Evaluating robustness of gait event detection based on machine learning and natural sensors

Abstract

A real-time system for deriving timing control for functional electrical stimulation for foot-drop correction, using peripheral nerve activity as a sensor input, was tested for reliability to investigate the potential for clinical use. The system, which was previously reported on, was tested on a hemiplegic subject instrumented with a recording cuff electrode on the Sural nerve, and a stimulation cuff electrode on the Peroneal cuff. Implanted devices enabled recording and stimulation through telelinks. An input domain was derived from the recorded electroneurogram and fed to a detection algorithm based on an adaptive logic network for controlling the stimulation timing. The reliability was tested by letting the subject wear different foot wear and walk on different surfaces than when the training data was recorded. The detection system was also evaluated several months after training. The detection system proved able to successfully detect when walking with different footwear on varying surfaces up to 374 days after training, and thereby showed great potential for being clinically useful.

Clinical Application of Acceleration Sensor to Detect the Swing Phase of Stroke Gait in Functional Electrical Stimulation

“…A variety of artificial and natural sensors have been studied for use in FES of feet, including gyroscopes (Ghoussayni et al 2004), tilt sensors (Dai et al 1996), electronystagmographic signals (Hansen et al 2004), electromyographic signals (Vodovnik et al 1965), and accelerometers (Mansfield and Lyons 2003). Ghoussayni et al (2004) reported that overall accuracy of the gyroscope sensor system when worn on the shank was 96% for able-bodied subjects and 94% for stroke patients.…”

External control of movements and artificial neural networks

“…Skelly and Chizeck [37] used fuzzy logic as the first stage of a two level algorithm for real time detection of gait phases during electrically stimulated locomotion of paraplegic subjects. Hansen et al [38,39] developed a control for the real time correction of drop foot using ALNs. The inputs for the ALN were electroneurorgraphy signals recorded from the sural nerve by a cuff electrode.…”

Balance Assessment during the Landing Phase of Jump-Down in Healthy Men and Male Patients after Anterior Cruciate Ligament Reconstruction

“…There have been numerous motion analysis studies, but they are mainly concerned with gait [5][6][7][8][9][10][11][12][13]. Some studies considered motion analysis after ACLR [14][15][16].…”