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
Alignment of AI Knowledge Units and Cybersecurity Competencies for PUPR’s Programs of Study
(Polytechnic University of Puerto Rico, 2025) Vivas Gotay, Roberto; Cruz, Alfredo
The rapid integration of artificial intelligence into cybersecurity practice has increased the need for precise, curriculum-level alignment between emerging artificial intelligence concepts and established national cybersecurity education frameworks. This master’s degree project presents a structured alignment of Artificial Intelligence in Cybersecurity knowledge units with the proposed Master of Science in Computer Science curriculum at the Polytechnic University of Puerto Rico. Rather than designing new curricular content, this work analyzes existing and planned graduate courses to identify where artificial intelligence–
enabled cybersecurity concepts are already embedded and how they can be formally documented to support accreditation and program evaluation requirements. In addition, competency statements were developed for cybersecurity-related courses and aligned with nationally recognized cybersecurity workforce frameworks to support workforce relevance. The results demonstrate that a curriculum-first alignment strategy can meet the expectations of the Artificial Intelligence in Cybersecurity program while preserving existing course structures. This approach provides a replicable framework for institutions seeking to integrate artificial intelligence considerations into graduate cybersecurity education without redesigning the curriculum. Key Terms – AI Cyber Knowledge Units, Cybersecurity Education, Graduate Competencies, Workforce Development.
Building a Spam Detector Using Neural Networks Activation Functions
(Polytechnic University of Puerto Rico, 2025) Castillo Echavarría, Rafael E.; Rodríguez Espinosa, Lisabel
This project explores the application of Artificial Neural Networks in the classification of electronic mail as either "Spam" or "Ham" (legitimate). By using activation functions, which serve as the mathematical "gates" that decide whether a neuron should fire a spam prediction. The experiment shows how automated filtering systems can greatly increase accuracy and reduce false positives by using tuning functions such as the Sigmoid and the Rectified Linear Unit (ReLU) [1]. Artificial neural networks are strong instruments that can make difficult decisions and learn from data. They are made up of layers of linked neurons that change with practice. Using the test data, the network updates its weights and biases. Activation functions facilitate this process by allowing the model to learn from errors and get better over time. This is the beginning of the creation of predictive generative artificial intelligence. Key Terms ⎯ Activation Function, Artificial
Neural Network, Rectified Linear Unit, Sigmoid.
Analyst-In-Loop LLM Systems for Forensic Timeline Analysis Assistance
(Polytechnic University of Puerto Rico, 2025) Rodriguez Ruiz, Oscar J.; Duffany, Jeffrey
The increasing volume and complexity of digital evidence in digital forensic investigations of today have made manual timeline analysis not only inefficient but a reckless waste of resources and effort. Tools such as Plaso (Log2timeline) have shown to be highly effective at creating “super timelines” that gather information from various sources. Creating datasets spanning thousands of events, which can be actively considered “noise” for the forensics examiner. However, within the past years, we have made great strides in the field of artificial intelligence. These allow for the utilization of the processing power of the neural networks to assist with the process of detecting anomalies and filtering for essential parts of an investigation. Through extracting general outputs with Plaso as a CSV file, we can utilize said outputs to highlight the role that private AI models will begin to take within the field after considerable training with the available forensic training data. Keywords ⎯ Digital Forensics, Event Reconstruction, LLM, Plaso Supertimeline.
Intelligent Agents for Natural Language Interaction
(Polytechnic University of Puerto Rico, 2025) Velázquez Marrero, Nelson; Torres Batista, Nelliud D.
This research study explores the use of ai agents for decision making, and problem solving. They leverage advanced natural language processing techniques of large language models to analyze user inputs and determine which external tool to call. The use of agentic technology is called tool calling to perform complex tasks. Tool calling is the agent’s ability to invoke external functions or API’s as it was their own built command. Using these ai agents users can get insights from data without technical knowledge. Keywords - Agentic AI, Function Calling, Large Language Models, Natural Language Interaction.
Integration of Predictive Analytics into Inventory Management Systems Using Machine Learning
(Polytechnic University of Puerto Rico, 2025) Martínez de La Cruz, José A.; Torres Batista, Nelliud D.
Small and medium-sized retail businesses frequently face difficulties maintaining optimal inventory levels due to fluctuating demand, seasonality, and traditional manual decision making. This article proposes the design of an intelligent inventory management system integrating predictive analytics through machine learning techniques to forecast product demand and generate dynamic restocking recommendations. The system utilizes a cloud-hosted PostgreSQL database managed through Supabase, a FastAPI-based Python backend, and a React-based web interface. Forecasting models are developed using established time-series methodologies such as ARIMA, Prophet, and Long Short-Term Memory (LSTM) neural networks. The goal is to demonstrate how predictive analytics can enhance operational efficiency, reduce losses caused by inadequate inventory planning, and support data-driven decision-making in modern retail environments.
Keywords – Cloud Databases, Inventory Management, Machine Learning, Predictive Analytics, Time-Series Forecasting.