No abstract

Understanding the neurophysiological signals underlying voluntary motor control and decoding them for controlling limb prostheses is one of the major challenges in applied neuroscience and rehabilitation engineering. While pattern recognition of continuous myoelectric (EMG) signals is arguably the most investigated approach for hand prosthesis control, its underlying assumption is poorly supported, i.e., that repeated muscular contractions produce consistent patterns of steady-state EMGs. In fact, it still remains to be shown that pattern recognition-based controllers allow natural control over multiple grasps in hand prosthesis outside well-controlled laboratory settings. Here, we propose an approach that relies on decoding the intended grasp from forearm EMG recordings associated with the onset of muscle contraction as opposed to the steady-state signals. Eight unimpaired individuals and two hand amputees performed four grasping movements with a variety of arm postures while EMG recordings subsequently processed to mimic signals picked up by conventional myoelectric sensors were obtained from their forearms and residual limbs, respectively. Off-line data analyses demonstrated the feasibility of the approach also with respect to the limb position effect. The sampling frequency and length of the classified EMG window that off-line resulted in optimal performance were applied to a controller of a research prosthesis worn by one hand amputee and proved functional in real-time when operated under realistic working conditions.

For transradial amputees, the muscles in the residual forearm physiologically used for flexing/extending the hand fingers are the most appropriate targets for multifingered prostheses control. However, once the prosthetic socket is manufactured and fitted on the residual forearm, the electromyographic (EMG) signals recorded from the residual limb might not be originated only by the intention of performing finger movements but also by the muscular activity needed to sustain the prosthesis itself. In this work, we show that in eight healthy subjects wearing a prosthetic socket emulator, 1) variations in the weight of the prosthesis and 2) upper arm movements significantly influence the robustness of a traditional classifier based on a k-nn algorithm, causing a significant drop in performance. We demonstrate in simulated conditions that traditional pattern recognition does not allow the separation of the effects of the weight of the prosthesis because a surface recorded EMG pattern due only to the lifting or moving of the prosthesis is misclassified into a hand control movement. This suggests that a robust classifier should add to myoelectric signals, inertial transducers like multi-axes position, acceleration sensors, or sensors able to monitor the interaction forces between the socket and the end-effector. ( J Prosthet Orthot. 2012;24:86Y92.)KEY INDEXING TERMS: upper limb prosthetics, pattern recognition, myoelectric control T o myoelectrically control a multifingered dexterous prosthesis, such as the recently marketed RSL Steeper BeBionic, 1 the iLimb, 2 or research prototypes like the SmartHand, 3 VU Hand, 4 or the DARPA RP 2009 Intrinsic Hand, 5 it is necessary to map electromyographic (EMG) signals corresponding to different muscle contractions to the different existing degrees of freedom (DoFs) of the hand using a suitable algorithm. Myoelectric control techniques can be divided into two categories: nonYpattern recognition based and pattern recognition based. 6,7 NonYpattern recognition control includes proportional control, threshold control, onset analysis, and finite state machines. These schemes have a simple structure and have been mostly deployed in on/off or proportional control. In particular, in proportional control, the strength of muscle contractions controls the prosthesis speed or force. This type of control scheme has received widespread clinical acceptance but provides reduced functionality, typically limited to only one or two DoFs. In research laboratories, sophisticated algorithms implement pattern recognition. 6 This is based on the condition that amputees can voluntarily activate repeatable and distinct EMG signal patterns for each class of motion, which, in turn, can be mapped to physiologically appropriate prosthesis commands.A multitude of groups have implemented and designed controllers using different combinations of extracted features and classification methods (for a review of the EMG processing techniques, refer to the work by Oskoei and Hu 7 ) showing the feasibility of controllin...

Developing an artificial arm with functions equivalent to those of the human arm is one of the challenging goals of bioengineering. State-of-the-artprostheses lack several degrees of freedom and force the individuals to compensate for them by means of compensatory movements, which often result in residual limb pain and overuse syndromes. Passive wristsmay reduce such compensatory actions, nonethelessto date their actual efficacy, associated to conventional myoelectric hands is a matter of debate. We hypothesized that a transradial prosthesiswould allow a simpler operation if its wrist behaved compliant during the reaching and grasping phase, and stiff during the holding andmanipulation phase. To assess this, we compared a stiff and a compliant wrist and evaluating the extent of compensatory movements in the trunk and shoulder, with unimpaired subjects wearing orthoses, while performing nine activities of daily living taken from the southampton hand assessment procedure. Our findings show indeed that the optimal compliance for a prosthetic wrist is specific to the phase of the motor task: the compliant wrist outperforms the stiff wrist during the reaching phase, whereas the stiff wrist exhibits more natural movements during the manipulation phase of heavy objects. Hence, this paper invites rehabilitation engineers to develop wrists with switchable compliance.

In this paper we present surface electromyo-graphic (EMG) data collected from 16 channels on five unimpaired subjects and one transradial amputee performing 12 individual finger movements and a rest class. EMG were processed using a traditional Time Domain feature-set and classifiers: a Linear Discriminant Analysis (LDA) a k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM). Using continuous datasets we show that it is possible to achieve an accuracy up to 80% across subjects. Thereafter possibilities to reduce the numbers of channels physically required, as well as the number of features have been investigated by means of a developed Genetic Algorithm (GA) that included a bonus system to reward eliminated features and channels. The classification was performed firstly on the full datasets and in later runs using the GA. The GA demonstrated high redundancy in the recorded 16 channel data as well as the insignificance of certain features. Although the GA optimization yielded to reduce 8 to 11 channels depending on the subject, such reduction had little to no effect on the classification accuracies.