Computer Engineering
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12475/57
Browse
32 results
Search Results
Item Analysis of Sentiment in YouTube Comments for 2024 Political Campaigns for Governor of Puerto Rico(Polytechnic University of Puerto Rico, 2024) Oriol Rivera, Carlos A.; Duffany, JeffreyThe analysis of public sentiment is an invaluable tool in political campaigns, enabling candidates and their teams to assess voter attitudes and adjust campaign strategies accordingly. This project focuses on collecting and analyzing video comments on YouTube from the months leading up to an election to determine the public’s sentiment toward different candidates for governor in Puerto Rico. To make this sentiment analysis, the Text Blob Python library was used due to its ease of use and robust functionality. The project incorporates both client-side and server-side components, integrating modern web development frameworks and libraries to provide good user experience. This investigation outlines the data collection methodology, system architecture, analysis process, discussion of results, and coding logic used to achieve the analysis. Key Terms ⎯ Political Campaigns, Sentiment Analysis, TextBlob Python Library.Item Applications of Fast.ai Pretrained Models in Image Classification Problem(Polytechnic University of Puerto Rico, 2024) Tapia Maldonado, Antonio Ahmed; Duffany, JeffreySince the inception of Transformers and GPTs, artificial intelligence has proliferated. Fast.ai is among the cutting-edge libraries that are leading new advancements in the field. To harness the power of fast.ai and other advancements in the field, we set out to try and evaluate the practicality of the fast.ai library. To achieve this, we choose a given use case for artificial intelligence and then set out to fulfill said use case by leveraging fast.ai. We created three image classification models through fast.ai and then made an application that used those models. The use case we chose was a local wildlife fauna and flora classifier. The results from training the models were models with meager error rates, and these models had little to no data engineering. Key Terms ¾ computer vision, deep learning, fast.ai, image classification.Item Cybersecurity Tools(Polytechnic University of Puerto Rico, 2024) López Ubinas, Harry E.; Duffany, JeffreyThe goal of this project is to analyze the effectiveness of different Cybersecurity tools. It will test different techniques such as vulnerability scanning on the network, Wi-Fi hacking, and password cracking. Key Terms ¾ cybersecurity, password cracking, vulnerability scanning, wi-fi-hacking.Item Developing an Accessible Web Journal with WCAG Guidelines, Fitts’s Law, and Capital T Concept(Polytechnic University of Puerto Rico, 2023) Mercado, Carlos; Duffany, JeffreyIn the ever-evolving digital landscape, enhancing web accessibility and user experience remains a paramount objective. By expanding the application of Fitts's Law to user interface design, the researcher unlocks the potential to create web experiences that are both efficient for all users and exceptionally inclusive, including the tactile and digital advantages of interactivity. By harnessing the Capital T Concept, the researcher craft an accessible reading experience where users, including those with disabilities, can effortlessly navigate pages and embark on a journey of exploration. This article delves into the innovative fusion of the WGAG guidelines, Fitts's Law, and the Capital T Concept principles with accessible web design, illuminating the path to a more inclusive digital world. Key Terms ⎯ Capital T Concept, Fitts’s Law, Web Accessibility, WCAG.Item A Personal Health Monitoring and Emergency Assistance Mobile Application(Polytechnic University of Puerto Rico, 2023) Rosario Colón, Jonathan D.; Duffany, JeffreyAs digital technology continues to advance; new opportunities arise for enhancing emergency response and health management. The Be Safe mobile application focuses on identifying these opportunities and leveraging today's AI capabilities to improve the efficiency and effectiveness of emergency services. By utilizing Dart, FlutterFlow, Firebase, and OpenAI's ChatGPT, the app enables users to store and monitor vital health data, record and upload emergency videos, and receive real-time AI-driven guidance. The primary goal of the project is to optimize emergency response in Puerto Rico by providing accurate information to first responders, ultimately saving time and resources. With the integration of advanced AI-driven communication features and personalized content generation, Be Safe aims to be a powerful tool for both individuals and first responders in managing health and ensuring safety during emergencies. Key Terms - Be Emergency Response, Health Management, AI-driven Communication, Personalized Content, Opportunities.Item Considerations on SQL Optimization Tools in MS Azure SQL Server Database using SQL language(Polytechnic University of Puerto Rico, 2021) Rodríguez-Ortiz, Arlene; Duffany, JeffreyDatabases are essential since are designed to stored and organized data that can be easily managed and accessed. They are crucial to many organizations, companies, and are used in many aspects of our lives. The relational database, based on the relational model, and represented in a tabular way, is one of the most used. Relational database management systems are used to maintain them. One of the most known languages for querying and maintaining relational databases is the Structured Query Language. On this paper article, the researcher explored different optimization tools in MS Azure SQL Server Database that could bring information that could help students and developers to optimize their queries and improve performance. Key Terms ⎯ Query Plans, Query Profiler, SQL Optimization Tools, and Structured query language (SQL).Item Meteorite Landing Data Visualization with Python(Polytechnic University of Puerto Rico, 2019) Atiles Gil de Lamadrid, Ileana M.; Duffany, JeffreyFor billions of years, the Earth has witnessed meteorite falls. Meteorites enter the Earth’s atmosphere and land in more places than others. Recording on meteorites has been based on sighting and recovery. Many meteorites recoveries had been possible to Earth’s conditions (such as cold temperatures) and human dedication. This project aims to corroborate data findings using Python programming language in a JupyterLab web environment. Data visualization of meteorites sample data will help to analyze where they land the most, which is the heaviest in mass and what year had the most landings. Zipf’s law is considered as an approach to investigate if meteorites hitting the Earth follow any distribution pattern. Key Terms ⎯ Data Visualization, JupyterLab, Meteorite, Python3.Item An Overview to Digital Forensics Tools(Polytechnic University of Puerto Rico, 2010) Blakely Santiago, Waldemar; Duffany, JeffreyThis paper is in support of seven newly created tutorials, focused on different digital forensic analysis tools. The tutorials are intended as in-class laboratory exercise for the computer forensics classes at the Polytechnic University of Puerto Rico. These tutorials are specifically designed to provide basic understanding on the functionalities and capabilities of each particular digital forensic tool. The seven tutorials will serve as a starting point for new users to explore and acquire knowledge in the computer forensics field. Forensic analysis tools are currently been used by law enforcement, private forensic investigators and particular individuals to recover evidence, company files or personal files from specifics electronic medias. The correct use of digital forensics tools is a key factor in the recovery, authentication and analysis phase of electronic data. The newly created tutorials provide examples of the examination phases of electronic media and digital data. Key Terms - Data Recovery, Electronic Data, Forensics, Storage Device, Tutorial.Item Audio Fingerprinting with Robustness to Pitch Scaling and Time Stretching(Polytechnic University of Puerto Rico, 2013) Díaz Millet, Yesenia; Duffany, JeffreyCurrent audio fingerprinting systems are becoming increasingly robust against noise and filter distortions, however songs that have been pitch scaled and time stretched are still likely to pass undetected. This research focuses on expanding an existing landmark-based fingerprinting method to identify songs that have been pitch scaled and time stretched to escape current systems while still sounding natural to the human ear. Two feature extraction methods have been explored with the purpose of resolving each task individually. The constant Q spectrogram was used for feature extraction, instead of a conventional spectrogram, to identify songs that have been pitch scaled. Mel-frequency Cepstral Coefficients were used as features for the other task. The goal is to verify whether or not low-level spectral based features alone are capable of handling such transformations in a song instead of needing to use mid-level or high-level musical features as is the case with other Song ID methods. Key Terms - Audio Fingerprinting, Feature Extraction, Music Information Retrieval, Music Similarity.Item R: Color Package(Polytechnic University of Puerto Rico, 2009) Rivera Negrón, Eurípides; Duffany, JeffreyAbstract - R is a software language mostly used of statistical and mathematical purporses. R capabilities are extended by user’s submitted packages. The gColor Package provides R Language a method to solve Systems of Inequation (represented as a matrix) in files created by the Discrete Mathematics and Theoretical Computer Science (SIMACS). The advantange of the gColor Package is the import fo DIMACS files which supports compress (binary) and uncompress (ASCII) format, currently not available in R Language,and the conversion of the data imported from vertices and edges into a an adjacency matrix; allowing users to import graphs from other systems and use it as a matrix object. This document is divided in four sections. The Introduction provides and overviedw of the problem and the justification to the development of this project. The R Language brings an introduction to R. The system of Inequation explains briefly what is it and how can be representd in R. The gColor Package explains the structure of the package. How the package was build and integrated with R is explained in section Building the Package. Key Terms - ASCII, CRAN, DIMACS, Dynamic Link Library (DLL)