Machine Learning Assisted Self-Powered Identity Recognition Based on Thermogalvanic Hydrogel for Intelligent...

Area of Science:

• Materials Science
• Biotechnology
• Security Engineering

Background:

• Traditional identity recognition systems struggle with accuracy, complexity, and power dependency in the intelligent era.
• There is a need for advanced biometric security solutions that are robust and self-sufficient.
• Biometric authentication is crucial for intelligent security and human-machine interaction.

Purpose of the Study:

• To develop a finger temperature-driven intelligent identity recognition strategy.
• To utilize a thermogalvanic hydrogel (TGH) for active biometric characteristic discernment.
• To enhance security and human-machine interaction through a novel self-powered recognition system.

Main Methods:

• Fabrication of a thermogalvanic hydrogel (TGH) using a dual network PVA/Agar hydrogel in an H2O/glycerol binary solvent with a redox couple.
• Development of a concave-arranged TGH array to capture intrinsic finger temperature features from five distinct sites.
• Integration of machine learning algorithms for user identification based on extracted thermal biometric data.

Main Results:

• The TGH array successfully distinguished user characteristics by extracting intrinsic temperature features.
• High average recognition accuracy of 97.6% was achieved using the TGH array combined with machine learning.
• The self-powered identity recognition strategy was successfully implemented in a smart lock system.

Conclusions:

• The finger temperature-driven TGH array offers a promising solution for advanced identity recognition.
• This self-powered biometric strategy provides more reliable security than traditional password-based systems.
• The technology has significant advantages for intelligent security and future human-machine interaction in the Internet of Everything.