24067 research outputs found
Sort by
Enhancing Credit Path Planning With LLM-Based Multi-Agent Systems
Get PDFThis work explores applying Multi-Agent (MA) Large Language Models (LLMs) to enhance credit card management, an underexplored area for their multi-step reasoning capabilities. Focusing on Equifax’s Optimal Path™ model [1]—a personalized solution for credit score optimization—the study addresses two key challenges: first, designing a natural language interface for financial credit models to improve accessibility and aid customer decision-making, and second, enhancing the reliability and real-world applicability of complex financial models prone to generating invalid or unfeasible recommendations caused by a lack of practical interpretability and susceptibility to edge cases. To tackle these, we propose and evaluate various MA designs, including sequential critique, debate-based, self-reflective, and chain of agents’ frameworks. Each architecture utilizes specialized LLM agents to either generate explanations or identify/correct problematic action plans. Performance is assessed using a novel, unsupervised goal-alignment metric, evaluating generated plans against user requests and company objectives. Results show that one and two-agent systems effectively provide natural language interfaces. Notably, two-agent systems, employing self-consistency techniques, significantly improve response alignment and reduce variability for challenging requests compared to single-agent systems. Moreover, combining self-consistency with prompt engineering methods (e.g., few-shot Chain of Thought and score change distribution) leads to higher, more stable alignment for moderately complex user queries. The study reveals no single universally optimal architecture; while chain and debate agents excel in standard tasks, collaborator agents demonstrate unique robustness against unrealistic requests, producing grounded outputs
Problematic Smartphone Use Experiences of Students
Get PDFSmartphones extend people\u27s opportunities by improving their daily living and well-being. Hence, given the tool’s features and affordances that promote human development, smartphones facilitate the achievement of the individual liberties and freedoms of ordinary people. However, there are serious concerns about the emotional, social and cultural factors underlying smartphone usage patterns and their association with problematic use and depressive behaviors. Therefore, the overriding goal of the research reported on in this paper was to investigate how smartphone use influences individuals’ emotional wellness, interpersonal relationships and sociocultural contexts. Existing academic literature indicated that there was a need to investigate the intricate interplay between smartphone use and indicators of problematic behaviors. Hence, undergraduate students were invited to participate and a mixed-methods research approach was adopted. Data were collected using a prescreening questionnaire, semi-structured interviews and focus group discussions and were analyzed thematically by means of a systematic coding process. The data revealed that smartphone users have many different perspectives and coping strategies and this finding highlighted the complexities of smartphone-related problems. Furthermore, the study underlined the importance of cultural factors and individual differences in addressing the complex relationship between smartphone use and digital wellness
Static Malware Analysis for Incident Response: Developing a Tactical Aid with EMBER
Get PDFIncident responders face a variety of challenges when identifying malware using existing solutions, particularly when rapid tactical decisions are needed. Traditional malware detection methods are often signature-based, limiting their effectiveness to previously known threats detected by anti-virus (AV) engines. Online analysis tools introduce confidentiality risks, potentially alerting adversaries that their actions are under scrutiny. While free sandbox environments offer useful capabilities, they often require substantial setup time and hardware resources that may not be available in the field. This research leverages the Elastic Malware Benchmark for Empowering Researchers (EMBER) dataset to develop a lightweight, portable tactical decision aid that enables incident responders to rapidly determine whether a binary warrants further investigation. Furthermore, the study evaluates the efficacy of this decision aid by testing it on recent malware samples from 2022 to 2023, assessing the suitability of the 2018 EMBER dataset as a training benchmark for identifying modern threats. A GitHub repository has been created to share the resulting tactical decision aid with the broader cybersecurity community, fostering collaboration and facilitating future research
University Philharmonic Orchestra and Cooke String Quartets
Get PDFNancy Conley, Conductorhttps://digitalcommons.kennesaw.edu/musicprograms/2940/thumbnail.jp
Experts on Repositories: Depositing Graduate Student Work
Get PDFDid you know graduate student work can be uploaded to a repository and shared with a global audience? Our expert Juliet Langman, Dean of the Graduate College and Professor of Applied Linguistics, discusses the role repositories and databases like ProQuest can play for graduate students and their post-academic career. This session was moderated by Assistant Director of Academic Engagement and Instruction, Collegiate Librarians Kristina Clement.https://digitalcommons.kennesaw.edu/sprpresents/1009/thumbnail.jp
KSU Faculty Brass Quintet
Get PDFKSU Faculty Brass Quintethttps://digitalcommons.kennesaw.edu/musicprograms/2947/thumbnail.jp
KSU Opera Theater presents: Amahl and the Night Visitors & La Divina
Get PDFJoin the KSU School of Music for an evening of operatic storytelling featuring two one-act performances. Gian Carlo Menotti’s Amahl and the Night Visitors is a beloved holiday classic that follows a young boy whose encounter with three mysterious kings leads to a miraculous journey of generosity and healing. Thomas Pasatieri’s La Divina offers a humorous and poignant glimpse into the life of a retired opera star preparing for her final curtain call.This double bill showcases the exceptional talent of KSU’s voice students and faculty, and celebrates the richness and diversity of operatic performance.https://digitalcommons.kennesaw.edu/musicprograms/2946/thumbnail.jp
Soovin Kim, Violin
Get PDFKorean-American violinist Soovin Kim is an exciting player who has built on the early successes of his prize-winning years to emerge as a mature and communicative artist. After winning first prize at the Niccolò Paganini International Competition, Mr. Kim was recipient of the prestigious Borletti-Buitoni Trust Award, an Avery Fisher Career Grant, and the Henryk Szeryng Foundation Career Award. Today he enjoys a broad musical career, regularly performing repertoire such as Bach sonatas and Paganini caprices for solo violin, sonatas for violin and piano by Beethoven, Brahms, and Ives, string quartets, Mozart and Haydn concertos and symphonies as a conductor, and new world-premiere works almost every season.https://digitalcommons.kennesaw.edu/musicprograms/2945/thumbnail.jp
Data Privacy Regulations in the Gaming Industry: A Comparative Analysis of Singapore, Macau, and Japan
Get PDFThis study explores the relatively under-researched area of comparing data privacy regulations and best practices across different countries, with a focus on the gaming industry. It provides an overview of general data privacy principles and existing global regulations, analyzing how gaming operators leverage personal data for competitive advantage. Specifically, the research examines the data privacy approaches and regulatory requirements in Singapore, Macau, and Japan, highlighting the cultural and historical contexts influencing these regulations. Through a comparative analysis, the article discusses the compliance needs for gaming operators in these jurisdictions
A Complete Transfer Learning-Based Pipeline for Discriminating Between Select Pathogenic Yeasts from Microscopy Photographs
Get PDFPathogenic yeasts are an increasing concern in healthcare, with species like Candida auris often displaying drug resistance and causing high mortality in immunocompromised patients. The need for rapid and accessible diagnostic methods for accurate yeast identification is critical, especially in resource-limited settings. This study presents a convolutional neural network (CNN)-based approach for classifying pathogenic yeast species from microscopy images. Using transfer learning, we trained the model to identify six yeast species from simple micrographs, achieving high classification accuracy (93.91% at the patch level, 99.09% at the whole image level) and low misclassification rates across species, with the best performing model. Our pipeline offers a streamlined, cost-effective diagnostic tool for yeast identification, enabling faster response times in clinical environments and reducing reliance on costly and complex molecular methods