Compact Memristive Neuromorphic Braille Keyboard

2025

Closed access Metadata (CSL-JSON)
DOI 10.1109/icct-europe63283.2025.11157664
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Classical keyboards do not have the tactile sensing or braille translations for the visually impaired. It tends to be very bulky when transformed into a braille-supported device with overlays, complicating the user experience. We proposed a compact Braille keyboard based on memristive neuromorphic circuits. This implementation, designed with the open-source SkyWater 130 nm CMOS technology node, ensures scalable and cost-effective fabrication. Memristive circuits, known for their high speed, low power, and compact size, act as accelerators of MAC operations required for Braille pattern recognition. System and hardware simulations are presented for memristive neural network implementation of precise braille-to-character mapping, including two Braille scripts: Grade 1 and Grade 2.