Judson University is a private evangelical university in Elgin, Illinois. It was founded in 1913. Judson was formed out of the liberal arts component of Northern Baptist Theological Seminary. When the seminary moved from Chicago to Lombard, Illinois, it was decided to make the college separate from the seminary. Originally known as Judson College, it was named after Adoniram Judson, the first American Baptist missionary to foreign shores. The university has campuses in Elgin and Rockford, Illinois, and a student body of approximately 1,300. Judson College became Judson University on August 28, 2007.
Healthcare systems increasingly rely on predictive analytics to improve patient outcomes, yet concerns about data privacy and model transparency remain significant barriers to adoption. This paper presents a novel framework integrating Federated Learning (FL) with Explainable Artificial Intelligence (XAI) to enable privacy-preserving predictive analytics in distributed healthcare environments. Our approach allows multiple healthcare institutions to collaboratively train machine learning models without sharing sensitive patient data, addressing critical privacy regulations such as HIPAA and GDPR. We incorporate explainability techniques including SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to provide clinically interpretable insights into model predictions. The framework is evaluated on real-world healthcare datasets for disease prediction and risk stratification tasks. Results demonstrate that federated models achieve comparable accuracy to centralized approaches while maintaining data privacy, with explainability layers enhancing clinical trust and adoption. Our work bridges the gap between advanced predictive analytics and practical healthcare deployment, offering a scalable solution that balances model performance, privacy preservation, and interpretability. This research contributes to the advancement of trustworthy AI in healthcare systems.
The problem regarding plastic waste requires ingenious solutions to make recycling more efficient and less environmentally harmful. Traditional methods of sorting plastic materials have several disadvantages; most rely on manual effort or low-degree automation regarding speed, accuracy, and scalability. Thus, this paper presents an innovative sorting system that employs IoT, generative AI, and machine learning to sort plastic waste in real-time. It manifests itself in a system where IoT sensors capture detailed waste characteristics, which later advanced AI algorithms sort into highly particularized categories of plastics. Generative AI models raise sorting accuracy by generating synthetic datasets to handle the variation within plastic waste forms, enhancing classification models’ robustness. Real-time data processing acts for immediate automated decision-making, thus considerably reducing the time taken in sorting and operational costs. The results indicated that the proposed system increases sorting efficiency by 30
Breast cancer (BC) is one of the most common and deadly diseases necessitating early identification and effective diagnosis to increase survival chances. However, traditional diagnostic approaches suffer from high false-positive and false-negative rates and limited accessibility in resource-constrained settings. To overcome these challenges, a novel deep learning-based COBRC-MOS is proposed for the classification of BC using mammographic images. Initially, the input mammography images are gathered from the MIAS dataset. The input images are preprocessed using contrast-limited Adaptive Histogram Equalization (CLAHE). The EfficientNet is used for feature extraction, and the Crayfish Optimization Algorithm (CFO) is used to select the most discriminative and optimal features by efficiently exploring the search space to enhance model performance and interpretability. Then the SVM is used to classify eight types of breast cancer namely, malignant papillary carcinoma (MPC), malignant mucinous carcinoma (MMC), Malignant Ductal Carcinoma (MDC), malignant lobular carcinoma (MLC), Benign Tubular Adenoma (BTA), Benign Phyllodes Tumor (BPT), Benign Fibroadenoma (BF), Benign Adenosis (BA). Finally, the U-Net segmentation is used to identify affected regions accurately. Moreover, the proposed COBRC-MOS model classification accuracy was 98.35
This paper presents an enhanced simulation framework for accurately modeling modern computer architectures and evaluating system performance. The proposed platform supports a wide range of instruction set architectures (ISAs), memory hierarchies, and interconnect designs, enabling researchers to explore hardware behavior and optimize system-level performance. Through modular design and extensive configuration options, the simulator allows for in-depth analysis of processor pipelines, cache coherence protocols, and network-on-chip topologies. Experimental validation using real-world benchmarks demonstrates the framework's accuracy and efficiency, making it a valuable tool for architects and system designers.
The rapid growth of medical imaging data and shortage of expert clinicians have created a critical need for automated, accurate, and interpretable diagnostic systems. This study proposes a unified deep learning framework for early disease identification from multi-modal medical images, including X-rays, MRI, CT scans, and histopathological slides. The approach integrates a hybrid CNN–Transformer architecture to effectively capture both local spatial features and global contextual dependencies, enhancing diagnostic performance. To address the "black-box" limitation of deep learning models, explainable artificial intelligence techniques such as Grad-CAM and SHAP are incorporated to provide visual and interpretable insights into model predictions. Transfer learning and data augmentation strategies are employed to overcome limited annotated medical datasets and improve generalization. Experimental results demonstrate that the proposed framework achieves high accuracy, sensitivity, and specificity across multiple disease detection tasks, outperforming existing baseline models. Furthermore, the generated explainability maps enhance clinical trust by highlighting diagnostically relevant regions. The findings emphasize the potential of explainable deep learning systems as scalable, reliable, and ethically aligned solutions for next-generation computer-aided diagnosis.