🪨 Machine learning project using logistic regression to classify sonar signals as either rocks or mines. Uses scikit-learn to train a binary classifier on sonar dataset with 60 numerical features for accurate underwater object detection.

A real world crypto currencies streaming and analysing using kafka through snowflake.

Seatbelt detection using YOLOv5 ML model

Explore Transformer architecture, token-by-token generation, and LLM training through hands-on Python notebooks training workflows with Phi-3.

Fine-tuning OpenAI's Whisper model on Persian speech datasets for enhanced automatic speech recognition (ASR) performance.

Machine Learning as a Service for HEP

An intelligent machine learning application that predicts student exam scores and provides personalized recommendations for academic improvement using advanced AI and data analytics.

🏡 A Flask-based machine learning application that predicts Boston housing prices with elegant precision. Features real-time predictions, a interface, comprehensive documentation, and production-ready deployment.

A Machine Learning model created using prebuild model. We need to feed the images to the model and it will predict if the same person is there else it will mark as unknown.

Animal Classification: A CNN-based image recognition model.

Forecasting the crime in a city from OSN data

This is an end-to-end ML project, which aims at developing a classification model for the problem of predicting credit card frauds using a given labeled dataset. The classifier used for this project is RandomForestClassifier. Deployed in Heroku.

Group project for Hackathon

The Smart Crop Disease Detection System is a Django web app that uses machine learning to identify crop diseases from leaf images. It helps farmers detect diseases quickly and take action to protect their crops. The system features AWS S3 image storage, TensorFlow Lite integration, and a responsive front-end for easy use.

EY Hackathon Project

BioSim model with Conditional Variational Autoencoder

to predict the survival of the fittest.

Comment Toxic Analyzer build on machine Learning algorithm (Random Forest) capable to analyze toxicity present in comment or any text with the accuracy of around 83%

SugarSense : The Diabetes Prediction Application

Predict the winning team of IPL matches using XGBoost and Flask, powered by historical data from 2008–2024.