Adaptive restriction rules provide functional and safe stimulation patternfor foot drop correction

We report on our advances in sensory feedback data processing and control s ystem design for functional electrical stimulation (FES) assisted correctio n of foot drop. We have applied 2 methods of signal purification on the bin integrated electroneurogram (i.e., optimized low pass filtering and wavele t denoising) before training adaptive logic networks (ALN). ALN generated s timulation control pulses, which correspond to the swing phase of the impai red leg when dorsal flexion of the foot is necessary to provide safe ground clearance. However, the obtained control signal contained sporadic stimula tion spikes in the stance phase, which can collapse the subject, and infreq uent broken stimulation pulses in the swing phase, which can result in unpr edictable consequences. In this study, we have introduced adaptive restrict ion rules (ARR), which are initially used as previously reported and then d ynamically adapted during the use of the system. Our results suggest that A RR provide a safer and more reliable stimulation pattern than fixed restric tion rules.