DEMA: A Deep Learning-Enabled Model for Non-Invasive Human Vital Signs Monitoring Based on Optical Fiber Sensing

Area of Science:

• Biomedical Engineering
• Optical Sensing Technologies
• Artificial Intelligence in Healthcare

Background:

• Optical fiber sensors offer advantages like small size and immunity to electronic interference.
• Current vital sign monitoring methods can be invasive and uncomfortable for long-term use.
• There is a need for convenient, non-invasive solutions for continuous health monitoring.

Purpose of the Study:

• To develop a non-invasive system for precise vital sign monitoring.
• To integrate optical fiber sensing with advanced deep learning for improved accuracy.
• To provide a comfortable and effective alternative for daily health surveillance.

Main Methods:

• Utilized an optical fiber sensor integrated with a Mach-Zehnder interferometer (MZI).
• Employed Long Short-Term Memory (LSTM) networks for data analysis and vital sign extraction.
• Developed a non-invasive monitoring system for human vital signs.

Main Results:

• The system demonstrated precise vital sign readings through non-invasive means.
• The integration of MZI and LSTM networks surpassed conventional monitoring approaches.
• Achieved accurate detection and monitoring of vital signs without direct skin contact.

Conclusions:

• The developed system offers a promising non-invasive approach for continuous vital sign monitoring.
• Potential applications include medical diagnostics, health surveillance, and intelligent healthcare.
• This technology enhances patient comfort and facilitates long-term health evaluation.