Prediction of distal arm joint angles from EMG and shoulder orientation for prosthesis control
Current state-of-the-art upper limb myoelectric prostheses are limited by only being able to control a single degree of freedom at a time. However, recent studies have separately shown that the joint angles corresponding to shoulder orientation and upper arm EMG can predict the joint angles corresponding to elbow flexion/extension and forearm pronation/ supination, which would allow for simultaneous control over both degrees of freedom. In this preliminary study, we show that the combination of both upper arm EMG and shoulder joint angles may predict the distal arm joint angles better than each set of inputs alone. Also, with the advent of surgical techniques like targeted muscle reinnervation, which allows a person with an amputation intuitive muscular control over his or her prosthetic, our results suggest that including a set of EMG electrodes around the forearm increases performance when compared to upper arm EMG and shoulder orientation. We used a Time-Delayed Adaptive Neural Network to predict distal arm joint angles. Our results show that our network's root mean square error (RMSE) decreases and coefficient of determination (R(2)) increases when combining both shoulder orientation and EMG as inputs.
Available from: Scott Beardsley
- "Current efforts using EMG for closed-loop control of lower limb prostheses have focused primarily on classification of EMG signals to identify discrete classes of movement (Au, Berniker et al. 2008, Delis, Carvalho et al. 2009, Hargrove, Huang et al. 2009, Ha, Varol et al. 2011, Hargrove, Simon et al. 2011, Huang, Zhang et al. 2011, Huang and Ferris 2012, Silver- Thorn, Current et al. 2012, Hargrove, Simon et al. 2013, Miller, Beazer et al. 2013, Wentink, Beijen et al. 2013). This emphasis on classification parallels current techniques used in upper limb prosthetic systems to compensate for the uncertainty in mapping a subset of EMG inputs to multiple degrees of freedom and types of movement (Kuiken, Miller et al. 2005, Yatsenko, McDonnall et al. 2007, Kuiken, Li et al. 2009, Artemiadis and Kyriakopoulos 2010, Bueno, French et al. 2011, Pulliam, Lambrecht et al. 2011, Akhtar, Hargrove et al. 2012, Hebert and Lewicke 2012, Jiang, Vest-Nielsen et al. 2012, Muceli and Farina 2012, Jiang, Muceli et al. 2013, Li, Chen et al. 2013). Multi-layer artificial neural networks and SVMs have been used extensively for this purpose in upper extremity prosthetic systems and have been shown to provide accurate discrimination across classes of limb movement, particularly when used in combination with neuro-fuzzy systems and auto-regressive models (Englehart and Hudgins 2003, Karlik, Tokhi et al. 2003, Liu 2007, Au, Berniker et al. 2008). "
[Show abstract] [Hide abstract]
Powered robotic prostheses create a need for natural-feeling user interfaces and robust control schemes. Here, we examined the ability of a nonlinear autoregressive model to continuously map the kinematics of a transtibial prosthesis and electromyographic (EMG) activity recorded within socket to the future estimates of the prosthetic ankle angle in three transtibial amputees.
Model performance was examined across subjects during level treadmill ambulation as a function of the size of the EMG sampling window and the temporal 'prediction' interval between the EMG/kinematic input and the model's estimate of future ankle angle to characterize the trade-off between model error, sampling window and prediction interval.
Across subjects, deviations in the estimated ankle angle from the actual movement were robust to variations in the EMG sampling window and increased systematically with prediction interval. For prediction intervals up to 150 ms, the average error in the model estimate of ankle angle across the gait cycle was less than 6°. EMG contributions to the model prediction varied across subjects but were consistently localized to the transitions to/from single to double limb support and captured variations from the typical ankle kinematics during level walking.
The use of an autoregressive modeling approach to continuously predict joint kinematics using natural residual muscle activity provides opportunities for direct (transparent) control of a prosthetic joint by the user. The model's predictive capability could prove particularly useful for overcoming delays in signal processing and actuation of the prosthesis, providing a more biomimetic ankle response.
Journal of Neural Engineering 09/2014; 11(5):056027. DOI:10.1088/1741-2560/11/5/056027 · 3.30 Impact Factor
[Show abstract] [Hide abstract]
ABSTRACT: We study thigh angle prediction in level-ground walking using inertial measurement units (IMUs). Our approach take advantage of the periodicity of thigh movements during level-ground walking to identify a new method, which formulates the thigh angular data into a multi-tone frequency model and reconstruct data for prediction based on the frequency estimation results. To test the accuracy of our proposed algorithm, we collect data from one thigh and take it as a reference for the prediction result of the other's. Furthermore, both intra-subject and inter-subject performances of our prediction algorithm are validated through multiple datasets collected from ten different subjects.
Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2013 International Conference on; 01/2013
[Show abstract] [Hide abstract]
ABSTRACT: Inertial and magnetic sensors are valuable for untethered, self-contained human movement analysis. Very recently, complete integration of inertial sensors, magnetic sensors, and processing into single packages, has resulted in miniature, low power devices that could feasibly be employed in an implantable motion capture system. We developed a wearable sensor system based on a commercially available System-in- Package inertial and magnetic sensor. We characterized the accuracy of the system in measuring three-dimensional orientation-with and without magnetometer-based heading compensation-relative to a research grade optical motion capture system. The root mean square error was less than 4° in dynamic and static conditions about all axes. Using four sensors, recording from seven degrees-of-freedom of the upper limb (shoulder, elbow, wrist) was demonstrated in one subject during reaching motions. Very high correlation and low error was found across all joints relative to the optical motion capture system. Findings were similar to previous publications using inertial sensors, but at a fraction of the power consumption and size of the sensors. Such ultra-small, low power sensors provide exciting new avenues for movement monitoring for various movement disorders, movement-based command interfaces for assistive devices, and implementation of kinematic feedback systems for assistive interventions like Functional Electrical Stimulation.
IEEE Transactions on Neural Systems and Rehabilitation Engineering 05/2014; 22(6). DOI:10.1109/TNSRE.2014.2324825 · 3.19 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.