In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.

As an important economic crop, apples are significantly affected by disease infestations, which can lead to substantial reductions in apple yield and economic losses. To rapidly and accurately detect apple leaf diseases, we propose a lightweight attention detection model ALD-YOLO based on the YOLOv8 architecture. To improve overall efficiency, we design the Faster_C2F module within the Backbone and Neck by optimizing YOLOv8’s primary C2F (Faster Implementation of CSP Bottleneck with 2 convolutions) modules with the more computationally effective FasterNet Block. To strengthen the model’s ability to capture multi-scale feature information and focus on smaller disease targets, the EMA (Efficient Multi-Scale Attention) module is introduced at the input end where the Neck connects to the detection module of the Head, forming a new Faster_C2F_EMA module. Two novel C2F modules can achieve the optimal balance of detection accuracy and efficiency. Furthermore, to reduce the model’s parameters and retain more image information, most convolution modules in the YOLOv8 architecture are replaced by a lightweight downsampling module ADown. In comparison with YOLOv8n and YOLOv8s, experimental results on the AppleLeaf9 dataset showed that ALD-YOLO increased mAP by 1.4% and 0.6%, and reduced GFLOPs by 29.63% and 79.93%, respectively. The CPU inference testing showed that the improvement of our model in frames per second reached up to 119.23% compared to YOLOv8s. Therefore, our model delivers more stable and efficient detection of apple leaf diseases, even on edge devices.

Long and tedious calibration time hinders the development of motor imagery- (MI-) based brain-computer interface (BCI). To tackle this problem, we use a limited labelled set and a relatively large unlabelled set from the same subject for training based on the transductive support vector machine (TSVM) framework. We first introduce an improved TSVM (ITSVM) method, in which a comprehensive feature of each sample consists of its common spatial patterns (CSP) feature and its geometric feature. Moreover, we use the concave-convex procedure (CCCP) to solve the optimization problem of TSVM under a new balancing constraint that can address the unknown distribution of the unlabelled set by considering various possible distributions. In addition, we propose an improved self-training TSVM (IST-TSVM) method that can iteratively perform CSP feature extraction and ITSVM classification using an expanded labelled set. Extensive experimental results on dataset IV-a from BCI competition III and dataset II-a from BCI competition IV show that our algorithms outperform the other competing algorithms, where the sizes and distributions of the labelled sets are variable. In particular, IST-TSVM provides average accuracies of 63.25% and 69.43% with the abovementioned two datasets, respectively, where only four positive labelled samples and sixteen negative labelled samples are used. Therefore, our algorithms can provide an alternative way to reduce the calibration time.

Upper extremity exoskeleton rehabilitation robots have become a significant piece of rehabilitation equipment, and planning their motion trajectories is essential in patient rehabilitation. In this paper, a multistrategy improved whale optimization algorithm (MWOA) is proposed for trajectory planning of upper extremity exoskeleton rehabilitation robots with emphasis on isokinetic rehabilitation. First, a piecewise polynomial was used to construct a rough trajectory. To make the trajectory conform to human-like movement, a whale optimization algorithm (WOA) was employed to generate a bounded jerk trajectory with the minimum running time as the objective. The search performance of the WOA under complex constraints, including the search capability of trajectory planning symmetry, was improved by the following strategies: a dual-population search, including a new communication mechanism to prevent falling into the local optimum; a mutation centroid opposition-based learning, to improve the diversity of the population; and an adaptive inertia weight, to balance exploration and exploitation. Simulation analysis showed that the MWOA generated a trajectory with a shorter run-time and better symmetry and robustness than the WOA. Finally, a pilot rehabilitation session on a healthy volunteer using an upper extremity exoskeleton rehabilitation robot was completed safely and smoothly along the trajectory planned by the MWOA. The proposed algorithm thus provides a feasible scheme for isokinetic rehabilitation trajectory planning of upper extremity exoskeleton rehabilitation robots.

For the electroencephalogram- (EEG-) based motor imagery (MI) brain-computer interface (BCI) system, more attention has been paid to the advanced machine learning algorithms rather than the effective MI training protocols over past two decades. However, it is crucial to assist the subjects in modulating their active brains to fulfill the endogenous MI tasks during the calibration process, which will facilitate signal processing using various machine learning algorithms. Therefore, we propose a trial-feedback paradigm to improve MI training and introduce a non-feedback paradigm for comparison. Each paradigm corresponds to one session. Two paradigms are applied to the calibration runs of corresponding sessions. And their effectiveness is verified in the subsequent testing runs of respective sessions. Different from the non-feedback paradigm, the trial-feedback paradigm presents a topographic map and its qualitative evaluation in real time after each MI training trial, so the subjects can timely realize whether the current trial successfully induces the event-related desynchronization/event-related synchronization (ERD/ERS) phenomenon, and then they can adjust their brain rhythm in the next MI trial. Moreover, after each calibration run of the trial-feedback session, a feature distribution is visualized and quantified to show the subjects’ abilities to distinguish different MI tasks and promote their self-modulation in the next calibration run. Additionally, if the subjects feel distracted during the training processes of the non-feedback and trial-feedback sessions, they can execute the blinking movement which will be captured by the electrooculogram (EOG) signals, and the corresponding MI training trial will be abandoned. Ten healthy participants sequentially performed the non-feedback and trial-feedback sessions on the different days. The experiment results showed that the trial-feedback session had better spatial filter visualization, more beneficiaries, higher average off-line and on-line classification accuracies than the non-feedback session, suggesting the trial-feedback paradigm’s usefulness in subject’s self-modulation and good ability to perform MI tasks.