Accurate decoding of materials using a finger mounted accelerometer
This work addresses the challenge of efficient sensory feedback for stroke rehabilitation and prosthetic designs, though it is incremental as it applies an existing method to a new application.
The study tackled the problem of providing low-cost sensory feedback for stroke rehabilitation and prosthetics by demonstrating that a finger-mounted accelerometer can accurately decode materials during touch, achieving 88% classification accuracy across seven materials and six participants within 7 seconds.
Sensory feedback is the fundamental driving force behind motor control and learning. However, the technology for low-cost and efficient sensory feedback remains a big challenge during stroke rehabilitation, and for prosthetic designs. Here we show that a low-cost accelerometer mounted on the finger can provide accurate decoding of many daily life materials during touch. We first designed a customized touch analysis system that allowed us to present different materials for touch by human participants, while controlling for the contact force and touch speed. Then, we collected data from six participants, who touched seven daily life materials-plastic, cork, wool, aluminum, paper, denim, cotton. We use linear sparse logistic regression and show that the materials can be classified from accelerometer recordings with an accuracy of 88% across materials and participants within 7 seconds of touch.