Skip to content
View jm2601's full-sized avatar

Block or report jm2601

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jm2601/README.md

Hello, I'm Javier πŸ‘‹

About Me

πŸ‘¨β€πŸ’» I'm a Software Engineer with a passion for coding and technology. My journey began in 2020, and since then, I've been continuously learning and growing in the tech space.

πŸŽ“ I recently graduated from the University of California, Merced in May 2024 with a Bachelor's degree in Computer Science and Engineering, where I honed my skills in Python, C++, Image Processing, Computer Vision, and Database Systems.

🌱 Currently, I'm focused on improving my expertise in Full-Stack Development and Machine Learning, and I'm always on the lookout for new and challenging projects.

πŸ”­ My latest project is LifeLine Aid, which is a mobile application that connects refugees with humanitarian aid. It was developed at CalHacks 2023 and received 1st Place for Best use of CockroachDB. Check it out here.

Technologies & Tools

  • Languages: Python, SQL, C/C++, HTML, CSS, JavaScript.
  • Frameworks & Libraries: React, Next.js, Flask, FastAPI, Node.js, pandas, NumPy, PyTorch, TensorFlow, scikit-learn, Matplotlib.
  • Tools: Git, Zsh/Bash/Unix/Linux, ArcGIS, MATLAB.
  • Databases: SQLite, CockroachDB, Firebase, PostgreSQL.

Projects

Here are some highlights from my portfolio:

As part of my internship with Omron Robotics and Safety Technologies, I implemented an 8-layer convolutional neural network (CNN) for leaf classification and anomaly detection in a cross-platform application. The CNN was trained on a dataset of 30,000 images to detect irregular patterns, such as bacterial infections and mold, achieving high precision in anomaly detection.

  • Technologies Used: TensorFlow, OpenCV, React Native, Firebase, Flask, Anaconda, Python
  • Outcome: Developed a real-time application allowing users to upload single or batch images for instant anomaly detection. This proof of concept demonstrated the potential of machine learning to automate quality control processes, with potential to reduce the time and costs associated with manual inspection.

Boasting a comprehensive database of UC Merced's Pavilion and YWDC's menu, this app guarantees to revolutionize the way you select your meals. With just a few taps, you'll be presented with a personalized meal suggestion tailored to your specific requirements - whether it's dietary restrictions, BMI, or target goals. The app even offers alternative options and shows you the nearest location to grab your healthy meal. Say goodbye to lengthy decision-making processes and hello to a simplified, efficient, and healthy lifestyle with our iOS app.

  • Technologies Used: React Native, SQLite, Flask, Python, pandas, Anaconda, Figma, Selenium, Node.js, Sqlalchemy
  • Outcome: Our team was clever enough to bypass the engineers that created the UC Merced Dining website. We created an SQLite database containing all the food:calorie information and we were able to successfully scrape the UC Merced Pavilion / YWDC Website. Our team made a back-end server with flask with routing that could communicate with the front-end. I successfully developed an initial version of our mobile app's front-end using React-Native. Our project won 1st Place at HackMerced!

This project was part of my data science summer internship. My team and I were tasked with evaluating multiple machine learning models for ECG data classification. We started doing binary classification between normal and abnormal heartbeats and moved to multi-class classification by labeling abnormal heartbeats with their underlying disease or condition.

  • Technologies Used: Sci-kit Learn, pandas, NumPy, PyTorch, Keras, Tensorflow, Python, Jupyter Notebook, Matplotlib
  • Outcome: I learned how to preprocessed and normalized complex datasets to boost model accuracy, employing hyper-parameter tuning and advanced preprocessing techniques for both supervised and unsupervised learning. I learned about various machine learning models for classification such KNN, Neural Networks, Random/Deep Forest, and XGBoost. I collaborated with Ph.D. and Masters students, showcasing our findings through a poster presentation for researchers and staff at Lawrence Livermore National Laboratories.

Feel free to check out more of my projects here.

Connect With Me

Thank you for visiting my GitHub profile!

Pinned Loading

  1. Bay-Valley-Tech-Code-Academy/EatsInReach Bay-Valley-Tech-Code-Academy/EatsInReach Public

    JavaScript

  2. UCMercedACM/flowspeak UCMercedACM/flowspeak Public

    A customizable app that helps non-verbal individuals, including those with autism, communicate using icons, text-to-speech, and predictive AI, offering emotional insights and support through LLMs.

    JavaScript 1

  3. Leaf-Classification Leaf-Classification Public

    Forked from ibarrx/Leaf-Classification

    CSE 120 Capstone Project

    Jupyter Notebook

  4. HealthyUC HealthyUC Public

    1st Place winning project at Hack Merced 2023 -> Devpost: https://devpost.com/software/healthy-uc

    JavaScript 2 1

  5. No767/lifelineaid No767/lifelineaid Public

    Cal Hacks 2023 app

    TypeScript

  6. HackmercedVII-Temp/zer0DayRepo HackmercedVII-Temp/zer0DayRepo Public

    Java 1