Related Experiment Video
Updated: Jun 21, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
2.7K
Combinatorial Bionic Hierarchical Flexible Strain Sensor for Sign Language Recognition with Machine Learning
Xuanjie Zong1,2, Nianqiang Zhang1,2, Jilai Wang1
1Key Laboratory of High Efficiency and Clean Mechanical Manufacture of Ministry of Education, School of Mechanical Engineering, Shandong University, Jinan, Shandong 250061, China.
ACS Applied Materials & Interfaces
|July 16, 2024
Summary
This study introduces a novel flexible strain sensor (CBH-sensor) inspired by nature. It achieves a wide sensing range and high sensitivity, enabling accurate sign language gesture recognition for improved human-computer interaction.
Area of Science:
- Materials Science
- Biomedical Engineering
- Wearable Technology
Background:
- Flexible strain sensors are crucial for wearables and health monitoring.
- Simultaneously achieving wide sensing range and high sensitivity remains a significant challenge.
- Existing sensors often compromise performance for specific applications.
Purpose of the Study:
- To develop a flexible strain sensor with a balanced wide sensing range and high sensitivity.
- To create a sensor utilizing a cross-scale combinatorial bionic hierarchical design.
- To demonstrate the sensor's application in sign language gesture recognition.
Main Methods:
- A combinatorial bionic hierarchical design integrating microscale and macroscale features was employed.
- Three-dimensional printing, prestretching, and mold transfer techniques were used to fabricate the sensor.
- The sensor's performance was evaluated for its sensing range, sensitivity, and application in gesture recognition.
Main Results:
- The combinatorial bionic hierarchical flexible strain sensor (CBH-sensor) achieved a wide sensing range of 150%.
- The sensor demonstrated high sensitivity with a gauge factor of up to 2416.67.
- An array of CBH-sensors successfully recognized nine sign language gestures with 100% accuracy using machine learning.
Conclusions:
- The CBH-sensor effectively addresses the challenge of balancing sensing range and sensitivity.
- The sensor shows significant potential for enabling communication for the deaf and hard-of-hearing community.
- Applications in human-computer interfaces and gesture-driven interactions are promising.
