Leveraged Knowledge in Node JS, React JS, Python, MaterialUI, Java, Rails, Rest API, and Debugging
Leveraged Knowledge in React JS, Redux, MaterialUI, Ant Design, PostgreSQL, Java, Android SDK, JUnit, DI, Rest API, Amazon AWS S3, Firebase, Google Map
Leveraged Knowledge in Java, Grails, Android, Node JS, React JS, Vue JS, Redux, React Native, MySQL, Rest API
Leveraged Knowledge in PHP, Java, Ember JS, Bootstrap, MSSQL, Microsoft SSIS, Android SDK, JUnit, Angular JS, Rest API
Algorithms | Software Engineering | Machine Learning | Artificial Intelligence | Cryptography | Distributed System | Data Mining | Natural Language Processing
Data Structure and Algorithms | Programming in C, C++, Java, Python | Database Management System | Computer Networks | Operating System | Software Engineering | Computer Architecture | Computer Graphics | Microprocessor | Computer Organization and Architecture | Theory of Computation | Numerical Methods | Probability and Statistics | Discrete Mathematics
MUAC: Multi-User Access Control website and mobile application built using React and React Native for the research project.
Utilized: React JS, React Native, Redux, Express JS, Node JS, Git
I developed an web application dedicated to Do-It-Yourself (DIY) projects, aiming to empower users with step-by-step guides for creating various innovative projects independently.
Utilized: Rails, Bootstrap CSS, PostgreSQL, Git, Figma
GitHub: https://github.com/sagar-pathak/electro-lab
A Machine Learning Approach to Anomalous Financial Transaction Detection using SWIFT synthetic dataset.
Utilized: Python, Numpy, SciPy, Git, Jupyter Notebook, Google Colab
Github: https://github.com/sagar-pathak/financial-crime-detection
Paper: Available on Google Scholar
This research project presents the implementation of a Deep Q-Learning Network (DQN) for a self-driving car on a 2-dimensional (2D) custom track, with the objective of enhancing the DQN network's performance. It encompasses the development of a custom driving environment using Pygame on a track surrounding the University of Memphis map, as well as the design and implementation of the DQN model. The model was trained over 1000 episodes, and the average reward received by the agent was found to be around 40, which is approximately 60% higher than the original DQN and around 50% higher than the vanilla neural network.
Utilized: Python, Tensorflow, Keras, Pandas, Numpy, Git, Jupyter Notebook, Google Colab
Source Code: https://github.com/sagar-pathak/rl-dqn-2d-car-racing
Paper: https://arxiv.org/pdf/2402.08780
This project aims to classify customers into high, medium, and low churn risk categories.
Source Code: https://github.com/sagar-pathak/customer-churn-prediction