Ujan Pradhan

Tech enthusiast student with a strong work ethic and a passionate about AI-ML,Software Development & Finance.Independent Researcher and exploring various fields of technology.Seeking SDE/AI/Data Science intern roles to apply knowledge and gain practical experience.

• Google Developer Society Wow 23 Hackathon, Chennai Runners-Up
• IEEE SRM SB TechTrack 24 Hackathon Winner
• Smart India Hackathon 23 Internal Round Finalist, SRM Hackathon 7.0 Finalist
• Academic Scholarship from SRM University
• Qualified Pre-Regional Mathematical Olympiad (PRMO) & National Talent Search Examination Stage-I from WB-State List

• Analyzing Land Submergence Impact on Temperature Using Random Forest Regression and Explainable AI Techniques, Ujan Pradhan, M.N. Aditya, Dr. Rajkumar R., ACOIT'24, 2024, Accepted for presentation at ACOIT'24, 2024. Proceedings to be published in IEEE Xplore
• Handwriting Improvement Using Optical Character Recognition and Reinforcement Learning, Ujan Pradhan, M.N. Aditya, IEEE TALE, 2024, Accepted for presentation at IEEE TALE, 2024. Proceedings to be published in IEEE Xplore

IEEE SRMIST Student Branch - R&D Domain Member 

SRM Electronics Club - Machine Learning Domain Lead

Hybrutos Racing - Web-Developer & Corporate Affairs Member

• 3D Brain Tumor Detection Using Vision Transformers and Explainable AI, Brain tumor detection using Vision Transformers (ViT) for highly accurate image analysis, combined with Explainable AI (XAI) techniques such as Grad-CAM, LIME, and SHAP to provide transparency and interpretability in predictions. A U-Net model is employed for precise segmentation of brain tumors, while advanced 3D visualizations, dynamic colored graphs, and GIFs are used to enhance the representation of tumor regions
• Minimal NeRF Implementation with JAX and Flax, Implementation of Neural Radiance Fields (NeRF) using the JAX and Flax libraries. NeRF is a technique for generating 3D scene representations from 2D images by modeling how light interacts with objects to create photorealistic renders
• Emotion Recognition from Audio Speech, Speech Emotion Recognition (SER) model using LSTM layers, NLP techniques and deep learning to classify speech recordings into 6 emotions (fear, angry, disgust, neutral, sad, happy)
• Video Anomaly Detection, It is a video-processing project using DenseNet121 Transfer Learning to detect 14 categories of abnormal situations in video with an accuracy of 91.53 %
• Agro Tech Nexus, Developed an all-in-one solution for farmers, including crop-price prediction, weather alerts, cold-storage information, market access transportation, a tool marketplace, and chat-bot/phone-based assistance