2011
DOI: 10.1109/tbme.2011.2161671
|View full text |Cite
|
Sign up to set email alerts
|

Continuous Locomotion-Mode Identification for Prosthetic Legs Based on Neuromuscular–Mechanical Fusion

Abstract: In this study, we developed an algorithm based on neuromuscular–mechanical fusion to continuously recognize a variety of locomotion modes performed by patients with transfemoral (TF) amputations. Electromyographic (EMG) signals recorded from gluteal and residual thigh muscles and ground reaction forces/moments measured from the prosthetic pylon were used as inputs to a phase-dependent pattern classifier for continuous locomotion-mode identification. The algorithm was evaluated using data collected from five pa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

15
431
1
2

Year Published

2015
2015
2023
2023

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 468 publications
(449 citation statements)
references
References 24 publications
15
431
1
2
Order By: Relevance
“…However, they present limitations such as fixed sampling window size, large number of sensors, lack of analysis for decision time, gait phases and gait periods. Other works have addressed the recognition of gait phases, but they still use a fixed sampling window size [27], [36]. In contrast, our method achieved high accuracy for simultaneous recognition of locomotion and gait phases, while dealing with uncertainty and using only three inertial measurement units.…”
Section: Discussionmentioning
confidence: 94%
See 3 more Smart Citations
“…However, they present limitations such as fixed sampling window size, large number of sensors, lack of analysis for decision time, gait phases and gait periods. Other works have addressed the recognition of gait phases, but they still use a fixed sampling window size [27], [36]. In contrast, our method achieved high accuracy for simultaneous recognition of locomotion and gait phases, while dealing with uncertainty and using only three inertial measurement units.…”
Section: Discussionmentioning
confidence: 94%
“…Interestingly, our high-level recognition system is able to autonomously determine when the evidence accumulated from sensor measurements is enough to make accurate decisions. This aspect is an improvement over previous works, which normally restrict the decision-making and recognition processes with a fixed and predefined number of sensor samples [27], [34], [42]. We consider that our work offers the potential to develop intelligent wearable robots, capable to recognise human movements and adapt their performance to provide fast and safe assistance in activities of daily living.…”
Section: Discussionmentioning
confidence: 96%
See 2 more Smart Citations
“…All these techniques have achieved reasonable recognition accuracies in steady-state, while the accuracy is much lower in transition between activities [6]. Sensor fusion-based PR for identifying different activities to improve the accuracy and responsiveness have been discussed in [6,11] .…”
Section: Introductionmentioning
confidence: 99%