Eco-Friendly Corn Silk-Based Triboelectric Nanogenerator Sensor for Automated Human Motion Recognition using...

Area of Science:

• Materials Science
• Biomedical Engineering
• Green Electronics

Background:

• Human activity monitoring is crucial for healthcare and fitness.
• There is a growing need for sustainable and biodegradable electronic sensors.
• Existing sensors often lack eco-friendly materials and self-powering capabilities.

Purpose of the Study:

• To design and develop a biodegradable triboelectric nanogenerator (TENG) sensor using corn silk.
• To integrate the TENG sensor with machine learning for intelligent human motion detection.
• To demonstrate a sustainable and self-powered solution for wearable human activity monitoring.

Main Methods:

• Utilized corn silk as the primary triboelectric material for a biodegradable TENG sensor.
• Integrated the TENG sensor with an ensemble machine learning model (Histogram gradient boosting classifier).
• Developed a graphical user interface for real-time sensor data processing and activity recognition.

Main Results:

• The corn silk-based TENG sensor generated an output voltage of 101 V and could charge commercial capacitors.
• The integrated machine learning model achieved a 98.7% classification accuracy for distinguishing between walking, running, and jumping.
• The sensor was successfully evaluated as a wearable device for autonomous human motion detection.

Conclusions:

• A novel, biodegradable, and eco-friendly TENG sensor based on corn silk was successfully developed.
• The combination of the TENG sensor and machine learning offers a highly accurate method for human activity recognition.
• This technology presents a promising pathway for intelligent, self-powered, and sustainable human motion monitoring systems.