This website showcases my Projects, Acheivements, Blogs,Publications and articles.
Hello, I’m Mayank Vyas, a master’s student in Data Analytics at Arizona State University. I specialize in data science, machine learning, and AI-driven solutions for real-world problems. Explore my portfolio to learn more about my projects, experience, and skills.
This Project contains an implementation of a Multi-Layer Perceptron (MLP) from scratch using Python. It demonstrates the fundamental concepts of building and training a neural network, including forward propagation, backward propagation, and parameter optimization.
This Projects provides an end-to-end data analysis framework, utilizing the Yelp dataset to gain actionable insights into business performance. The code demonstrates how to scrape, process, query, and analyze data stored in JSON format, providing powerful business-level analytics.
The project "Intersection Control using Reinforcement Learning and SUMO" focuses on optimizing traffic flow at urban intersections by leveraging reinforcement learning algorithms. The system uses the SUMO (Simulation of Urban MObility) tool to simulate real-world traffic scenarios and applies reinforcement learning to control traffic lights dynamically. The goal is to improve traffic efficiency by reducing congestion and enhancing overall traffic management in smart city environments. The project demonstrates how AI can be used to optimize urban mobility and provide intelligent solutions for real-time traffic control.
The project "Root Phenotyping" utilizes deep learning techniques for automated root detection and phenotyping in plants. By implementing the Mask R-CNN architecture, the system segments and identifies plant roots from high-resolution images, providing accurate measurements of root length and structure. The goal of this project is to improve the efficiency and accuracy of root phenotyping in agricultural research, enabling better understanding of plant growth and aiding in crop improvement studies. The project showcases the use of computer vision and deep learning in agricultural science for automated analysis of root systems.
The project "Intelligent Image Forwarding" focuses on optimizing the process of forwarding images in a network based on their content and context. By employing machine learning techniques, the system intelligently classifies and prioritizes images, ensuring efficient and relevant forwarding based on predefined criteria. This project aims to enhance network performance by reducing bandwidth usage and improving the speed of image transmission. It demonstrates how AI can be used to optimize communication systems, particularly in environments with limited resources or high network traffic.
The project "Tele_bot" is a Telegram-based bot that automates tasks and provides interactive functionalities within the Telegram messaging platform. It utilizes the Telegram Bot API to enable users to perform various operations like sending automated messages, fetching data, and integrating with external services. The bot can be customized to handle different commands and interactions, offering a user-friendly interface for executing specific tasks. This project showcases how bots can be used to automate processes, enhance user engagement, and integrate applications with messaging platforms like Telegram.