicting multiple complications associated with heart disease, such as cardiogenic shock, pulmonary edema, and ventricular fibrillation, among others. A novel framework combining a K-Nearest Neighbors-based imputation technique with a Gradient Boosting model is proposed for multi-label classification of heart disease complications. The methodology demonstrates significant improvement over conventional techniques by employing an enriched pre-processing pipeline and a rigorous comparative analysis across several machine learning algorithms. Evaluation through metrics including accuracy, precision, recall, F1-score, and Hamming loss affirms the effectiveness and generalizability of the framework. Moreover, a novel framework is proposed that leverages a Hybrid Shallow Neural Network (HSNN) architecture, designed to balance model complexity and computational efficiency. Additionally, a new feature selection algorithm, termed Gini Importance for Multi-Label (GIML), is introduced, which systematically evaluates and selects the most relevant features across all labels by employing a gini impurity-based mechanism. Furthermore, in the domain of biomedical imaging, particularly cell nucleus segmentation in microscopy images, the study introduces mA-UNet—an advanced model engineered to detect fine-grained foreground elements in imbalanced datasets. This model outperforms existing approaches, attaining a mean Intersection over Union score of 95.50%, and exhibits hardware efficiency when deployed on the Zynq UltraScale+ FPGA. Collectively, the research underscores the transformative role of interpretable and high-performance AI in addressing complex clinical and biomedical imaging tasks
CAREERS ON THE SPECTRUM: Enhancing Higher Education Career Services for First-Generation Neurodivergent College Students
No full textThis study investigates the unique career service needs and experiences of first-generation neurodivergent college students (FGNCS) at the University of Mississippi. First-generation college students (FGCS), as the first in their families to attend college, often face distinct challenges in navigating higher education due to limited familial support and unfamiliarity with academic resources. Meanwhile, neurodivergent students, those with conditions such as autism spectrum disorder, ADHD, and various cognitive differences, encounter unique barriers related to sensory sensitivities, communication, and social integration within academic and career environments. At the intersection of these identities, FGNCS encounter distinct challenges in career services that may not be fully addressed. This highlights a need for support methods that integrate the career exploration resources valuable for FGCS with the accommodations necessary for neurodivergent students.
This study uses a qualitative analysis of FGNCS perceptions, examining how current career service practices impact their academic engagement, career readiness, and overall college experience. The insights gained from this research inform recommendations for enhancing career services to create a more inclusive and supportive framework. By understanding and addressing these students\u27 unique needs, the study aims to guide the University of Mississippi and similar institutions toward building equitable career service models. Ultimately, these findings highlight the importance of accessible and responsive career resources that cater to diverse student populations. Such resources can create pathways for FGNCS and other marginalized groups to achieve both professional and academic success
Navigating Cultural Transitions: The Adaptation Experiences of Bangladeshi International Students in the USA
No full textThis thesis explores how Bangladeshi international students adapt to life and study in the United States. I conducted in-depth interviews with students at the University of Mississippi to understand their everyday experiences. My focus was on how they manage cultural, academic, and social challenges. I used segmented assimilation theory, Berry’s acculturation model, and Bourdieu’s concept of cultural capital to guide my analysis. The findings are shared in three main parts. First, I discuss how students use community support and religious networks to feel at home. Second, I look at how they deal with language barriers, classroom culture, and identity shifts. Third, I explore how their skills, education, and class background shape their ability to adapt. Most students showed strong academic motivation. Many said failure was not an option because of family and social expectations. They faced emotional struggles like homesickness and loneliness, but they kept moving forward. This study highlights the unique journey of Bangladeshi students—a group often overlooked in research. Their stories show how cultural identity, community, and personal resources shape their paths in a new country. By listening to their voices, this thesis adds to our understanding of international student life and cultural adaptation
Wasted
No full textThis research examines waste production during home football games at the University of Mississippi through comprehensive documentation and analysis of tailgating activities and cleanup operations. Using ethnographic methodology, the study involved conducting interviews and filming tailgating events and subsequent waste management processes for home football games during the 2023 and 2024 seasons. This documentation culminated in the creation of a short documentary film titled WASTED. “WASTED” reveals substantial waste generation, with tailgating areas alone producing over 600 tons of trash during the 2023 football season Additional tonnage data from the 2024 season further demonstrates the consistency of this pattern of waste production.
The findings indicate that college football game weekends generate extraordinary amounts of waste within compressed timeframes, creating significant environmental challenges that extend far beyond the immediate campus community. In particular, these results suggest the need for heightened awareness of environmental sustainability in college athletics, particularly given that the University of Mississippi represents one of the smaller SEC institutions in a relatively small college town. This research addresses a critical gap in public awareness regarding the environmental footprint of collegiate sporting events. The documented waste levels reveal shocking quantities that demand immediate attention from university administrators, environmental advocates, and policymakers. The study emphasizes the urgent need for comprehensive waste reduction strategies, particularly targeting food waste, which constitutes a significant portion of the total tonnage. These findings contribute to the growing body of literature on sustainable practices in higher education and provide empirical data essential for developing effective waste management policies in collegiate athletic environments
