IoT-powered deep learning brain network for assisting quadriplegic people

Abstract

Brain-computer interface (BCI) systems have recently emerged as a prominent technology for assisting paralyzed people. Recovery from paralysis in most patients using the existing BCI-based assistive devices is hindered due to the lack of training and proper supervision. The system's continuous usage results in mental fatigue, owing to a higher user concentration required to execute the mental commands. Moreover, the false-positive rate and lack of constant control of the BCI systems result in user frustration. In this paper, we propose a framework for BCI systems that utilize deep learning (DL) in a efficient manner to reduce mental fatigue and frustration. The proposed Deep learning Brain System (DBS) recognizes the patient's intention for upper limb movement by a DL model based on the features extracted during training. DBS correlates and maps the different electroencephalogram (EEG) patterns of healthy subjects with the identified pattern's upper limb movement. The stroke-affected muscles of the paralyzed are then activated using the obtained superior pattern. The implemented DBS consisting of four healthy subjects and a quadriplegic patient achieved 94% accuracy for various patient movement intentions. The results show that DBS is an excellent tool for providing rehabilitation, and it delivers sustained assistance, even in the absence of caregivers.