IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

IN the above article [1], we found the formula (1) is presented incorrectly because of an error in the formula editing process. The correction is as follows: ITR=[log₂K+Plog₂P+(1-p)log₂(1-P/K-1)]×60/T (1).

Treadmill-based repeated perturbation training (PBT) induces motor adaptation in reactive balance responses, thus lowering the risk of slip-induced falls. However, little evidence exists regarding intervention-induced changes in neuromuscular control underlying motor adaptation. Examining neuromuscular changes could be an important step in identifying key elements of adaptation and evaluating treadmill training protocols for fall prevention. Moreover, identifying the muscle synergies contributing to motor adaptation in young adults could lay the groundwork for comparison with high fall-risk populations. Thus, we aimed to investigate neuromuscular changes in reactive balance responses during stance slip-PBT. Lower limb electromyography (EMG) signals (4/leg) were recorded during ten repeated forward stance (slip-like) perturbations in twenty-six young adults. Muscle synergies were compared between early-training (slips 1-2) and late-training (slips 9-10) stages. Results showed that 5 different modes of synergies (named on dominant muscles: W_TA, W_{S_VLAT}, W_{R_GAS}, W_{R_VLAT}, and W_{S_GAS}) were recruited in both stages. 3 out of 5 synergies (W_TA, W_{R_VLAT}, and W_{S_GAS}) showed a high similarity (r>0.97) in structure and activation between stages, whereas W_{R_GAS} and W_{S_VLAT} showed a lower similarity (r<0.83) between the two stages, and the area of activation in W_TA, the peak value of activation in W_{R_VLAT} and the activation onset in W_{R_GAS} showed a reduction from early-to late-training stage (p<0.05). These results suggest that a block of stance slip-PBT resulted in modest changes in muscle synergies in young adults, which might explain the smaller changes seen in biomechanical variables. Future studies should examine neuromuscular changes in people at high risk of falls.

This study aimed to develop a novel framework to quickly personalize electromyography (EMG)-driven musculoskeletal models (MMs) as efferent neural interfaces for upper limb prostheses. Our framework adopts a generic upper-limb MM as a baseline and uses an artificial neural network-based policy to fine-tune the model parameters for MM personalization. The policy was trained by reinforcement learning (RL) to heuristically adjust the MM parameters to maximize the accuracy of estimated hand and wrist motions from EMG inputs. Our present framework was compared to the baseline MM and a widely used MM parameter optimization method: simulated annealing (SA). An offline evaluation was performed to first quantify the time required for MM personalization and the kinematics estimation accuracy of personalized MMs based on data collected from able-bodied subjects. Then, in an online evaluation, additional human subjects, including an individual with a transradial amputation, performed a virtual hand posture matching task using generic and personalized MMs. Results showed that compared to the baseline generic MM, personalized MMs estimated joint motion with lower error in both offline (p<0.05) and online tests (p=0.014), demonstrating the benefit of MM personalization. The RL-based framework performed model optimization in under one second on average in cases that took SA over 13 minutes and yielded comparable kinematics estimations both offline and online. Hence, our present personalization framework can be a practical solution for the daily use of EMG-driven MMs in prostheses or other assistive devices.