Remaining useful life (RUL) prediction of bearings is essential for effective prognostics and health management (PHM). Although deep learning-based RUL prediction methods achieve high prediction accuracy, they often introduce significant parameter redundancy due to their inability to efficiently capture the intricate temporal dynamics in bearing degradation signals, leading to computationally expensive models with limited practical applicability. To address this challenge, we propose a novel RUL prediction framework that integrates the Wasserstein distance of cyclic spectrum (WDCS) with a Lightweight TimesNet (WDCS-LTN). Specifically, the WDCS serves as a health indicator, effectively extracting multiperiodic features from bearing degradation signals. Subsequently, the LTN transforms the 1-D WDCS sequence into multiple 2-D tensors with varying localities, enabling precise modeling of intraperiod and interperiod temporal dynamics. A shared lightweight inception block is constructed within the LTN to capture temporal variations in 2-D space while maintaining low model complexity. Experimental results on bearing degradation datasets show that WDCS-LTN achieves a prediction error (mean absolute error) of 0.091 with only 37k parameters, outperforming existing methods in terms of accuracy, parameter efficiency, and memory consumption. Through efficiently modeling the temporal dynamics, WDCS-LTN ensures practicality for industrial applications by addressing parameter redundancy while offering enhanced prediction capabilities.

In steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI), improving the recognition performance for new subjects without calibration data is the key challenge for practical application. Unsupervised transfer learning is an effective way to overcome it. However, existing studies focus solely on what to transfer, rather than how to effectively transfer, resulting in unsatisfactory transfer effectiveness or even negative transfer. In this study, an innovative unsupervised cross-subject transfer learning method for SSVEP-BCI was proposed, named SUTL. It involves that subject transferability estimation (STE) and a multi-domain alignment method were proposed to alleviate the potential interference of differences in SSVEP signal distribution among subjects. STE screens appropriate transferable subjects from the source subject pool, while domain alignment directly makes all subjects more similar. Then, SUTL sufficiently exploits the information of the selected source subjects, learning and transferring both generalization knowledge and subject-specific knowledge to boost the recognition performance for the new subject. The performance of SUTL was evaluated on two public SSVEP datasets (benchmark dataset and BETA dataset) with 40 classes, the extensive experimental results reveal that SUTL markedly boosts the effectiveness of SSVEP cross-subject transfer and dramatically outperforms the state-of-art methods. SUTL significantly enhances the recognition performance of SSVEP-BCI for new subjects and facilitates its practical application.

Robotic hand exoskeletons can provide assistance to people who suffer from hand functional disability or spinal cord injury (SCI). However, the current hand exoskeletons remain challenging with respect to having a user-friendly design that satisfies human motion with a lightweight structure. Here we propose a method of using topology optimization in the design of finger exoskeletons, which is a lightweight and integrate manufactured exoskeleton. The exoskeleton is designed by generating the topology configuration according to the bending state of the finger. The objective function in the optimization is set to be the maximization of output displacement of the design domain. After obtaining the topology configuration, a conjugate surface flexure hinge is developed as an elastic joint to replace the compliant part of the topologies. Finally, a rigid-compliant parallel exoskeleton is fabricated by a 3D printer and the performance of the mechanism is verified.

The cross-correlation between the electroencephalogram (EEG) and surface electromyography (sEMG) has important research value both in human-robot integration and intelligent rehabilitation robots. The purpose of this study is to explore the relationship between EEG and sEMG when EEG has different trends. The asymmetric cross-correlation of EEG and sEMG in different states were analyzed by using the multifractal asymmetric detrended cross correlation analysis (MF-ADDCA) method. The synchronous EEG and sEMG in the process of tracking feedback force were analyzed. In order to investigate the dynamic process of asymmetric degree, the rolling window MF-ADDCA method was adopted. The analysis results showed that the asymmetries existed in the cross-correlation between EEG and sEMG and the asymmetric cross-correlation were multifractal. In a resting state, the cross-correlation between EEG and sEMG was symmetric. The asymmetries cross-correlation between EEG and sEMG were stronger in large fluctuations under myodynamia enhancement state, and were stronger in small fluctuations under myodynamia stability state.

Action observation (AO) is a promising methodology for promoting cortical activations of the sensorimotor area via the mirror neuron systems. Integration of AO with brain-computer interfaces (BCIs) is appealing for neural rehabilitation applications. One of the important issues in BCI-based AO is discriminating when a user is actively engaged with the BCI,i.e. intentional control (IC) state versus when a user is not engaged with the BCI, i.e. non-intentional control (NC) state. In this study, we designed a visual gaiting stimulus, which was in the form gaiting sequence of a human, to elicit the steady-state motion visual evoked potential (SSMVEP) response in visual area. And we proposed a convolutional neural network (CNN) to discriminate IC and NC states. The results illustrated the proposed CNN can discriminate the IC and NC states. Furthermore, combining attention feature from the frontal area and SSMVEP features, i.e. a hybrid approach, showed significant performance improvement over only using SSMVEP features when the time window length was longer than 2s. And the accuracy achieved 91.94±6.20% when utilizing the hybrid approach in IC vs. NC discrimination.

Many of current human pose estimation methods based on depth images require training stage. However, the training stage costs huge work on making samples. And many methods for human pose occlusion condition cannot work well. In this study, a novel approach to estimate human pose with a depth image called model‐based recursive matching (MRM) is introduced. A human skeleton model with customised parameters is created based on T‐pose to fit different body types. The authors use depth image and 3D point cloud corresponding to input. In contrast to previous work, the proposed method avoids training step and can give an accurate estimation in the case of the human occlusion condition. They demonstrate the method by comparing to the method Kinect offered by using random forest on 20 human poses. And the ground truth of coordinates of pose joint is made by the motion capture system. The result shows that the proposed method not only works well on the general human pose but also can deal with human occlusion better. And the authors’ method can be also applied to the disabled people and other creatures.