Inkjet-printed fully customizable and low-cost electrodes matrix for gesture recognition

Area of Science:

• Biomedical Engineering
• Wearable Technology
• Sensor Technology

Background:

• Surface electromyography (sEMG) is crucial for controlling advanced prosthetic limbs and rehabilitation devices.
• Current sEMG systems can be costly and lack customization for diverse user needs.
• Accurate gesture recognition using sEMG is vital for real-world device control.

Purpose of the Study:

• To develop an affordable, customizable platform for acquiring and analyzing sEMG signals.
• To create a novel, inkjet-printed sEMG sensor matrix for measuring forearm muscle activity.
• To evaluate the performance of the printed sEMG system for gesture recognition.

Main Methods:

• Fabrication of 8-channel sEMG matrices using nanoparticle-based inks and a commercial inkjet printer.
• Acquisition of multi-channel sEMG data from 12 participants performing 12 distinct finger movements.
• Analysis of signal similarity, dissimilarity between movements, and classification accuracy.

Main Results:

• Inkjet-printed sEMG signals demonstrated high similarity across repetitions for all participants.
• A significant difference between distinct finger movements was observed (dissimilarity index > 0.2).
• The system achieved high classification accuracy, ranging from 93% for flexion to 95% for extension.

Conclusions:

• Inkjet printing offers a viable, low-cost method for producing customizable sEMG sensors.
• The developed platform enables accurate sEMG-based gesture recognition for controlling assistive devices.
• This technology has the potential to enhance the functionality and accessibility of prosthetic and rehabilitation technologies.