🤖 AI Smart Automated Light Control System

An AI-powered smart lighting system that reduces energy consumption by 30-50% using machine learning, real-time optimization, and weather integration.

🛠️ Built With

2.mov

🎯 Key Features

• AI-Powered Predictions: 85-96% accuracy occupancy prediction using Random Forest
• Real-time Control: WebSocket-based live updates across web and mobile
• Weather Integration: Automatic brightness adjustment based on weather conditions
• Energy Analytics: Real-time monitoring with 30-50% energy reduction
• Cross-Platform: Web (React) and Mobile (React Native/Expo) applications
• Production Ready: Deployed on Vercel (frontend) and Render (backend)

📊 Results

• Energy Reduction: 30-50%
• Cost Savings: $150+ per month
• AI Accuracy: 85-96%
• CO₂ Reduction: ~45 kg/month

🌐 Live Demo

• Web App: ai-smart-automated-swight.vercel.app
• API: ai-smart-automated-swight.onrender.com

🚀 Quick Start

Prerequisites

• Python 3.11+
• Node.js 18+

Installation

# Clone repository
git clone https://github.com/DavidOmokagbor1/Ai_smart_Automated_Swight.git
cd Ai_smart_Automated_Swight

# Backend setup
cd backend
pip install -r requirements.txt
cp env.example .env
# Edit .env with your configuration

# Frontend setup
cd ../frontend
npm install

# Run
python app.py  # Backend on :5000
npm start      # Frontend on :3000

🏗️ Tech Stack

Frontend: React 18, Tailwind CSS, Socket.IO Client, Recharts
Backend: Flask, Flask-SocketIO, SQLAlchemy, Scikit-learn
Mobile: React Native, Expo
Deployment: Vercel, Render
Monitoring: Datadog, MonitorUptime Robot
APIs: OpenWeatherMap

📁 Project Structure

├── backend/     # Flask API + ML models
├── frontend/    # React web app
├── mobile/      # React Native app
└── docs/        # Documentation

📚 Documentation

• System Overview
• Weather API Setup
• Datadog Setup
• Security Guide
• Deployment Guide

📝 License

MIT License

👨‍💻 Author

David Omokagbor
GitHub: @DavidOmokagbor1