Communities in PRCR
Select a community to browse its collections.
- Colecciones de la Albizu University
- Colecciones digitales de Atenas College
- Colecciones de los Centros Sor Isolina Ferré
- Materiales utilizados para la certificación.
Recent Submissions
“How to”, Practical approach to Multi Agent Cyber Defense
(Polytechnic University of Puerto Rico, 2026) Pérez Narváez, Dylan Renier; Rodríguez Espinosa, Lisabel
This project is a guided "how to" approach that explains how multi agent defense is studied, how theory guides exploration, and how practical understanding develops. It includes two hands-on proof of concepts, one built in n8n and one in Python, that put these ideas into practice using real tools. The goal is to help connect research and application in order to simplify the study of the field. This will give the reader both conceptual understanding as well as a real application of the material.
A Metadata-Driven Secure Data-Sharing Model for Controlled Access to Proprietary Information
(Polytechnic University of Puerto Rico, 2026) Cabán Ferrer, Eddie; Duffany, Jeffrey
A metadata-driven secure data-sharing model is proposed for controlling access to proprietary information exchanged between internal enterprise sources and external collaborators. The framework was designed to show that secure sharing can be governed through identity-aware authorization, tags-based policy enforcement, protected file storage, and persistent auditing rather than through static permissions or vendor-specific platforms. The implemented system integrates an identity provider, a policy evaluation engine, a relational database for metadata and audit records, object storage for protected files, and an application layer that coordinates token validation, authorization queries, storage access, and request measurement. Evaluation was conducted in three stages: a controlled baseline, a moderate workload stage, and a larger workload stage. Across these stages, the framework maintained correct access-control behavior, prevented unauthorized proprietary downloads, and preserved complete audit capture for protected actions. The results support the feasibility of a vendor-independent middleware approach for deterministic, auditable, policy-directed control of sensitive document sharing.
Adverse News Detection and Classification System for Anti-Money Laundering Investigations
(Polytechnic University of Puerto Rico, 2026) Rivera Rodríguez, Fabiola; Cruz, Alfredo
Adverse media screening is an important component of Anti-Money Laundering (AML) compliance, requiring the analysis of large volumes of unstructured news data. This project presents the development of an automated adverse media detection system using Natural Language Processing techniques to support AML-focused risk analysis. The system collects multilingual news articles from publicly available Really Simple Syndication feeds, applies Named Entity Recognition using spaCy models for English and Spanish, and incorporates rule-based filtering and normalization to improve entity extraction consistency. A keyword-based risk-scoring methodology assigns article-level risk scores, which are later aggregated to evaluate entity-level exposure to adverse media indicators. A Streamlit based web application was developed to facilitate interactive exploration of ranked entities and associated articles. The system achieved 90.66% precision in entity extraction, with a 95% confidence interval ranging from 85.55% to 94.09%, demonstrating the effectiveness of the proposed approach for multilingual adverse media analysis within AML contexts.
CyberSecureHub: An Educational Platform for Cybersecurity Learning
(Polytechnic University of Puerto Rico, 2026) Rodríguez Franceschini, Germán; Cruz, Alfredo
Cybersecurity education is fragmented across separate websites, technical blogs, certification pages, and practice platforms. Entry level professionals must move between resources to learn penetration testing, security operations, and career pathways, which slows learning and disconnects theory from practice. The CyberSecureHub web application was developed using Python and the Flet framework to centralize foundational cybersecurity content into a single browser accessible environment. The platform integrates Red Team and Blue Team material, certification guidance, three tiers of Capture the Flag (CTF) challenges, and an Artificial Intelligence (AI) chatbot that provides support. The system was implemented and tested end-to-end. Results confirm that modular architecture can present offensive and defensive concepts together and that a contextual chatbot can support learning without replacing it. Design Project Article for the Graduate Programs at the Polytechnic University of Puerto Rico. Includes a graduate project poster summarizing the research through concise text and visuals derived from the same study.
Predictive Maintenance for Heavy-Duty Truck Fleets: An Explainable Machine Learning Approach on the SCANIA Component X Dataset
(Polytechnic University of Puerto Rico, 2026) Hernández Vázquez, Irvin E.; Torres Batista, Nelliud D.
Component failures in heavy-duty truck fleets generate substantial operational costs and safety risks. This study develops a cost-optimized predictive maintenance system using real-world heavy-duty truck telemetry. A calibrated gradient boosting model achieves a 45% reduction in operational maintenance cost and 86% failure recall. The primary contribution lies in configuration-stratified explainability analysis using a game-theoretic attribution framework. We demonstrate that vehicle specification groups exhibit mechanistically distinct failure pathways, with feature importance rankings diverging significantly across categories. Global predictors include sensor variance and usage intensity metrics, but stratified analysis reveals specification-dependent degradation signatures previously unreported. The observed precision ceiling reflects inherent data constraints rather than methodological limitations. These findings challenge the homogeneous fleet assumption and suggest that specification-aware alerting could substantially improve maintenance efficiency. This work establishes stratified explainability as a foundation for knowledge-driven, targeted predictive maintenance in industrial fleet management.