Phaneesha Chilaveni's Projects
This project involves analyzing genome data to identify genetic variations associated with autism and using machine learning algorithms such as random forest, GBM, Adaboost, and XGBoost to detect autism from genetic markers. The project includes comparing the performance of these algorithms.
This project uses deep learning to classify clothing items in the Fashion-MNIST dataset, with a focus on accuracy and performance evaluation using various techniques.
Using Python, Streamlit, PyDeck, and GCP, we created a web app for analyzing NYC collision data. We extracted data from NYC Open Data, analyzed it with BigQuery, and visualized results with Looker Studio. The app provides insights for stakeholders to help improve road safety in NYC.
Adding two numbers and giving the output in binary form
Using power method to find dominant Eigen values for a nxn matrix
Chinook database SQL queries
The goal of CLAIMED is to enable low-code/no-code rapid prototyping style programming to seamlessly CI/CD into production.
Crime is an integral aspect of our society; whether as a victim or an offender, everyone has been witness to a crime. In our project, we analyzed crime data, and I haveΒ chosenΒ the "Chicago Criminal dataset report," which contains crime episodes in Chicago from 2001 to the present. We looked at crime patterns over time, crime hotspots.
"Deep-Learning-with-PyTorch-Object-Localization" is a project that harnesses the power of deep learning and PyTorch to achieve precise object localization in images. Explore the cutting-edge techniques and enhance your computer vision skills with this hands-on project.
The project is about teaching an agent to navigate a grid environment using reinforcement learning and SARSA algorithm, with rewards and penalties for reaching certain positions and colliding with obstacles. It includes a GridEnvironment class, SARSA_Agent function, and a render function to display the learning process.