Abstract:The traditional classification methods for limb motion recognition based on sEMG have been deeply researched and shown promising results. However, information loss during feature extraction reduces the recognition accuracy. To obtain higher accuracy, the deep learning method was introduced. In this paper, we propose a parallel multiple-scale convolution architecture. Compared with the state-of-art methods, the proposed architecture fully considers the characteristics of the sEMG signal. Larger sizes of kernel filter than commonly used in other CNN-based hand recognition methods are adopted. Meanwhile, the characteristics of the sEMG signal, that is, muscle independence, is considered when designing the architecture. All the classification methods were evaluated on the NinaPro database. The results show that the proposed architecture has the highest recognition accuracy. Furthermore, the results indicate that parallel multiple-scale convolution architecture with larger size of kernel filter and considering muscle independence can significantly increase the classification accuracy.

Rigid body orientation determined by IMU (Inertial Measurement Unit) is widely applied in robotics, navigation, rehabilitation, and human-computer interaction. In this paper, aiming at dynamically fusing quaternions computed from angular rate integration and FQA algorithm, a quaternion-based complementary filter algorithm is proposed to support a computationally efficient, wearable motion-tracking system. Firstly, a gradient descent method is used to determine a function from several sample points. Secondly, this function is used to dynamically estimate the fusion coefficient based on the deviation between measured magnetic field, gravity vectors and their references in Earth-fixed frame. Thirdly, a test machine is designed to evaluate the performance of designed filter. Experimental results validate the filter design and show its potential of real-time human motion tracking.

No abstract

No abstract

Mounting evidences have indicated that terminal differentiation-induced lncRNA (TINCR) contributes to various cellular processes, such as proliferation, apoptosis, autophagy, migration, invasion, and metastasis. However, the function of TINCR in regulating migration of MSCs is largely unknown. In this study, the effects of TINCR on the migration of rat MSCs from the bone marrow were studied by Transwell assays and wound healing assays. Our results suggested that TINCR positively regulated migration of rMSCs. miR-761 mimics suppressed rMSC migration, whereas miR-761 inhibitor promoted migration. Target prediction analysis tools and dual-luciferase reporter gene assay identified Wnt2 as a direct target of miR-761. miR-761 could inhibit the expression of Wnt2. Further, the investigation about the function of TINCR in miR-761-induced migration of rMSCs was completed. These results demonstrated that TINCR took part in the regulation of miR-761-induced migration in rMSCs through the regulation of Wnt2 and its Wnt2 signaling pathway. Taken together, our results demonstrate that lncRNA-TINCR functions as a competitive endogenous RNA (ceRNA) to regulate the migration of rMSCs by sponging miR-761 which modulates the role of Wnt2. These findings provide evidence that lncRNA-TINCR has a chance to serve as a potential target for enhancing MSC homing through the miR-761/Wnt2 signaling pathway.

Exoskeletons with a Bowden cable for power transmission have the advantages of a concentrated mass and flexible movement. However, their integrated motor is disturbed by the Bowden cable’s friction, which limits the performance of the force loading response. In this paper, we solve this problem by designing an outer-loop feedforward-feedback proportion-differentiation controller based on an inner loop disturbance observer. Firstly, the inner loop’s dynamic performance is equivalent to the designed nominal model using the proposed disturbance observer, which effectively compensates for the parameter perturbation and friction disturbance. Secondly, based on an analysis of the stability of the inner loop controller, we obtain the stability condition and discuss the influence of modeling errors on the inner loop’s dynamic performance. Thirdly, to avoid excessive noise from the force sensors being introduced into the designed disturbance observer, we propose the feedforward-feedback proportion-differentiation controller based on the nominal model and pole configuration, which improves the outer loop’s force loading performance. Experiments are conducted, which verify the effectiveness of the proposed methods.

The fast-growing techniques of measuring and fusing multi-modal biomedical signals enable advanced motor intent decoding schemes of lower-limb exoskeletons, meeting the increasing demand for rehabilitative or assistive applications of take-home healthcare. Challenges of exoskeletons' motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission. In this paper, we solve this problem by proposing an ahead-of-time continuous prediction of lowerlimb kinematics, with the prediction of knee angles during level walking as a case study. Firstly, an end-to-end kinematics prediction network(KinPreNet) 1 , consisting of a feature extractor and an angle predictor, is proposed and experimentally compared with features and methods traditionally used in ahead-of-time prediction of gait phases. Secondly, inspired by the electromechanical delay(EMD), we further explore our algorithm's capability of compensating response delay of mechanical transmission by validating the performance of the different sections of prediction time. And we experimentally reveal the time boundary of compensating the hysteretic response. Thirdly, a comparison of employing EMG signals or not is performed to reveal the EMG and kinematic signals' collaborated contributions to the continuous prediction. During the experiments, EMG signals of nine muscles and knee angles calculated from inertial measurement unit (IMU) signals are recorded from ten healthy subjects. Our algorithm can predict knee angles with the averaged RMSE of 3.98 deg which is better than the 15.95-deg averaged RMSE of utilizing the traditional methods of ahead-of-time prediction. The best prediction time is in the interval of 27ms and 108ms. To the best of our knowledge, this is the first study of continuously predicting lower-limb kinematics in an ahead-of-time manner based on the electromechanical delay (EMD).

No abstract