Computer/Information Science Engineer Student | Future-ready Cloud & AI Automation Enthusiast

• 🔬 Bridging AI research with scalable product development
• 🚀 Driving innovation in ML, cloud, and automation for real-world impact
• 🌐 Strong communicator; passionate about collaboration and continuous learning

Open to opportunities in: AI/ML Engineering • Full-Stack Development • Cloud Solutions • Technical Leadership

• Programming:

• AI & Machine Learning:

• Cloud Platforms:

• Development Tools:

• Databases:

ML-based cardiac arrhythmia detection and classification using ECG data with signal processing, feature extraction, and supervised learning models Detection & Classification of Cardiac Arrhythmia An AI-powered diagnostic tool for real-time ECG analysis and clinical reporting This repository implements a state-of-the-art ECG Arrhythmia Detection and Classification system. Designed for clinicians and medical researchers, it bridges the gap between raw signal data and actionable medical insights using advanced Machine Learning. 🔍 Multi-Source Input Support for ECG CSVs, high-res images, and manual physiological data. 🧠 Weighted KNN Intelligence Classifies 16 arrhythmia types with high precision using a pre-trained Weighted KNN model.

End-to-end remote-sensing pipeline for detecting and characterising subsurface water ice in the Faustini Permanently Shadowed Region using Chandrayaan-2 DFSAR compact-polarimetry SAR, OHRC imagery, Bayesian inference, and ML validation An end-to-end remote-sensing pipeline for detecting and characterising subsurface water ice in the lunar south polar Faustini Permanently Shadowed Region (PSR), using Chandrayaan-2 SAR compact-polarimetry SAR, OHRC high-resolution optical imagery, and machine-learning validation. Water ice trapped in lunar south-polar PSRs is a critical resource for future crewed missions — as drinking water, oxygen, and rocket propellant via electrolysis. Doubly Shadowed Craters (DSCs), craters nested inside a PSR whose floors receive no scattered sunlight, are the thermally coldest environments on the Moon and the highest-priority targets for ice characterisation. The Chandrayaan-2 SAR instrument (L-band, 1.25 GHz, compact polarimetry) provides ~2–5 m penetration into dry lunar regolith, making it the primary tool for detecting buried ice dielectric anomalies without contact drilling.

AI/ML pipeline for next-day forest fire probability mapping & multi-hour spread simulation using VIIRS satellite data, Random Forest, and Cellular Automata at 30m resolution over Uttarakhand, India Next-day fire probability maps + multi-hour fire spread simulation at ification, and vectorized Cellular Automata. The CA engine implements vectorised 8-neighbourhood spread using shifts — no Python loops over pixels. For each burning source cell spreading to a neighbouring cell in direction θ: Wind factor (directional alignment): Slope factor (uphill spread faster): Moisture factor (high humidity suppresses fire): All outputs are valid GeoTIFFs readable by QGIS, ArcGIS, GDAL, and rasterio. VIIRS footprint expansion: Each 375 m native VIIRS detection is rasterised as a disk of radius 6 pixels (180 m) at 30 m grid to account for geolocation uncertainty.

Full-stack console-based Java E-commerce application with MVC architecture, PBKDF2 password hashing, shopping cart, order management, and file-based persistence Welcome to the Java Learning Repository! This repository is dedicated to learning and mastering Java programming from basics to advanced concepts. 🚀 Data Structures & Algorithms Object-Oriented Programming (OOP) Java Development Kit (JDK) 8 or higher IDE: IntelliJ IDEA, Eclipse, or VS Code Basic programming knowledge (optional) Set up your IDE and start learning! If you find any issues or have improvements: This project is open source and available under the MIT License.

Forest fire spread simulation for Uttarakhand, India using NASA VIIRS satellite data, Copernicus DEM, and a Rothermel Cellular Automation model Physics-based fire spread simulation for the Uttarakhand region using satellite fire detections, terrain analysis, and a Rothermel-inspired Cellular Automaton model. Forest fires in Uttarakhand (Himalayan foothills, India) are a recurring ecological and humanitarian crisis. This project builds an end-to-end pipeline that: Builds a fire risk probability map from 5 years of historical VIIRS fire frequency (2019–2023) using spatial Gaussian smoothing — no ML training required. Simulates fire spread using a physics-based Cellular Automaton (CA) model driven by Rothermel fire-behavior equations, incorporating wind, slope, aspect, fuel load, and humidity.

Personal developer portfolio website showcasing projects, skills, certifications, and experience in AI/ML, cloud, and full-stack development. Deployed in AWS, Azure, GitHub pages A modern, responsive developer portfolio showcasing my projects, skills, and experience as a Computer Science engineer. Built with cutting-edge technologies and deployed across multiple cloud platforms for optimal performance and availability. If you'd like to suggest improvements or modifications: This project is licensed under the MIT License.

AI-based forest fire detection using satellite imagery and environmental data with supervised ML classification, accuracy benchmarking, and geographic hotspot visualization The system is designed to help with early wildfire detection and can be integrated into environmental monitoring systems. 🔥 Real-time fire detection in forest images 🧠 Deep CNN architecture for high accuracy 📱 Easy-to-use interface for predictions ⚡ Fast inference for real-time applications 🌍 Environmental protection focus The model is a Convolutional Neural Network (CNN) trained on a labeled dataset of forest images categorized as Fire 🔥 or No Fire 🌲. The network learns spatial features in the images to make binary classification predictions. It is actively maintained with clean code, thorough documentation, and follows software engineering best practices.

End-to-end Delhi air quality index analysis with time series decomposition, multi-source AQI data aggregation, trend forecasting, and interactive heatmap visualizations A comprehensive time series analysis and forecasting system for Delhi's air quality patterns, providing actionable insights for environmental monitoring and public health assessment. This project delivers an end-to-end analysis of Delhi's Air Quality Index (AQI) using advanced time series modeling techniques. By leveraging SARIMA forecasting and comprehensive statistical analysis, we uncover critical patterns in air pollution that directly impact over 30 million residents in the National Capital Region. It is actively maintained with clean code, thorough documentation, and follows software engineering best practices.

GitHub Pages hosted personal website and portfolio for Jaideep M C — Information Science Engineer and AI/ML enthusiast This project focuses on jaideep193.github.io with practical implementations using modern tools and techniques. It is actively maintained with clean code, thorough documentation, and follows software engineering best practices.

Alternate GitHub profile README for Jaideep M C — certificates, accomplishments, and developer identity Implements linear regression and documents performance metrics (MAE, RMSE) in Jupyter notebooks. Includes visual analytics (scatter plots, correlation matrices) and notebook-based workflow for reproducibility. Real-time attendance logging using face recognition and camera feeds. Detects and identifies individuals from live video, tagging attendance to a database with accuracy checks.

Production-ready distributed Go web app for GCP exposing GCE instance metadata via REST API, with Docker, Kubernetes (GKE), and Jenkins CI/CD pipeline 🚀 GCE Instance Metadata Service A distributed multi-tier Go application for Google Cloud Platform Frontend · Backend · Cloud-Native · Microservices This is a production-ready Go web application that demonstrates a distributed, multi-tier architecture for Google Cloud Platform (GCP). Please follow these steps: Follow Go conventions ( ) Add tests for new features Version Date Changes 2.0.0 2024 Enhanced features, optimized pipeline Copyright 2015 Google Inc. Jaideep193 - Cloud & DevOps Enthusiast 📧 Connect for collaboration and contributions ⭐ If you find this project helpful, please give it a star! ⭐ Made with ❤️ for the cloud-native community

Multimodal AI chatbot built with Streamlit and Google Gemini 2.0 Flash API — supports text, PDF, image, audio, and video interactions This project is a full multimodal AI chatbot built using Streamlit and Google Gemini 2.0 Flash API. It allows you to interact with text, PDFs, images, audio, and video files through a simple and intuitive web UI. It is actively maintained with clean code, thorough documentation, and follows software engineering best practices.

Linear regression model for house price prediction with EDA, outlier detection, hyperparameter tuning, and visual analytics using Jupyter Notebook 🚀 How to Run This project implements a machine learning solution for predicting house prices using linear regression. The model analyzes key housing features including: 📏 Square Footage - Living area in square feet 🛏️ Bedrooms - Number of bedrooms 🚿 Bathrooms - Number of bathrooms The solution demonstrates practical application of supervised learning techniques in real estate valuation and provides accurate price predictions across diverse property types. The project utilizes a comprehensive housing dataset ( ) containing: Square Footage Living area in square feet Bedrooms Number of bedrooms Bathrooms Number of bathrooms Price Target variable (house prices) The dataset provides diverse housing samples enabling robust model training and evaluation across different property types and price ranges. Project completed as part of SkillCraft Technology Machine Learning internship - Task 1 ⭐ If you found this project helpful, please consider giving it a star!

Automate compliant ad creation with AI-powered design generation - 100% FREE with custom ML model! ADGENESIS is an AI SaaS platform that helps marketers and designers create platform-compliant advertisements in seconds. Upload your brand guidelines, describe your ad concept, and let AI generate professional designs that meet platform requirements (Meta, Google, LinkedIn). NEW: Now powered by a custom fine-tuned ML model - generate unlimited ads for FREE with zero OpenAI costs! Latest version includes manual object rendering Canvas now properly scales 1080x1080 designs to 800x800 display Background colors render correctly Fixed!

K-Means clustering model for customer segmentation using Mall Customers dataset with feature engineering and cluster visualization This project implements a comprehensive K-means clustering algorithm to segment customers of a retail store based on their demographic and spending characteristics. The analysis uses the MallCustomers dataset to identify distinct customer groups for targeted marketing strategies and business insights. The comprehensive analysis provides actionable insights for business strategy development, with multiple visualization approaches making the results accessible to both technical and non-technical stakeholders. The identified customer segments enable data-driven decision making for marketing, product development, and customer relationship management initiatives.

Big data analytics on e-commerce datasets including Brazilian Olist marketplace data — data processing, insights, and exploratory analysis This project focuses on bigdata with practical implementations using modern tools and techniques. It is actively maintained with clean code, thorough documentation, and follows software engineering best practices.

Real-time hand gesture recognition system using MediaPipe and OpenCV that controls media playback via keyboard commands A real-time hand gesture recognition system that enables touchless media control using computer vision. Control your media playback, volume, and other functions with simple hand gestures captured through your webcam. How It Works This project leverages MediaPipe for hand tracking and gesture detection to provide an intuitive, touchless interface for controlling media playback. The system recognizes various hand gestures in real-time and translates them into keyboard commands for media control.

Real-time facial recognition attendance system using OpenCV with live camera feed, automated CSV/Excel log export, and database tagging A Python-based Attendance Management System using Face Recognition (OpenCV + Machine Learning). Automatically recognizes faces from a webcam to mark attendance in real-time, saving the results in a CSV file! 🖼️ Face Detection & Dataset Creation: Capture face images from a webcam and organize them into structured user folders. 🧑‍🏫 Model Training: Train a robust LBPH (Local Binary Patterns Histograms) recognizer on your dataset for identification.

• NVIDIA Certified Associate: Generative AI & LLMs - Demonstrated expertise in leveraging large language models and generative AI architectures for real-world applications
• Microsoft Certified: Power Platform Fundamentals - Proficient in Power Apps, Power Automate, and Power BI for business solutions
• Microsoft Certified: Azure Fundamentals - Foundation-level knowledge of Azure cloud services and infrastructure
• Microsoft Certified: Azure Data Fundamentals - Expertise in data concepts, data analytics, and BI fundamentals on Azure
• Oracle Certified: Data Science Professional - Demonstrated knowledge of ML algorithms, data preprocessing, and model evaluation
• Oracle Certified: Generative AI Professional - Specialized skills in implementing generative AI solutions on Oracle Cloud

✅ Machine Learning Projects: Developed 4+ production-grade ML models with >85% accuracy in classification tasks ✅ Real-Time Computer Vision: Built facial recognition and forest fire detection systems using OpenCV and deep learning ✅ Cloud Infrastructure: Architected and deployed cloud solutions on Azure, GCP, and Oracle Cloud platforms ✅ Time Series Analysis: Implemented advanced forecasting models for air quality and environmental data ✅ Full-Stack Development: Created end-to-end web applications using React, Node.js, MongoDB, and modern DevOps practices ✅ Code Contributions: Consistent GitHub activity with 100+ commits demonstrating continuous learning and improvement ✅ Technical Documentation: Maintained comprehensive README files and project documentation for portfolio projects

• Google Cloud Skills Boost: Advanced practitioner with multiple cloud certifications
• Proficient in Data Science, Machine Learning, Cloud Computing, and Full-Stack Development
• Strong expertise in Python, JavaScript, and modern development tools

See my full portfolio and contributions on GitHub

Connect professionally and explore career opportunities

View my Google Cloud Skills Badges and certifications

Reach out for collaborations and opportunities

✨ "Innovation through Intelligence • Impact through Code • Future through AI" ✨