Suresh Kumar

AI-DRIVEN SMART HEALTHCARE SYSTEM WITH EDGE COMPUTING Term Meaning (Simple Explanation) AI (Artificial Intelligence) Teaches the computer to act smart — like detecting health problems. Smart Healthcare Using technology to monitor and improve health automatically. Edge Computing Instead of sending all data to the cloud (internet), we process it on a small local computer like a Raspberry Pi (you’ll simulate this in software). Monitoring System A tool that checks patient health continuously and gives warnings if there’s a danger. WHAT DOES THIS PROJECT DO? • Imagine a patient is wearing a smart band that sends data like heart rate or oxygen level to your system. • Your software will: • Collect health data (like heart rate, oxygen) – you’ll simulate this. • Check if the health data is dangerous (using ai). • Send alerts if a health issue is detected (example: low oxygen). • Store health history in cloud storage. • Show this information in a mobile app for patients and doctors. WHAT YOU NEED TO BUILD (SOFTWARE ONLY) 1. Data Simulation (Fake Sensors) Example: If heartbeat is too high or low → it will trigger a warning. Use Python to generate random, realistic health data like: •Heartbeat (ECG) → 60–100 bpm •Oxygen level (SpO2) → 95– 100% 3. Backend Server (Optional but useful) Use Flutter (easy and works on both Android/iOS) or Java (Android). 2. AI-Based Detection Use machine learning (AI) in Python. Create a simple backend using Python Flask or Node.js. It will send the health data from Python to your app or Firebase. Teach it what is “normal” and what is “dangerous”. The app shows: Firebase will store: •Real-time health data •Graphs (charts) •Alerts (if AI detects danger) •Login screen for security •Health history (time, data) •Login and password info •App messages 5. Firebase Cloud Storage 4. Mobile App (Required) 5. TIMELINE (SOFTWAR E-ONLY) Phase Duration Task Phase 1: Planning & Design 1 Week Confirm scope, create UI mockups, architecture Phase 2: Simulated Sensor + AI 1 Week Python script to simulate ECG/SpO2, apply ML model Phase 3: Backend APIs + Firebase 1 Week Setup Firebase DB, write REST API using Node.js/Python Phase 4: Mobile App (Flutter or Android) 2 Weeks Real-time charts, alerts, login, trend analysis Phase 5: Security (OAuth, JWT) 3 Days User authentication and encrypted communication Phase 6: Testing & Debugging 1 Week Test all modules: app, API, AI prediction, data sync Phase 7: Documentation + Handover 3 Days Technical report, code comments, deployment help Home Screen (Live Data) DESIGN INSPIRATION BASED Circular progress bar for Oxygen (SpO2) Digital meter for Heart Rate "Status" text: Normal / Critical Button: View History / Settings Graph of last 24 hours History Screen Alerts Screen Table: Time, SpO2, HR Export PDF (optional) Red background Message: “Critical Condition Detected!” Emergency call option (optional) Login Screen Firebase Email/Password login Register, Forgot password buttons SYSTEM ARCHITECTURE OVERVIEW (SIMULATED) The system consists of three major components: 1. Simulated health data generator (python): continuously produces heart rate and spo2 data. 2. AI/ML engine (python): processes this data and checks for abnormal patterns. 3. Mobile app (flutter/java): displays data, alerts, history, and communicates with firebase.