Abstract
Robotic lower-limb rehabilitation training is a better alternative for the physical training efforts of a therapist due to advantages, such as intensive repetitive motions, economical therapy, and quantitative assessment of the level of motor recovery through the measurement of force and movement patterns. However, in actual robotic rehabilitation training, emergency stops occur frequently to prevent injury to patients. However, frequent stopping is a waste of time and resources of both therapists and patients. Therefore, early detection of emergency stops in real-time is essential to take appropriate actions. In this paper, we propose a novel deep-learning-based technique for detecting emergency stops as early as possible. First, a bidirectional long short-term memory prediction model was trained using only the normal joint data collected from a real robotic training system. Next, a real-time threshold-based algorithm was developed with cumulative error. The experimental results revealed a precision of 0.94, recall of 0.93, and F1 score of 0.93. Additionally, it was observed that the prediction model was robust for variations in measurement noise.
Highlights
The goal of rehabilitation exercises is to perform specific movements that induce motor plasticity to improve motor recovery and minimize functional deficits
This paper proposes a DL-based real-time emergency stop prediction method that can be used in robotic gait rehabilitation training systems without prior anomaly knowledge
This condition can reduce the false positive rate (FPR) while maintaining the true positive rate (TPR) of emergency stop detection because EN in the normal training data causes an increase in the FPR
Summary
The goal of rehabilitation exercises is to perform specific movements that induce motor plasticity to improve motor recovery and minimize functional deficits. Robotic rehabilitation may be a solution for automated training [2] This technology can provide accurate proprioceptive, kinematic, and kinetic guidance, as well as variable error practice, high-intensity, and repetitive taskspecific and interactive exercises for paretic lower-limbs [3, 4]. Based on these benefits, exoskeleton-type robotic lower-limb rehabilitation systems are used in medical fields [3, 5,6,7,8]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have