Large-Scale Multi-Class Image-Based Cell Classification with Deep Learning

Health Buddy is a web application that provides essential medical assistance, including predicting brain tumors, detecting retina problems, and finding nearby doctors. With a chatbot feature and AI-powered suggestions, it aims to improve the healthcare experience for users.

Real time Object detection: object detection system to enhance pedestrian safety and assist visually impaired individuals in navigating urban environments through real-time obstacle detection and alerts.

set of algorithms performed to carry out the analysis of the "thyroid-disease" database published in the UCI page

A novel feature selection algorithm using ACO-Ant Colony Optimization, to extract feature words from a given web page and then to generate an optimal feature set based on ACO Metaheuristics and normalized weight defined as a learning function of their learned weights, position and frequency of feature in the web page. JAVA based ACO Framework

Report on the performance of different machine learning algorithms in identifying persons of interest in the Enron Fraud Case

This repo includes complete end to end algorithm for dog breed classification mechanism using deep learning.

This project aims to develop a robust classification model using test-takers' demographics and questionnaire responses from the ASD screening dataset to accurately identify individuals with Autistic Spectrum Disorder (ASD) through optimization of performance metrics.

Study of the paper "On the Optimality of the Simple Bayesian Classifier under Zero-One Loss" by Domigos and Michael Pazzani of the University of California published for the "Machine Learning" international forum in 1997.

Classificateur de plantes médicinales basé sur RandomForest. Prédiction binaire avec explications et métriques complètes (accuracy, F1, ROC). Interface web interactive.

Hoax Analyner use KNN and Multinomial Naive Bayse

White and Red Wine classification using logistic regression

Predicting Next Booking Destinations for Airbnb Users. Feel free to access the Streamlit App in the link below.

Classification & Feature Selection for predicting blood glucose variability in Type 2 Diabetes

ML Classification Project

Big Data ML project to predict patient no-shows at clinics by building a Data Science pipeline on Databricks.

Welcome to my Data Science Portfolio! I'm Saravanan — an IITM Pravartak Certified Data Science Professional with practical experience building end-to-end ML and Deep Learning solutions across healthcare, finance, e-commerce along with NLP and GEN AI Domains. This portfolio highlights my work on real-world data-driven projects.