A Multi-Channel Ensemble Method for Error-Related Potential Classification Using 2D EEG Images.

An error-related potential (ErrP) occurs when people's expectations are not consistent with the actual outcome. Accurately detecting ErrP when a human interacts with a BCI is the key to improving these BCI systems. In this paper, we propose a multi-channel method for error-related potential detection using a 2D convolutional neural network. Multiple channel classifiers are integrated to make final decisions. Specifically, every 1D EEG signal from the anterior cingulate cortex (ACC) is transformed into a 2D waveform image; then, a model named attention-based convolutional neural network (AT-CNN) is proposed to classify it. In addition, we propose a multi-channel ensemble approach to effectively integrate the decisions of each channel classifier. Our proposed ensemble approach can learn the nonlinear relationship between each channel and the label, which obtains 5.27% higher accuracy than the majority voting ensemble approach. We conduct a new experiment and validate our proposed method on a Monitoring Error-Related Potential dataset and our dataset. With the method proposed in this paper, the accuracy, sensitivity and specificity were 86.46%, 72.46% and 90.17%, respectively. The result shows that the AT-CNNs-2D proposed in this paper can effectively improve the accuracy of ErrP classification, and provides new ideas for the study of classification of ErrP brain-computer interfaces.

Domain-Adaptive Prototype-Recalibrated Network with Transductive Learning Paradigm for Intelligent Fault Diagnosis under Various Limited Data Conditions.

In real industrial scenarios, intelligent fault diagnosis based on data-driven methods has been widely researched in the past decade. However, data scarcity is widespread in fault diagnosis tasks owning to the difficulties in collecting adequate data. As a result, there is an increasing demand for both researchers and engineers for fault identification with scarce data. To address this issue, an innovative domain-adaptive prototype-recalibrated network (DAPRN) based on a transductive learning paradigm and prototype recalibration strategy (PRS) is proposed, which has the potential to promote the generalization ability from the source domain to target domain in a few-shot fault diagnosis. Within this scheme, the DAPRN is composed of a feature extractor, a domain discriminator, and a label predictor. Concretely, the feature extractor is jointly optimized by the minimization of few-shot classification loss and the maximization of domain-discriminative loss. The cosine similarity-based label predictor, which is promoted by the PRS, is exploited to avoid the bias of naïve prototypes in the metric space and recognize the health conditions of machinery in the meta-testing process. The efficacy and advantage of DAPRN are validated by extensive experiments on bearing and gearbox datasets compared with seven popular and well-established few-shot fault diagnosis methods. In practical application, the proposed DAPRN is expected to solve more challenging few-shot fault diagnosis scenarios and facilitate practical fault identification problems in modern manufacturing.

The recovery of weak impulsive signals based on stochastic resonance and moving least squares fitting.

In this paper a stochastic resonance (SR)-based method for recovering weak impulsive signals is developed for quantitative diagnosis of faults in rotating machinery. It was shown in theory that weak impulsive signals follow the mechanism of SR, but the SR produces a nonlinear distortion of the shape of the impulsive signal. To eliminate the distortion a moving least squares fitting method is introduced to reconstruct the signal from the output of the SR process. This proposed method is verified by comparing its detection results with that of a morphological filter based on both simulated and experimental signals. The experimental results show that the background noise is suppressed effectively and the key features of impulsive signals are reconstructed with a good degree of accuracy, which leads to an accurate diagnosis of faults in roller bearings in a run-to failure test.

Enhancement of motor imagery training efficiency by an online adaptive training paradigm integrated with error related potential.

Objective. Motor imagery (MI) is a process of autonomously modulating the motor area to rehearse action mentally without actual execution. Based on the neuroplasticity of the cerebral cortex, MI can promote the functional rehabilitation of the injured cerebral cortex motor area. However, it usually takes several days to a few months to train individuals to acquire the necessary MI ability to control rehabilitation equipment in current studies, which greatly limits the clinical application of rehabilitation training systems based on the MI brain-computer interface (BCI).Approach. A novel MI training paradigm combined with the error related potential (ErrP) is proposed, and online adaptive training of the MI classifier was performed using ErrP. ErrP is used to correct the output of the MI classification to obtain a higher accuracy of kinesthetic feedback based on the imagination intention of subjects while generating simulated labels for MI online adaptive training. In this way, we improved the MI training efficiency. Thirteen subjects were randomly divided into an experimental group using the proposed paradigm and a control group using the traditional MI training paradigm to participate in six MI training experiments.Main results. The proposed paradigm enabled the experimental group to obtain a higher event-related desynchronization modulation level in the contralateral brain region compared with the control group and 69.76% online classification accuracy of MI after three MI training experiments. The online classification accuracy reached 72.76% and the whole system recognized the MI intention of the subjects with an online accuracy of 82.61% after six experiments.Significance. Compared with the conventional unimodal MI training strategy, the proposed approach enables subjects to use the MI-BCI based system directly and achieve a better performance after only three training experiments with training left and right hands simultaneously. This greatly improves the usability of the MI-BCI-based rehabilitation system and makes it more convenient for clinical use.

Bionic intelligent ankle-foot prosthesis based on the conjugate curved surface.

Given the poor biomimetic motion of traditional ankle-foot prostheses, it is of great significance to develop an intelligent prosthesis that can realize the biomimetic mechanism of human feet and ankles. To this end, we presented a bionic intelligent ankle-foot prosthesis based on the complex conjugate curved surface. The proposed prosthesis is mainly composed of the rolling conjugated joints with a bionic design and the carbon fiber energy-storage foot. We investigated the flexibility of the prosthetic ankle joint movement, and the ability of the prosthetic foot to absorb ground impact during the gait cycle. Experimental results showed the matching of the ankle/toe position relationship of the human foot during simulated walking, which is helpful to realize the biomimetic motion of the human foot and ankle. It can also help therapists and clinicians provide better rehabilitation for lower-limb amputees.

Self-supervised bi-classifier adversarial transfer network for cross-domain fault diagnosis of rotating machinery.

In real industrial scenarios, deep learning-based fault diagnosis has been a popular topic lately. Unfortunately, the source-trained model typically usually underperforms in target domain owning to changeable working conditions. To resolve this problem, a novel self-supervised bi-classifier adversarial transfer learning (SBATL) network by introducing self-supervised learning (SSL) and class-conditional entropy minimization is presented. Concretely, the SBATL is made up of a feature extractor, a discrepancy detector of two classifiers, and a clustering metric based on SSL, which jointly conducts self-supervised and supervised optimization in a two-stream training procedure. In the self-supervised stream, target pseudo labels obtained by SSL are used to construct the topological clustering metric for target feature optimization. In the supervised stream, the feature extractor and classifiers compete with each other in adversarial training, which bridges the discrepancy between two classifiers. Additionally, the class-conditional entropy minimization of target domain is further embedded into both streams to amend the decision boundaries of two classifiers to pass low-density regions. The results indicate that the SBATL gets better cross-domain fault diagnosis performances when compared with other popular methods.

A Novel Underactuated Robotic Finger with Variable Stiffness Joints.

Existing robotic hands mostly consist of rigid finger mechanism with constant joint stiffness, leading to poor handling performance and even unexpected safety issues. This paper proposed a novel underactuated robotic finger with variable stiffness joints based on human finger anatomy and electrostatic adhesion(ESA) principle. The proposed finger is unique in the 3D printable one-piece body structure consisting of three similar joints, actuated by only one linear actuator to mimic the flexion/extension movement of the human finger. It is characterized by simple actuation, light weight, low cost and compliant grasp. We constructed a portable finger prototype to investigate the variable stiffness performance. It turns out that the joint stiffness shows a growing trend as the applied voltage increases, which verifies the effectiveness of this design. The proposed novel finger indicates potential applications in service robots and prosthetic hands.

Multiscale noise suppression and feature frequency extraction in SSVEP based on underdamped second-order stochastic resonance.

OBJECTIVE: As one of the commonly used control signals of brain-computer interface (BCI), steady-state visual evoked potential (SSVEP) exhibits advantages of stability, periodicity and minimal training requirements. However, SSVEP retains the non-linear, non-stationary and low signal-to-noise ratio (SNR) characteristics of EEG. The traditional SSVEP extraction methods regard noise as harmful information and highlight the useful signal by suppressing the noise. In the collected EEG, noise and SSVEP are usually coupled together, the useful signal is inevitably attenuated while the noise is suppressed. Also, an additional band-pass filter is needed to eliminate the multi-scale noise, which causes the edge effect. APPROACH: To address this issue, a novel method based on underdamped second-order stochastic resonance (USSR) is proposed in this paper for SSVEP extraction. MAIN RESULTS: A synergistic effect produced by noise, useful signal and the nonlinear system can force the energy of noise to be transferred into SSVEP, and hence amplifying the useful signal while suppressing multi-scale noise. The recognition performances of detection are compared with the widely-used canonical coefficient analysis (CCA) and multivariate synchronization index (MSI). SIGNIFICANCE: The comparison results indicate that USSR exhibits increased accuracy and faster processing speed, which effectively improves the information transmission rate (ITR) of SSVEP-based BCI.

A Novel Variable Stiffness Compliant Finger Exoskeleton for Rehabilitation Based on Electromagnet Control.

In this study, we present the design of a variable stiffness finger exoskeleton for hand rehabilitation, to meet the requirements of different human users and versatile rehabilitation task. This paper describes the design principle and fabrication of the variable stiffness finger exoskeleton which combines a variable stiffness beam and a 3D printed compliant finger exoskeleton. Experimental studies have shown that by using the electromagnetic force, exoskeleton stiffness variation is achievable. Therefore, the proposed variable stiffness finger exoskeleton is capable of adapting the versatile tasks and providing a soft, wearable device for hand rehabilitation of different human users.