ED-FNN: A New Deep Learning Algorithm to Detect Percentage of the Gait Cycle for Powered Prostheses

• Published in: Sensors (Basel, Switzerland) Vol. 18; no. 7; p. 2389
• Main Authors: Vu, Huong Thi Thu, Gomez, Felipe, Cherelle, Pierre, Lefeber, Dirk, Nowé, Ann, Vanderborght, Bram
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 23.07.2018; MDPI
• Subjects: Accuracy; Algorithms; Amputation; Artificial intelligence; Electromyography; exoskeleton; Gait; gait event detection; gait phase prediction; gait recognition; International conferences; lower limb prosthesis; Neural networks; Phase transitions; Prostheses; Sensors; Skin; United States > US; Germany; exoskeleton; gait recognition; gait event detection; lower limb prosthesis; gait phase prediction

Throughout the last decade, a whole new generation of powered transtibial prostheses and exoskeletons has been developed. However, these technologies are limited by a gait phase detection which controls the wearable device as a function of the activities of the wearer. Consequently, gait phase detec...