AI-Based Smart Health Monitoring System using ESP8266

📘 Project Overview

AI-Based Smart Health Monitoring System

The AI-Based Smart Health Monitoring System is an educational project designed for Atal Tinkering Labs (ATL), STEM laboratories, schools, and beginner IoT learning.

The project combines the concepts of:

Internet of Things (IoT)
Artificial Intelligence (AI)
Sensors
ESP8266 Programming
Wi-Fi Communication
Data Collection
Data Analysis

The system uses sensors to collect environmental and pulse-related sensor readings. The ESP8266 NodeMCU processes these readings and can display the information through the Serial Monitor or an OLED display.

Because the ESP8266 has built-in Wi-Fi capability, the system can also transmit data to an IoT dashboard or web application.

The collected data can later be used for artificial intelligence and machine learning experiments. For example, students can collect sensor readings over time, create a dataset, and use Python to study patterns and build a simple machine-learning model.

Educational Data Flow
Sensors
↓
ESP8266 NodeMCU
↓
Data Processing
↓
OLED / Serial Monitor
↓
Wi-Fi Communication
↓
Data Storage
↓
AI / ML Analysis
↓
Educational Prototype Status

This project helps students understand how modern technologies such as IoT, sensors, cloud computing, programming, and artificial intelligence can work together.

Important: This project is intended only for education and experimentation. It should not be used for medical diagnosis or treatment decisions.

🎯 Objective

The main objectives of the AI-Based Smart Health Monitoring System are:

1. To understand the working of sensors and microcontrollers.

2. To collect temperature and pulse-related sensor data.

3. To learn how the ESP8266 NodeMCU processes sensor information.

4. To display sensor readings on the Serial Monitor or OLED display.

5. To understand Wi-Fi-based IoT communication.

6. To collect sensor readings for creating a dataset.

7. To introduce students to artificial intelligence and machine learning concepts.

8. To analyze patterns in collected data using software tools.

9. To develop an interdisciplinary STEM and ATL learning project.

10. To demonstrate the integration of Artificial Intelligence and Internet of Things technologies.

🔧 Required Components

1. NodeMCU ESP8266 – 1

2. Pulse Sensor – 1

3. DHT11 Temperature and Humidity Sensor – 1

4. OLED Display 0.96 inch (Optional) – 1

5. Breadboard – 1

6. Jumper Wires – Required

7. USB Cable – 1

8. Computer or Laptop – 1

9. Wi-Fi Connection – Required for IoT features

10. Arduino IDE Software – Required

🔌 Wiring & Connections

| Pulse Sensor | NodeMCU ESP8266 |
| ------------ | --------------- |
| VCC | 3.3V |
| GND | GND |
| Signal | A0 |

| DHT11 | NodeMCU ESP8266 |
| ----- | --------------- |
| VCC | 3.3V |
| GND | GND |
| DATA | D4 |

📺 OLED Display
OLED Display NodeMCU ESP8266
VCC 3.3V
GND GND
SDA D2
SCL D1

PULSE SENSOR

VCC → NodeMCU 3.3V
GND → NodeMCU GND
Signal → NodeMCU A0

DHT11 SENSOR

VCC → NodeMCU 3.3V
GND → NodeMCU GND
DATA → NodeMCU D4

OLED DISPLAY

VCC → NodeMCU 3.3V
GND → NodeMCU GND
SDA → NodeMCU D2
SCL → NodeMCU D1

IMPORTANT:

All components must share a common GND connection.

🔗 Circuit Diagram

Circuit diagram will be added soon.

⚙️ Working Principle

The AI-Based Smart Health Monitoring System works by collecting data from connected sensors.

Step 1: The DHT11 sensor collects temperature and humidity data.

Step 2: The pulse sensor provides a pulse-related analog signal to the NodeMCU.

Step 3: The NodeMCU ESP8266 reads the sensor signals.

Step 4: The microcontroller processes the received sensor data.

Step 5: The sensor values are displayed on the Serial Monitor or an OLED display.

Step 6: Using the built-in Wi-Fi capability of the ESP8266, the data can be transmitted to an IoT platform or web dashboard.

Step 7: Sensor readings can be collected and stored as a dataset.

Step 8: The collected dataset can be analyzed using Artificial Intelligence or Machine Learning techniques.

Step 9: A trained educational model can classify patterns in the collected prototype data.

Thus, the project demonstrates the complete flow from sensors to IoT communication and AI-based data analysis.

💻 Arduino Source Code

#include <DHT.h>

// DHT11 Configuration
#define DHTPIN D4
#define DHTTYPE DHT11

// Pulse Sensor
#define PULSE_PIN A0

DHT dht(DHTPIN, DHTTYPE);


void setup() {

  Serial.begin(115200);

  dht.begin();

  Serial.println();
  Serial.println("================================");
  Serial.println("AI HEALTH MONITORING SYSTEM");
  Serial.println("Educational ATL Prototype");
  Serial.println("================================");

}


void loop() {

  // Read temperature

  float temperature = dht.readTemperature();


  // Read humidity

  float humidity = dht.readHumidity();


  // Read analog pulse sensor signal

  int pulseValue = analogRead(PULSE_PIN);


  Serial.println();
  Serial.println("--------------------------------");


  // Temperature

  if (isnan(temperature)) {

    Serial.println("Temperature Sensor Error");

  } else {

    Serial.print("Temperature: ");

    Serial.print(temperature);

    Serial.println(" C");

  }


  // Humidity

  if (isnan(humidity)) {

    Serial.println("Humidity Sensor Error");

  } else {

    Serial.print("Humidity: ");

    Serial.print(humidity);

    Serial.println(" %");

  }


  // Pulse Sensor

  Serial.print("Pulse Sensor Value: ");

  Serial.println(pulseValue);


  /*
  =================================
  EDUCATIONAL PROTOTYPE ANALYSIS
  =================================
  */

  Serial.println();


  if (isnan(temperature)) {

    Serial.println(
      "Prototype Status: SENSOR ERROR"
    );

  }

  else if (temperature > 38) {

    Serial.println(
      "Prototype Status: ATTENTION"
    );

  }

  else {

    Serial.println(
      "Prototype Status: NORMAL RANGE"
    );

  }


  Serial.println("--------------------------------");


  // Wait for next reading

  delay(2000);

}

Arduino IDE Tip: Copy the code into Arduino IDE, select your Arduino board and COM port, then click Upload.

🤖 AI Analysis

Artificial Intelligence can be added to this project after collecting sufficient sensor data.

The AI workflow is:

Sensor Data
↓
Data Collection
↓
Dataset Creation
↓
Data Cleaning
↓
Feature Selection
↓
Machine Learning Model
↓
Pattern Analysis
↓
Educational Prototype Classification

For example, students can collect multiple sensor readings and save them in a CSV file.

The dataset may contain columns such as:

Temperature
Humidity
Pulse Sensor Value
Time
Prototype Label

The collected dataset can be analyzed using Python programming.

Machine Learning algorithms such as Decision Tree or K-Nearest Neighbors can be used for educational experimentation.

The purpose of the AI model is to learn patterns from the collected prototype data.

Important:

The AI output should be considered an educational demonstration only. It must not be considered a medical diagnosis.

🚀 Applications

School and ATL Lab STEM projects
Arduino and IoT learning
Science exhibitions
STEM demonstrations
Prototype development

⚠️ Testing & Safety Tips

Check VCC and GND connections before powering the circuit.
Never short 5V and GND.
Use an appropriate power supply for motors and high-current devices.
Check sensor and Arduino pin numbers carefully.
Test each component separately when troubleshooting.