Self-Assembly MXene/PDA@Cotton Fabric Pressure Sensor Integrated with Deep Learning for Sign Language Recognition

Area of Science:

• Materials Science
• Wearable Technology
• Biomedical Engineering

Background:

• Smart textiles and wearable devices are crucial for human-computer interaction, medical rehabilitation, and motion monitoring.
• Flexible pressure sensors offer excellent flexibility, stability, and multifunctionality, making them ideal for these applications.

Purpose of the Study:

• To develop a multifunctional wearable pressure sensor based on MXene/polydopamine (PDA)@cotton fabric.
• To evaluate the sensor's performance for physiological monitoring and human-computer interaction applications, including sign language translation.

Main Methods:

• Fabric modification using a dual hydrogen bond self-assembly strategy to create MXene/polydopamine (PDA)@cotton fabric.
• Characterization of sensor performance, including linear detection range, sensitivity, response/recovery times, and cyclic stability.
• Integration of sensors into a smart glove for gesture recognition and sign language translation, coupled with intelligent algorithms.

Main Results:

• The MXene/PDA@cotton fabric pressure sensor exhibited a wide linear detection range (0-146 kPa), high sensitivity (0.95 kPa⁻¹), and rapid response/recovery times (16.434 and 11.952 ms).
• The sensor demonstrated excellent stability over 5000 cycles.
• Successful monitoring of physiological parameters (facial expressions, respiration, joint bending) and realization of static gesture recognition and dynamic sign language translation using the smart glove.

Conclusions:

• The developed flexible pressure sensor shows great potential for intelligent human-computer interaction.
• This work provides valuable insights for the development of advanced sign language recognition systems and next-generation wearable devices.