Hello,

I am

Advay

Linkedin

"If something is important enough, even if the odds are against you, you should still do it."



- Elon Musk

img

About me

Visionary/Student/Researcher/Developer

Hi! I am currently a Senior at Edison High School, and I am interested in Artificial Intelligence and Machine Learning. I hope to learn complex Neural Networks to help me contribute to next-generation transportation and energy sources. I am skilled in Python and Java, and I founded the "Computer Club," a club to teach students programming, at my school. I am also involved in the UNICEF club and am a part of the school's Robotics team. I also play soccer and tennis and cook/bake in my freetime.

Skills

I have been programming consistently for around 5 years and have experience in Python, Java, HTML, CSS, and Javascript. Recently, I have been more focused on Data Science and Machine Learning, so I have been more heavily focused on Python

Artificial Intelligence/ Machine Learning

I have a udemy certification for Data Science/ Machine Learning and have created various projects with Python. I am skilled at feature engineering with Pandas abd Numpy, and also have experience in data visualization with MatplotLib and Seaborn. In Machine Learning, I have used libraries like Scikit Learn and Tensorflow as well as Computer vision libraries like OpenCV and Mediapipe.

Web Devlopment

I am skilled in HTML and CSS and know some Javascript. I created a personal blogging platform called Limitless using these languages. I also have experience using Python frameworks like Flask and Django. I used Flask to create a webpage for my skin disease detection project.

Leadership

I am an avid leader with dynamic interpersonal skills and excellent analytical and multi-tasking abilites. I founded and am the President of my school's Computer Science Club, am the President of my school's UNICEF Club, and am Co-Head Coder of my schools Robotics Team. I also hold board positions in my school's Assertive Teens Against Cancer Club and Science National Honors Society.

Research

I am currently working on a research project under Professor Mohite from Rice University. I have experience analyzing research papers and implimenting computational design to make prediction algorithms. I am working on feature engineering data to create an accurate prediction model.

Projects

Perovskite Data Science Project

Working under Professor Mohite from Rice University

Responsible for feature engineering Perovskite dataset using Python (Pandas, NumPy); Using PubChem API to access CID information and other properties of the 2D perovskite cations; Using methods like one-hot-encoding to create more advanced features in the dataset; Working on creating a neural network that can accurately classify newly synthesized 2D perovskites and predict their properties.

img

Skin Disease Classification

Link to Project Details

This application allows the user to capture an image of a skin mark on their body, and it predicts what the mark may be into 1 of 10 skin-disease categories. The web app also consists of hyperlinks so that the user can look into what the predicted skin mark is and take the right course of action. To build the application, I primarily used Python. I created the front-end using HTML and CSS, and I also used Flask to create a backend. To classify the image that the user captured and predict what it is, I used TensorFlow and made my own Convolutional Neural Network with approximately 75% accuracy. I also used OpenCV to display a webcam on the web application and allow the user to capture an image in real-time.

img

Predicting the Region of Origin of COVID-19 Variants

Link to Presentation

Meant to improve public health by predicting a SARS-CoV-2 lineage's country of origin using its genome; Takes various samples of the SARS-CoV-2 virus and their specific regions to help determine the possible region of origin of a different strand of the virus. A multinomial logistic regression model is used to predict the region of origin of a specific strand of a SARS-CoV-2 virus; The ML model has an accuracy between .93 and .98.

img

Graffiti Detection (Surveillance System)

Link to Presentation

Helps solve the problem of graffiti as the issue can be addressed more easily and efficiently; graffiti is typically left unreported for several months.; Utilizes a Convolutional Neural Network (ResNet50) to determine whether an image contained graffiti or not; Also used OpenCV to perform real-time detection of the graffiti.

img