G.
PULLAREDDY ENGINEERING COLLEGE(Autonomous):Kurnool
Affiliated to JNTUA,Ananthapuramu
DEPARTMENTOFELECTRONICSANDCOMMUNICATIONENGINEERING
BATCH NO:13 SEMESTER:VII SECTION:C
MAJOR PROJECT TITLE:
AI-ENABLED EMERGENCY AMBULANCE DISPATCH VIA TELEGRAM AND IOT
PROJECT BATCH:
NAME: ROLL NO:
SHAIK AFRA NYSH 229X1A04E4
K SRAVANI SURYA LAKSHMI 229X1A0412
K VENKATESH NAIK 229X1A04A4
PROJECT GUIDE: HEAD OF THE DEPARTMENT:
C.Rajeshwari,M.Tech,Ph.D Dr.S.NagarajaRao,M.Tech,Ph.D
Assistant Professor, Professor,Head of the Department,
Department of ECE, Department of ECE,
GPREC,Kurnool. GPREC,Kurnool.
ABSTRACT
This project, Artificial Intelligence and Telegram Channel Integrated Ambulance System,
presents an innovative approach to enhancing emergency medical services through intelligent
automation and real-time communication. The system utilizes AI algorithms to automatically
classify incoming emergency requests, prioritize them based on severity, and assign the nearest
available ambulance. By analyzing live traffic conditions and historical route data, it optimizes
dispatch routes to ensure the fastest possible response times.
A dedicated Telegram channel serves as a user-friendly platform for patients and caregivers to
request assistance, receive immediate acknowledgments, and track ambulance locations in real
time. This integration streamlines coordination among dispatch centers, medical teams, and
patients, significantly reducing delays and improving the quality of care provided during
emergencies. The solution offers a scalable, cost-effective framework adaptable to both urban
and rural healthcare networks.
Software:
Python – for AI algorithms and backend logic
TensorFlow / scikit-learn – for machine learning models (e.g., request classification, route
optimization)
Telegram Bot API – for integrating the Telegram channel communication
Google Maps API / OpenStreetMap – for live location tracking and route planning
Firebase / MySQL – for database management and storing emergency records
Flask / Django – for developing the web server and APIs
Docker – for containerizing and deploying the application
Git – for version control
BLOCKDIAGRAM:
Hardware Requirements
🔹 Sensors (Vital Sign Monitoring):
SPO2 Sensor (e.g., MAX30100) – oxygen saturation
Heartbeat Sensor (e.g., AD8232)
Respiratory Rate Sensor (e.g., Piezoelectric sensor or thermistor-based)
Temperature Sensor (e.g., LM35 or DS18B20)
🔹 Processing Board:
AI Board / Microcontroller / Microprocessor (e.g., Raspberry Pi, Arduino with AI Edge,
NVIDIA Jetson Nano)
Alternatively, the LSAI48266x (or any AI-capable development board in your
simulation)
🔹 Connectivity Modules:
Wi-Fi / GSM Module (e.g., ESP8266, SIM800L) for IoT communication
GPS Module (e.g., Neo-6M) for live location tracking
🔹 Display Unit:
LCD / OLED screen to show patient vitals
🔹 Power Supply:
5V / 12V regulated power supply (depending on board)
Battery backup (optional for mobile use)
Software Requirements
🔹 Programming Languages:
Python (for AI logic, data handling, and APIs)
C/C++ (if using Arduino)
🔹 AI & Data Processing Libraries:
TensorFlow or PyTorch (for model development)
scikit-learn (for data classification)
NumPy, pandas (data handling)
🔹 Communication & APIs:
Telegram Bot API (messaging and notifications)
Google Maps API or OpenStreetMap API (route tracking)
🔹 Database:
Firebase Realtime Database or MySQL (storing patient and ambulance data)
🔹 Web / Backend Frameworks:
Flask or Django (to create REST APIs)
🔹 Simulation / Visualization Tools:
Proteus or Fritzing (circuit simulation, optional)
Node-RED (IoT flows)
Grafana (for real-time dashboards, optional)
🔹 Version Control:
Git
