Scribd
Upload
24 views14 pages

A Smart Sleep Pattern Recognition and Quality Monitoring System

The document presents a project aimed at developing a smart sleep monitoring system using biometric sensors integrated with the BEAGLEBOARD RISC-V platform to analyze sleep patterns and quality. The system targets individuals with sleep disorders and health enthusiasts, utilizing machine learning algorithms for real-time classification of sleep stages. The project outlines its methodology, timeline, budget, and deliverables, emphasizing a cost-effective and non-invasive approach to continuous sleep monitoring.

Uploaded by

Anbuselvi Mathivanan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
24 views14 pages

A Smart Sleep Pattern Recognition and Quality Monitoring System

The document presents a project aimed at developing a smart sleep monitoring system using biometric sensors integrated with the BEAGLEBOARD RISC-V platform to analyze sleep patterns and quality. The system targets individuals with sleep disorders and health enthusiasts, utilizing machine learning algorithms for real-time classification of sleep stages. The project outlines its methodology, timeline, budget, and deliverables, emphasizing a cost-effective and non-invasive approach to continuous sleep monitoring.

Uploaded by

Anbuselvi Mathivanan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

A Smart Sleep Monitoring System for Sleep Pattern

Recognition and Quality Monitoring

Presentation by
Aathi Sankar (3122 22 3002 002)
Karthayani T S (3122 22 3002 055)
III Year, B.E,ECE

Under the guidance of


Dr M Anbuselvi
Associate Professor, ECE Department
PRESENTATION OUTLINE

• Objective
• Motivation
• Scope
• Proposed Methodology
• Deliverables
• Timeline
• Budget Estimate
• References

2 v 1.0
OBJECTIVE

• This project aims to develop a smart sleep monitoring system that integrates
multiple biometric sensors with the BEAGLEBOARD RISC-V platform to
provide insights into sleep patterns and quality.

MOTIVATION
• With the growing appearance of sleep problems, the sleep monitoring system
study has been one of the hotspots in the field of smart human monitoring.
Our project aims to improvise the accuracy of the existing monitoring systems
by the integration of vital sensors with BEAGLEBOARD RISC-V processor
to observe sleep patterns and quality.

3 v 1.0
SCOPE
• Primary target beneficiaries :
1) People with Sleep Disorders
2) Health and Wellness Enthusiasts

• Secondary beneficiaries :
1) Healthcare professionals for diagnosis of sleep related
illnesses.
2) Researchers who study sleep related behaviors
3) Market of consumer electronics - Wearable electronics

4 v 1.0
PROPOSED SYSTEM

5 v 1.0
PROPOSED METHODOLOGY

• Sleep pattern is recorded with the various physiological sensors,


integrated with the BEAGLEBOARD RISC-V board, in real-time.

• Stages of sleep is classified with an appropriate machine learning


algorithm

• The major significance of the proposed system includes the vital


sensors, Synapse EXG, which captures EEG and ECG data, the
MAX30101 sensor for monitoring heart rate and SpO2 (oxygen
saturation) and a GSR/EDA sensor for measuring electrodermal
activity and stress levels.

6 v 1.0
PROPOSED METHODOLOGY

• BEAGLEBOARD processor is a low power consuming and is highly


efficient for handling real-time data due to ARM cortex-A processor, it
also provides seamless data acquisition through USB, GPIO, I2C and
WiFi. The BEAGLEBOARD performs signal processing and feature
extraction, focusing on critical metrics like brainwave patterns, heart rate
variability, and skin conductance.

• These features are then used to classify different sleep stages, such as
REM(Rapid Eye Movement), light sleep, and deep sleep, through a real-
time algorithm designed to detect changes in physiological parameters.

• The classification algorithm processes data to provide insights into the


quality of sleep and detect any irregularities, such as fragmented sleep or
potential signs of sleep disorders.
7 v 1.0
PROPOSED METHODOLOGY

• Thus the integration of multi-modal physiological data, low-power


operation, and real-time classification is performed.

• It is a cost-effective and non-invasive solution for continuous sleep


monitoring, providing valuable insights into sleep health,
facilitating further research in sleep pattern analysis.

8 v 1.0
WORK PLAN

9 v 1.0
TIMELINE (In months)

10 v 1.0
BUDGET ESTIMATE

S.No Component Cost(INR) Quantity Available In

1 BEAGLEBOARD 102110898 15,720.00 1 Element14.com

2 Synapse EXG Sensor 1864.00 2 Aryabot.in

3 tiny GSR(EDA) Sensor 1495.00 1 ProtoCentral

4 MAX30101 Sensor 1932.00 1 Robu.in

5 Consumables 2125.00 Robu.in

Total Estimation 25,000

11 v 1.0
DELIVERABLES
• Integration of all vital sensors with BEAGLEBOARD RISC-V
microcontroller for real-time data collection and processing.

• Implementation of machine learning / deep learning algorithms to classify


sleep stages based on physiological data.

• Paper publication in Flagship conferences.


EXISTING PATENTS
1. Baumgart-Schmitt, R. (2001). U.S. Patent No. 6,272,378. Washington, DC:
U.S. Patent and Trademark Office.
2. Muzet, A. G. (2017). U.S. Patent No. 9,820,680. Washington, DC: U.S. Patent
and Trademark Office.
3. Lovett, E. G., Sweeney, R. J., & Kenknight, B. H. (2012). U.S. Patent No.
8,192,376. Washington, DC: U.S. Patent and Trademark Office.

12 v 1.0
REFERENCES
1. Rahul, A., & Deivanai, K. (2014). Sleep monitoring system. International Journal
of Computer Applications, 96(18).
2. Rajguru, K., Tarpe, P., Aswar, V., Bawane, K., Sorte, S., & Agrawal, R. (2022,
February). Design and Implementation of IoT based sleep monitoring system for
Insomniac people. In 2022 Second International Conference on Artificial
Intelligence and Smart Energy (ICAIS) (pp. 1215-1221). IEEE.
3. Saleem, K., Bajwa, I. S., Sarwar, N., Anwar, W., & Ashraf, A. (2020). IoT
Healthcare: Design of Smart and Cost‐Effective Sleep Quality Monitoring System.
Journal of Sensors, 2020(1), 8882378.

4. Saad, W. H. M., Khoo, C. W., Ab Rahman, S. I., Ibrahim, M. M., & Saad, N. H. M.
(2017, June). Development of sleep monitoring system for observing the effect of
the room ambient toward the quality of sleep. In IOP Conference Series: Materials
Science and Engineering (Vol. 210, No. 1, p. 012050). IOP Publishing

13 v 1.0
Thank You

You might also like