Wilmington University

With the increasing complexity of cyber assaults in cloud environments, adaptable security solutions are needed that can support real-time detection and autonomous response. In this paper, we propose a reinforcement learning-based dynamic cyber defense framework. We deploy a Deep Q-Network (DQN) to train effective defensive strategies to counteract the evolving cyberattacks. We leverage the CICIDS2017 dataset for model creation and the UNSW-NB15 dataset for external validation, involving preprocessing of data, feature engineering, and adaptive policy learning. We compare the proposed DQN with decision tree, support vector machine, random forest, XGBoost, and multilayer perceptron models. The proposed DQN achieves an accuracy of 99.72

Objective:Clinical nurse attrition from the bedside calls for innovative professional development strategies that diversify skills and support wellbeing and retention. To address this issue, the largest health system in Delaware implemented the nation's first Nursing Research Fellowship in Robotics and Innovation using external grant funding. Programmatic Methods:Following a competitive application pool, four bachelors-prepared clinical nurses were selected from two hospital campuses across four diverse practice areas. This eight-month, paid fellowship grounded in adult learning theory combined weekly didactic instruction with mentored, hands-on research in a structured, collaborative, and independent format. The nurse fellows serve as co-investigators on an IRB approved robotics study. Longitudinal pre-, mid-, and post-fellowship surveys assessed knowledge acquisition, program experience, and well-being. Programmatic Results:Nurse fellows demonstrated gains in research competencies and specialty areas that included protocol development, informatics, artificial intelligence, robotics, and techquity. All fellows reported increased job satisfaction, improved psychological wellbeing, enhanced professional confidence, and intent to remain at the bedside. Scholarly outcomes included multiple accepted national and regional conference abstracts, published commentary articles, and co-authorship of an original research manuscript. Conclusions:This novel fellowship effectively integrated research education, innovation, and paid protected time to strengthen clinical nurses' research capability, professional fulfillment, and retention to the bedside. This program offers a replicable model for advancing nursing workforce wellbeing through immersive, mentored research experiences.

This study develops an integrated predictive business intelligence (BI) framework that combines machine learning (ML), explainable artificial intelligence (XAI), and large language models (LLMs) for customer response prediction in banking. Using the UCI Bank Marketing dataset of 45,211 observations, we compare Logistic Regression, Decision Tree, Random Forest, and XGBoost using accuracy, precision, recall, F1-score, and ROC-AUC. Among the evaluated models, Random Forest achieved the strongest overall performance, with 90.0% accuracy, 56.0% precision, 53.0% recall, 55.0% F1-score, and 91.8% ROC-AUC. XGBoost produced the highest recall at 78.0%, with 86.0% accuracy, 45.0% precision, 57.0% F1-score, and 91.4% ROC-AUC. Logistic Regression achieved 82.0% accuracy and 90.3% ROC-AUC, whereas Decision Tree achieved 87.0% accuracy and 67.3% ROC-AUC. We apply SHapley Additive exPlanations (SHAP) to identify the factors contributing to model predictions and integrate an LLM to convert structured prediction and explanation outputs into natural-language business insights. The resulting architecture connects predictive modeling, model explainability, BI visualization, and managerial interpretation within a unified decision-support workflow. The findings indicate that Random Forest provides a balanced predictive performance for the benchmark task, while XGBoost offers greater sensitivity to potential positive cases. The framework demonstrates how combining ML with XAI and LLM-based interpretation can improve the accessibility and transparency of predictive BI. However, practical deployment requires institution-specific validation, particularly because the benchmark data originate from a Portuguese banking campaign and include variables that may introduce temporal leakage. The study therefore positions the proposed framework as a research and deployment architecture rather than evidence of direct performance in U.S. banking environments.

Hospital readmission among patients with chronic diseases remains a major challenge for healthcare systems due to its association with poor patient outcomes and increased healthcare costs. This study proposes a machine learning-based framework for the early prediction of 30-day hospital readmission risk using the publicly available Diabetes 130-US Hospitals dataset from the UCI Machine Learning Repository. A comprehensive preprocessing pipeline, feature engineering, and feature selection techniques were employed to improve data quality and predictive performance. Eight supervised machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, LightGBM, CatBoost, Multilayer Perceptron, and XGBoost, were developed and comparatively evaluated. Model performance was assessed using accuracy, precision, recall, F1-score, specificity, and the area under the receiver operating characteristic curve (AUC-ROC). The experimental results demonstrated that ensemble learning models consistently outperformed conventional machine learning approaches. Among all evaluated models, XGBoost achieved the best performance, attaining 92.16% accuracy, 0.92 precision, 0.91 recall, 0.91 F1-score, 0.95 specificity, and an AUC-ROC of 0.972. These findings indicate that XGBoost effectively identifies patients at high risk of early hospital readmission and can serve as a reliable predictive tool for clinical decision support. The proposed framework has strong potential for integration with Electronic Health Record systems to facilitate early intervention, improve patient outcomes, reduce preventable readmissions, and support value-based healthcare delivery.

Mental-health issues are difficult to identify in their early stages within online platforms because of the complexity, inconsistency, and narrative character of user-generated text. The development of natural-language processing (NLP) and transformer architectures opens new possibilities for large-scale automated detection of psychological distress signals. In this context, the present work constructs a computational pipeline that classifies real-world mental-health forum posts as indicating anxiety or depression—two clinically distinct yet linguistically overlapping conditions. The proposed end-to-end system, ProStack-MH (Probabilistic Stacking for Mental-Health Text Classification), combines rigorous dataset cleaning, noise elimination, staff-content removal, semantic text normalization, transformer-friendly preprocessing, class-balancing, and user-level data partitioning to prevent leakage. ProStack-MH stacks two complementary transformer encoders—roberta-base and distilroberta-base—whose softmax probability vectors are concatenated and passed to a lightweight Logistic Regression meta-learner. Six baselines are evaluated under a strict leakage-free, user-wise test split: classical TF-IDF + LR/SVM, BiLSTM, DistilBERT, MentalBERT, DeBERTa, and RoBERTa-base. Model behaviour is explained post-hoc using SHAP feature attributions and GoEmotions-based affective profiling. An ablation study confirms that the stacking step—rather than either base learner alone—drives the improvement. ProStack-MH achieves 93.38% accuracy, F1 = 0.9302, MCC= 0.8674, and ROC-AUC= 0.98, outperforming all baselines on every metric. This framework provides a reproducible methodological foundation for computational mental-health monitoring, risk screening, and early-intervention research.