Deep-Learning Technique To Convert a Crude Piezoresistive Carbon Nanotube-Ecoflex Composite Sheet into a Smart, Portable, Disposable, and Extremely Flexible Keypad

ACS Appl Mater Interfaces. 2018 Jun 20;10(24):20862-20868. doi: 10.1021/acsami.8b04914. Epub 2018 Jun 11.

Abstract

An extremely simple bulk sheet made of a piezoresistive carbon nanotube (CNT)-Ecoflex composite can act as a smart keypad that is portable, disposable, and flexible enough to be carried crushed inside the pocket of a pair of trousers. Both a rigid-button-imbedded, rollable (or foldable) pad and a patterned flexible pad have been introduced for use as portable keyboards. Herein, we suggest a bare, bulk, macroscale piezoresistive sheet as a replacement for these complex devices that are achievable only through high-cost fabrication processes such as patterning-based coating, printing, deposition, and mounting. A deep-learning technique based on deep neural networks (DNN) enables this extremely simple bulk sheet to play the role of a smart keypad without the use of complicated fabrication processes. To develop this keypad, instantaneous electrical resistance change was recorded at several locations on the edge of the sheet along with the exact information on the touch position and pressure for a huge number of random touches. The recorded data were used for training a DNN model that could eventually act as a brain for a simple sheet-type keypad. This simple sheet-type keypad worked perfectly and outperformed all of the existing portable keypads in terms of functionality, flexibility, disposability, and cost.

Keywords: carbon nanotube; deep neural network; piezoresistive; portable keypad; tactile sensing.