Scribd
Upload
25 views9 pages

Sleep Monitering System

This document describes a sleep monitoring system that uses sensors to collect biometric data from patients as they sleep. The system analyzes the sensor data using a random forest algorithm to classify sleep into different categories like deep sleep, light sleep, REM sleep, and restless sleep. Sensors like an accelerometer, pulse oximeter, and microphone are connected to an Arduino microcontroller that collects the data and sends it to a computer. The computer then uses a random forest machine learning model trained on the sensor data to analyze and categorize patients' sleep. The goals of the system are to efficiently monitor sleep patterns and provide a low-cost solution.

Uploaded by

Amey Kottawar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
25 views9 pages

Sleep Monitering System

This document describes a sleep monitoring system that uses sensors to collect biometric data from patients as they sleep. The system analyzes the sensor data using a random forest algorithm to classify sleep into different categories like deep sleep, light sleep, REM sleep, and restless sleep. Sensors like an accelerometer, pulse oximeter, and microphone are connected to an Arduino microcontroller that collects the data and sends it to a computer. The computer then uses a random forest machine learning model trained on the sensor data to analyze and categorize patients' sleep. The goals of the system are to efficiently monitor sleep patterns and provide a low-cost solution.

Uploaded by

Amey Kottawar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

SLEEP MONITERING

SYSTEM
INTRODUCTION:
• Nowdays getting good quality sleep is important for every person to get better
physical health.

• So the department of internet of things(IOT) technology supports to build a


consistent and cost effective system to monitor the sleep quality of persons.

• This system is effective enough that it can proficiently monitor patient’s sleep using
commercial off the shelf (COS) sensors as well as predicts results using intelligent
capability.

• From this system we can easily measure the sleep patterns of patients and can give
cost effective system.
Objectives:
1. Use sensors to collect data.
2. Analyse the data using random forest algorithm.

3. Classify the sleep into categories .


Work Plan:
1. Research on the topic
2. Finalise research papers for reference
3. Learn about sensors.
4. Study random forest algorithm.
5. Define parameters to categorise sleep.
6. Compare sensors and choose one that best suits.
7. Formulate the budget.
8. Learn Arduino mega.
9. Implementation of random forest method.
10.Prototype building.

 
Hardware used :

• For body movement we have used ADXL 345


accelerometer.
• For heartbeat and level we have used pulse
oximeter and heartrate sensor MAX.30100
• For snoring detection we have used MAX.9814
sensor microphine amplifier.
CIRCUIT DIAGRAM:
Prototype:

We have connected the

1.Microphone amplifier sensor to the color of the shirt . This is to


record the snoring sound without with more accuracy

2.Pulse oximeter sensor to left arm to record SPO2 reading ,


body temperature and pulse count .

3.Accelerometer to right arm to note the movements of the body


Design of Proposed System
 Data of patients recorded from sensors, sent to computer.
 Random forest
 Data classified to four categories-
• Deep sleep
• Light sleep
• Rapid eye movement
• Restless sleep.
 Three steps-
i. Transfer of data from sensors to Arduino microcontroller
ii. Storing data in file and then using it for training and testing of classifier
iii. Collecting patient’s data and analyzing the sleep quality
Implementation Details:

• Thissystem contains aurdino mega


controller (2560) as a central
microcontroller .
• Thiscontroller takes real time records
from sensors and forwards them to
random forest model in computer
system.
• Thisis based on Main computer that is
attached to microcontroller.
Machine learning model:

Step 1 :- Importing CSV dataset file using pandas

Step 2 :- Plotting the dataset using matplotlib

Step 3 :- Encoding the dataset

Step 4 :Splitting the Dataset Set into Training and Testing Sets ( using SK
learn )

Step 5 : Training the model using training set

Step 6 : Testing the model using testing set

Step 7 : Check the accuracy of the model

Step 8 : Improve the model

You might also like