Mar 2024 – Present · 2 yrs 3 mos

• I authored a comprehensive guide for building a 6502-based computer using breadboards, inspired by Ben Eater’s custom kit. This step-by-step guide covers the complete assembly process, from unboxing and inventorying components to detailed pin connections and circuit testing. The project aims to provide enthusiasts with a clear and structured approach to understanding and constructing a working 6502 microprocessor-based computer. The guide also includes essential background on the 6502 architecture, practical tips for troubleshooting, and links to further resources for an enriched learning experience.

Dec 2023 – Feb 2024 · 2 mos

• I developed PyForge, a custom Python compiler using .NET and C#. PyForge features an interactive shell for real-time Python code execution, detailed diagnostics for debugging, and parse tree visualization for better understanding of code structure. It supports a variety of commands for enhanced user interaction, persistent variable management, and color-coded output for improved readability. Built with .NET 7.0 and tested using xUnit.net, PyForge aims to provide a comprehensive environment for parsing, evaluating, and debugging Python scripts efficiently.

Nov 2023 – Nov 2023 · 0 mo

• I built an interactive online learning platform similar to Udemy and Coursera. Using Next.js 14, React, TypeScript, and more, Athena offers a user-friendly environment for buying and selling courses. It features an integrated payment system, a dynamic course catalog, and real-time progress tracking, enhancing the e-learning experience.

Oct 2023 – Nov 2023 · 1 mo

• I developed CodeTrack, an issue tracker web application, utilizing Next.js, React, and TypeScript. This project was part of a course I finished and was designed to provide a comprehensive dashboard for efficient and effective oversight.
• The application features a dynamic and responsive user interface, created with React and styled using the @radix-ui/themes library. It employs Prisma, an ORM, to interact with the database, efficiently handling operations like counting open, in-progress, and closed issues. This integration showcases the seamless connection between the frontend and backend, ensuring real-time data accuracy.
• The implementation of Auth.js in CodeTrack allows for secure user authentication, enabling users to confidently manage their accounts and personal information. This security feature is crucial, as it not only protects user data but also ensures that issue tracking and project management are conducted in a controlled environment.
• A standout feature of CodeTrack is its user-centric functionality. Users have the capability to create their own issues, providing a detailed description of each problem or task. This feature empowers users to actively participate in project management, fostering a collaborative and efficient workflow.

Aug 2023 – Dec 2023 · 4 mos

• I developed an intelligent chess bot named KnightVision, designed to participate in the Chess Coding Challenge. Utilizing C# and the .NET 6.0 framework, KnightVision excels in adapting to opponent moves while operating within the competition's 256MB memory limit. The bot features advanced strategies such as an opening book for efficient early-game play, iterative deepening for optimal move selection, and the Negamax algorithm with alpha-beta pruning for efficient game tree search. Additionally, it incorporates a transposition table, quiescence search, and a sophisticated evaluation function to ensure strong performance throughout the game, enhancing its ability to play competitive chess.

Jun 2023 – Aug 2023 · 2 mos

• I completed a course by CodeWithMosh on React Native, focusing on building a mobile application using JavaScript. The course guided me through the process of creating 'DoneWithIt', an e-commerce application. This app is designed to provide a platform for users to sell items they no longer need, enhancing the user experience with a clean, responsive interface.
• Throughout the project, I utilized Expo alongside React Native, which greatly streamlined the development process. Expo provided a set of tools that made it easier to test and deploy the app on both iOS and Android devices without needing to change the codebase significantly.

May 2023 – Jun 2023 · 1 mo

• AutoPilot is my solution for controlling the Tello EDU Drone through a locally-hosted web interface. This system utilizes a robust Flask backend server and a user-friendly React frontend for seamless control of drone operations. Simple arrow key presses initiate commands like takeoff, landing, rotation, and even patrolling. Advanced features, such as facial recognition capabilities powered by OpenCV, expand drone functionalities by enabling real-time face tracking observable on the live video stream.
• The project integrates a robust Flask backend server, which facilitates direct interaction with the drone, performing various commands like taking off, landing, moving, rotating, flipping, and even patrolling. To make these operations user-friendly and accessible, I've developed an interactive React frontend. The front end is specifically designed with a focus on user experience – you can control your drone with simple arrow keys (with live video stream) for a more enjoyable experience. It provides real-time command issuance and response collection with fluid controls, ensuring that operating the drone feels as natural and intuitive as possible.

Apr 2023 – Jun 2023 · 2 mos

• Game Hub is a comprehensive web application built using React and TypeScript. This project is part of a project-based course offered by Code with Mosh, aiming to provide practical experience in developing modern web applications. The application is designed to create an engaging platform for gamers to explore and discover various video games.
• The application consumes data from the RAWG API, one of the largest video game databases that provide comprehensive details about games including titles, thumbnails, screenshots, videos, and many more. As part of the course, the project incorporates essential aspects of a modern web application including responsiveness, accessibility, and efficient state management, among others.

Apr 2023 – May 2023 · 1 mo

• PocketTrader is an automated trading bot for Alpaca's commission-free stock brokerage API. The bot enables seamless trade automation, asset checking, order management, technical analysis & position management, paper trading for strategy testing, and more!

Dec 2022 – Dec 2022 · 0 mo

• This project utilizes the LeNet convolutional network architecture to classify 43 different types of traffic signs. LeNet is a convolutional neural network that can be used for computer vision and classification models. LeNet (CNN) was designed to recognize handwritten digits. It was developed by Yann LeCun and his team at AT&T Bell Labs in the 1990s and is widely considered to be one of the first successful CNNs. LeNet consists of several convolutional and pooling layers, followed by fully connected layers. The architecture of LeNet has inspired many subsequent CNNs, and it is still widely used as a teaching tool for introducing the basics of CNNs to students and researchers. This project showcases a step-by-step implementation of the model and in-depth notes to customize the model further for higher accuracy.

Dec 2022 – Dec 2022 · 0 mo

• This project covers the topic of natural language processing, NLP, to classify user-generated text and determine its intent. The goal of this project is to build a model that can classify 10,000 Yelp reviews into either one-star or 5-star reviews. To accomplish this, the project uses NLP techniques to process and clean the text from the reviews, and then train the model using the clean text. The model is then evaluated and analyzed to measure accuracy and performance.

Dec 2022 – Dec 2022 · 0 mo

• This project utilizes an artificial neural network to perform a regression task, which means the model will predict a value based on the features. In this case, the model will have eight features to predict the purchasing amount for each customer. This project showcases a step-by-step implementation of the model as well as in-depth notes to customize the model further for higher accuracy.

Sep 2022 – Mar 2023 · 6 mos

• This project's objective is to design a system capable of gathering data from an array of sensors within a custom device, using this data to understand a patient's daily movement patterns and detect sleep apnea episodes. By offering more accurate and personalized treatment plans, this technology enhances the patient's quality of life and provides healthcare professionals with comprehensive insights into the patient's condition. Through this endeavor, I aim to showcase the potential of IoT and TinyML in healthcare and their impact on people's lives. I will utilize a combination of hardware and software to develop a custom system that collects data from multiple sources and employs machine learning models to identify sleep apnea.

Nov 2022 – Present · 3 yrs 7 mos · Greater Boston · Remote

• An educational platform designed for learning data structures and algorithms. Built using Next.js, React, and TypeScript, it aims to provide a structured learning environment with integrated LeetCode practice problems, progress tracking, and user customization.

Sep 2022 – Apr 2023 · 7 mos · Worcester, Massachusetts, United States · Remote

• The Sleep Apnea Detection System project aimed to create a comprehensive solution for monitoring and improving the health of individuals suffering from sleep apnea. The system combined machine learning, IoT hardware, and web development to gather data from various sensors and analyze it to understand a patient's daily movement patterns and the presence of sleep apnea. This information allowed for more accurate and personalized treatment plans for patients and provided healthcare professionals with detailed insights into the patient's condition.
• You can find the final project and related files here: https://github.com/redayzarra/homespace-capstone
• Developed a comprehensive Sleep Apnea Detection system, a crucial part of the overall project, by independently handling various aspects including machine learning, hardware, and software.
• Created a machine learning model utilizing TensorFlow and TinyML for efficient keyword spotting to control data collection.
• Programmed and integrated Arduino Nano 33 BLE Sense board with sensors to collect temperature, humidity, color, and audio data.
• Set up and configured Raspberry Pi hardware, developed code to process the collected data, analyze audio files for breath counting, and transmit the data to a MongoDB database.
• Conducted extensive testing and optimization to ensure the accuracy and reliability of the system, resulting in improved patient care and more informed healthcare professionals.
• Continuously explore new technologies and approaches to enhance the project's effectiveness and impact in the healthcare industry.