BeaType: an alternative communication method based on RFID devices

Abstract

Abstract Neuromuscular system diseases may lead to severe paralysis and loss of language function. Patients cannot communicate normally with the outside world and are difficult to receive timely help. To address this issue, researchers have developed various alternative communication technologies, among which breathing-based typing is a common method. However, existing technologies have limitations: some studies only support sending a small number of pre-set sentences, preventing users from freely expressing their intentions; others require interaction with a display screen and are not adapt-able to blind patients. In our previous work, we developed a breathing-based alternative communication technology based on commercial Radio Frequency Identification (RFID) devices, but its typing efficiency still needed improvement. In this study, we propose the BeaType system, design fine-grained method for expressing information through breathing, develop a new breathing movement feature extraction algorithm, derive a model for identifying breathing movements using a breathing control model, and finally output binary information using the proposed decoding model. Experiments show that BeaType has stable performance, and its typing efficiency is 15% higher than that of the previous work.