Electroencephalogram (EEG) signals are inherently non-stationary and exhibit significant inter-subject variability, leading to pronounced cross-subject distribution shifts that hinder accurate emotion recognition. Although graph convolutional networks (GCNs) and domain adaptation (DA) methods have made progress in mitigating individual differences, existing approaches still face two fundamental limitations: (1) traditional GCNs rely on static functional connectivity graphs, which fail to capture the dynamic temporal evolution of neural interactions during emotional processes, and (2) most DA-based methods only emphasize global feature alignment while overlooking emotion-specific semantic structures, thereby impairing both fine-grained discriminability and cross-subject generalization. To overcome these challenges, we propose the Prototypical Contrastive Learning with Temporal Dynamic Graph Convolutional Network (PCL-TDGCN) for EEG-based emotion recognition. Specifically, we construct an adaptive global EEG pattern memory mechanism to model temporally dynamic brain networks, thereby facilitating spatiotemporal neural interactions essential for emotion representation learning. Furthermore, we design a prototypical contrastive learning strategy that incorporates: (i) intra-domain contrastive learning to enhance the discriminability of emotional state representations, and (ii) inter-domain contrastive learning to mitigate distribution shifts across domains via semantic-aware prototypical alignment. Extensive experiments on three public datasets demonstrate that the proposed PCL-TDGCN outperforms state-of-the-art methods, achieving accuracy improvements of 1.08% (SEED), 6.53% (HIED), and 0.98% (SEED-IV) in subject-dependent experiments, and 1.08% (SEED), 7.51% (HIED), and 1.99% (SEED-IV) in subject-independent scenarios, respectively.

Effective regulation of social decision-making is crucial for achieving equitable outcomes in human interactions. This study explores the impact of endogenous regulation on social decision-making and associated neural changes through a neurofeedback (NF) training framework. Given the relationship between social decision making, emotions, and frontal alpha asymmetry (FAA), this NF training enables individuals to self-regulate their FAA, thereby influencing their decision-making behavior. Eighty-one participants were randomly divided into the up-FAA group aiming at up-regulating FAA, the down-FAA group aiming at down-regulating FAA, and the sham-NF group. First, our results validated the specific NF training effect on selfregulating FAA. Notably, not all participants in the up-FAA and down-FAA groups successfully learned to regulate their FAA, leading to further subdivision into up-learner, down-learner, up-nonlearner, and down-nonlearner categories based on learning efficacy. Participants who effectively learned to reduce their FAA (down-learners) showed significant changes in decision behavior under moderately unfair conditions, characterized by increased rejection rates during the ultimatum game (UG) task. They also exhibited larger N200 amplitudes while balancing the decisionmaking period. In contrast, up learners demonstrated minimal behavioral changes despite increases in FAA. We conclude that decreases in FAA have a more pronounced impact on social decision-making than increases during NF training. This study highlights the effects of FAA self-regulation on fairness-related decision-making, revealing the neurobiological factors that shape decisions influenced by fairness perceptions. These findings offer valuable insights for enhancing social cooperation and justice.

The interaction of the brain's decision-making and feedback stages is crucial for guiding human behavior. Previous studies mainly focused on the interaction immediately after the feedback, resulting in a limited understanding of brain communication dynamics during the interaction process. This study examined the communication dynamics of the brain network during decision-feedback interaction under various feedback conditions by employing a newly developed activation network approach to reveal its underlying neural mechanism. Thirty participants completed a decision-feedback task that involved a sequence of cue-induced predictions with highly predictable, somewhat predictable, and unpredictable feedback conditions. We constructed the activation network for all experimental stages using source-level EEG data in the alpha band. Notably, the brain exhibited the highest communication efficiency ($p < 0.05$) in receiving and integrating feedback with decision-making information during the feedback stage. Furthermore, the network-behavior correlations indicated that the brain tends to evaluate unexpected feedback under highly predictable conditions and expected feedback under unpredictable conditions, suggesting distinct neural strategies of the decision-feedback interaction process. Finally, we decoded the optimization process of decision-feedback interaction across the entire task. Although network correlations between the decision and feedback stages decreased over time (high predictable: $r = -0.447$, $p = 0.001$; unpredictable: $r = -0.305$, $p = 0.032$), classification accuracy significantly improved (${r = -0.448}$, $p = 0.010$, best accuracy: 86.667% ) under the highly predictable condition, corresponding with enhanced prediction behavior. These results indicate the optimization process of the cognitive resources allocation that supports more efficient interaction and improved predictive performance. Our findings advance the understanding of the mechanisms of decision-feedback interaction.

Steady-state visual evoked potential-based brain-computer interfaces (SSVEP-BCIs) hold significant promise for enabling high-speed human-computer interaction in real-world scenarios. However, existing frequency-domain decoding methods treat frequency spectrum features (the real and imaginary spectrum features) as a single feature without considering their unique spatial and spectral characteristics, resulting in insufficient generalizable features and limited classification accuracy in cross-subject scenarios. To address this issue, we propose a Dual-Branch Attention-Based Frequency Domain Network (DB-AFDNet) to independently decode real and imaginary spectral components, aiming to acquire more discriminative and generalizable features for cross-subject applications. Specifically, we construct inter-branch attention similarity constraints to encourage the two branches to have similar attention properties, promoting to learn the consensus characteristics in the dual branches. Furthermore, we propose intra-branch orthogonality constraints to explore branch-specific discriminative features to learn generalizable features. Experimental studies on two public datasets, the Benchmark and Beta datasets, demonstrate that DB-AFDNet outperforms state-of-the-art methods in cross-subject classification, achieving a relative improvement of 1.36$\%$ and 1.45$\%$, respectively.

Brain-computer interface (BCI) based on steady- state visual evoked potentials (SSVEP) is a popular paradigm for its simplicity and high information transfer rate (ITR). Accurate and fast SSVEP decoding is crucial for reliable BCI performance. However, conventional decoding methods demand longer time windows, and deep learning models typically require subject-specific fine-tuning, leaving challenges in achieving optimal performance in cross-subject settings. This paper proposed a biofocal masking attention-based method (SSVEP-BiMA) that synergistically leverages the native and symmetric-antisymmetric components for decoding SSVEP. By utilizing multiple signal representations, the network is able to integrate features from a wider range of sample perspectives, leading to more generalized and comprehensive feature learning, which enhances both prediction accuracy and robustness. We performed experiments on two public datasets, and the results demonstrate that our proposed method surpasses baseline approaches in both accuracy and ITR. We believe that this work will contribute to the development of more efficient SSVEP-based BCI systems.

Real-time emotion recognition provides promising applications for mental healthcare monitoring and human-computer interaction design. Electroencephalography (EEG) emotion recognition has become a hot topic in the field of affective computing and intelligent brain-computer interface (BCI), and it is a feasible solution for achieving real-time emotion recognition. However, due to the uncertainty and individual specificity of emotional cognition, there are still some challenges in achieving efficient online emotion decoding applications. To address this, in this work, we propose an online emotion decoding method named DMSGL (Real-Time EEG Emotion Recognition from Dynamic Mixed Spatiotemporal Graph Learning). Specifically, in the DMSGL, we propose to explore the latent emotion-related graph features from EEG with cognition-inspired and data-driven learning strategies, and the temporal analysis with attention learning is utilized to further extract the robust spatiotemporal graph patterns for efficient EEG emotion decoding. Both simulated online emotion decoding and real-time emotion monitoring experimental results have consistently indicated that the proposed DMSGL can effectively satisfy the application requirements of real-time emotion decoding and achieves an accuracy of 68.35% in real-world online scenarios. Compared with other baseline methods, the proposed DMSGL has improved by 2-5% in the scenario of real-time emotion recognition. In conclusion, the proposed DMSGL provides a promising solution for realizing real-time emotion recognition and further exploring related applications. Our code is released on https://github.com/UESTC-BAC/DMSGL.

Recent research has consistently indicated that the fusion of electroencephalography (EEG) features from multiple modalities can integrate cognitive state expressions across diverse dimensions, resulting in a substantial increase in emotion recognition accuracy. However, redundant information within the fused multimodal features could lead to the curse of dimensionality and overfitting of the learning model. In this work, we propose a multiscale EEG feature fusion and representation strategy for EEG emotion recognition named manifold of multiscale information fusion (MMIF), in which the optimal manifold of the multiscale fusion of local and global brain activation patterns can be automatically learned to realize an efficient representation of emotional EEG signals. To evaluate the performance, in this work, both off- and online EEG emotion recognition experiments were conducted, and the experimental results consistently verified the effectiveness and feasibility of the MMIF applied in real-time emotion decoding systems. Furthermore, the analytical experiments confirmed the discriminative capabilities and cognitive interpretability of the MMIF. In summary, the proposed MMIF model may provide an efficient avenue for exploring representations and enhancing the discrimination of multimodal fusion features, which may also provide a promising solution for designing online affective braincomputer interaction systems.

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://github.com/YYingDL/NSAL-DGAT.

In soft deformable terrain environments, the robot slips due to dynamic changes in wheel-ground contact, which poses a great challenge to the design of the driving torque of its motion control system. To solve the trajectory tracking control problem of wheeled mobile robots in soft deformation terrain, an event triggering mechanism based on wheel-ground mechanical parameters was designed, in which wheel-terrain mechanics has an important influence on the driving torque and is included in the control system design process. Aiming at the wheeled mobile robot in the working environment of soft ground, considering the rolling resistance of the wheel during its driving process, a dynamic model based on wheel-ground interaction is established. Estimation of unmodelled dynamic and rolling resistance terms for wheeled mobile robots in soft deformable terrain environments by adaptive neural networks. Based on the static event triggering strategy based on constant threshold, a hybrid threshold dynamic event triggering strategy based on rolling resistance is proposed. By proving that there is a positive lower bound on the inter-event time, which means that Zeno behavior is avoided. Meanwhile, the lower bound of inter-event time will change with the designed dynamic threshold. Finally, the good control performance of the proposed algorithm under different ground environments is verified by simulation. Note to Practitioners—With the advancement of detection tasks, the working environment of wheeled mobile robots has become increasingly complex. In the motion control of a wheeled mobile robot in a soft deformable terrain working environment, the influence of the robot ’s wheel-to-ground contact is crucial to the successful realization of the task. The existing wheeled mobile robot control methods for soft deformable terrain working environment usually ignores the influence between wheels and ground, which cannot meet the application requirements of this complex scene. Aiming at the problem of tracking control of wheeled mobile robots in soft deformable terrain working environment, this paper, the traction force change caused by wheel-ground contact mechanics is taken as the main factor of event-triggered mechanism, and the force feedback event-triggered tracking control method is designed. Theoretical algorithms and simulation results show that a trade-off between robot tracking performance and communication resources in different ground environments is realized.

Currently, deep neural networks can be extremely effective in robotic tactile perception. However, a major challenge is to solve the problem of continual learning of robotic tactile perception in an open and dynamic environment. In this paper, we propose a novel continual learning method for the domian incremental learning task in the field of tactile perception. To be specific, we introduce a morphology-specific variational autoencoders which can mitigate catastrophic forgetting by generating pseudo-samples for training in the continual learning process. We integrate the generative model and the discriminative model into one model, which reduces the size of model and improves the continual learning ability. In addition, considering the ordinal information between the hardness levels, we propose to add conditional information to the model and introduce a modified loss function to combine the latent value with the hardness information, which improves the continual learning performance by controlling the distribution and quality of pseudo-sample generation. Following this, we designed a tactile robot experiment, collected hardness data, and tested our model on this object hardness recognition task. We show experimentally that, after training, the model can still maintain the accuracy of more than 94% after learning three tasks in terms. Note to Practitioners—In the field of robotics tactile perception, the issue of continual learning in robots is a crucial problem that urgently requires resolution. We hope robots to effectively engage in continual learning across multiple tasks, ensuring the acquisition of new knowledge while mitigating the risk of forgetting previously acquired knowledge. In this paper, we propose a novel continual learning method for the domian incremental learning task. we introduce a morphology-specific variational autoencoders based on replaying pseudo-samples during continual learning process which reduces the size of model and improves the continual learning ability. We enhance model performance by integrating generative and discriminative models, incorporating conditional information to control the distribution of replayed sample types, and leveraging sequential relationships among samples. It is proved that the proposed method is able to effectively improve the accuracy in a tactile domian incremental learning task.

In the soft deformable terrain environment, the running state of the wheeled mobile robot is easily affected by the complex wheel-ground interaction, which limits its running state variables and input torque. In this paper, the tracking control of wheeled mobile robot under soft deformable terrain is studied, and a dynamic event trigger mechanism is proposed. Based on the proposed trigger strategy, an adaptive event trigger optimal tracking control algorithm for wheeled mobile robot system with nonlinear constraints is designed. By analyzing the nonlinear constraint problem faced by the dynamic model of wheeled mobile robot considering skidding and slipping, the dynamic model of wheeled mobile robot in soft deformable terrain environment with force-speed mixed constraints is constructed. Combining the force-speed constraint and the state error event-triggered idea, a dynamic event-triggered mechanism containing constraint information is designed, and Zeno behavior is avoided. An adaptive event-triggered optimal controller is constructed by combining adaptive dynamic programming algorithm and policy iteration algorithm. To make the wheeled mobile robot complete the tracking control. Finally, it is verified by simulation.

Emotion recognition based on electroencephalogram (EEG) is fundamentally associated with human-like intelligence system. However, due to the noise-sensitive characteristics of EEGs and the individual variability of emotions, it is very challenging to extract inherent emotion dependent patterns from emotional EEG signals. In this work, we propose a L1-norm space defined discriminative brain network manifold learning model (L1-SGL), in which the EEG noise outliers can be effectively separated and the pseudolabeled samples caused by subjective feelings can be automatically corrected. Off-line experimental results consistently indicate that the L1-SGL can effectively suppress the influence of noise and achieve an incomparable superiority performance over other existing methods in EEG emotion recognition. Besides, benefiting from the time efficiency of the L1-SGL, an online emotion monitoring and regulation system is further implemented in this work. On-line emotion decoding experimental results (86.30%) of 25 participants prove that the L1-SGL can effectively satisfy the real-time requirements of on-line emotional monitoring applications, and the significant negative emotion regulation experimental results ( $p \lt 0.001$ ) further confirm the feasibility and effectiveness of L1-SGL model in real-time emotion regulation and interactive applications. Overall, the L1-SGL provides a promising solution for the real-time online affective brain-computer interfaces (aBCIs) and the intelligent clinical closed-loop treatments.

In electroencephalographic-based (EEG-based) emotion recognition, high non-stationarity and individual differences in EEG signals could lead to significant discrepancies between sessions/subjects, making generalization to a new session/subject very difficult. Most existing domain adaptation (DA) and multi-source domain adaptation (MSDA) techniques aim to mitigate this discrepancy by aligning feature distributions. However, when confronted with many diverse domain distributions, learning domain-invariant features via aligning pairwise feature distributions between domains can be hard or even counterproductive. To address this issue, this article proposes an attention alignment approach to learning abundant domain-invariant features. The motivation is simple: despite individual differences causing significant differences in feature distributions in EEG-based emotion recognition, shared affective cognitive attributes (attention) of spectral and spatial domains can be observed within the same emotion categories. The proposed spectral-spatial attention alignment multi-source domain adaptation (S2A2-MSDA) constructs domain attention to represent affective cognition attributes in spatial and spectral domains and utilizes domain consistent loss to align them between domains. Furthermore, to facilitate discriminative feature learning on the target classes, S2A2-MSDA learns the conditional semantic information of the target domain using a pseudo-labeling method. This algorithm has been validated on the SEED and SEED-IV datasets in cross-session and cross-subject scenarios, respectively. Experimental results demonstrate that S2A2-MSDA outperforms existing representative DA and MSDA methods, achieving state-of-the-art performance.

Electroencephalogram (EEG) brain network embodies the brain’s coordination and interaction mechanism, and the transformations of emotional states are usually accompanied with changes in brain network spatial topologies. To effectively characterize emotions, in this work, we propose a cognition-inspired graph embedding model in the L1-norm space (L1-CGE) to learn an optimal low-dimensional embedded manifold for emotional brain networks. In the L1-CGE, the original brain networks are first encoded in the affinity space with the proposed cognition-inspired metric to construct the latent geometry manifold structure of emotional brain networks, and then the graph learning objective function is defined in the L1-norm space to obtain the optimal low-dimensional representations of brain networks. Essentially, the modularized community structures of emotional brain networks can be effectively emphasized by the L1-CGE to realize an effective depiction for emotions. Compared with existing methods, the L1-CGE model has achieved state-of-the-art performance on three public emotional EEG datasets in off-line conditions. Besides, the robust real-time experimental results have been achieved with the on-line emotion decoding system designed with L1-CGE. Both off- and on-line experimental results consistently demonstrate that the proposed L1-CGE is promising to provide a potential solution for the real-time affective brain-computer interface (aBCI) system.

An optimal tracking control system using neural adaptive techniques is introduced for nonlinear systems subjected to time delay and inequality constraints, which is partially uncertain. The nonlinear inequality constraints and partial uncertain time delay of the state are considered in the discrete-time nonlinear system. By transforming the inequality constraint information into augmented system state variables, and using the precompensator method, an augmentation system that contains constraints and transformed controller information is obtained. The Lyapunov–Krasovskii functionals (LKFs) can be used to deal with the partial uncertain state time delay. Subsequently, the optimal controller, the long-term cost function, the uncertain resistance, and system dynamics can be approximated by the action, critic, the disturbance, and the state estimation NNs, and suitable adaptive laws are obtained. Furthermore, the uniform ultimate boundedness (UUB) of the signals in the closed-loop control system can be obtained by the designed near-optimal controller. The inequality constraints are satisfied and the challenge arising from partial uncertain time delay has been successfully addressed, while a numerical simulation verification example is presented.

Emotion recognition based on electroencephalography (EEG) is a significant task in the brain-computer interface field. Recently, many deep learning-based emotion recognition methods are demonstrated to outperform traditional methods. However, it remains challenging to extract discriminative features for EEG emotion recognition, and most methods ignore useful information in channel and time. This article proposes an attention-based convolutional recurrent neural network (ACRNN) to extract more discriminative features from EEG signals and improve the accuracy of emotion recognition. First, the proposed ACRNN adopts a channel-wise attention mechanism to adaptively assign the weights of different channels, and a CNN is employed to extract the spatial information of encoded EEG signals. Then, to explore the temporal information of EEG signals, extended self-attention is integrated into an RNN to recode the importance based on intrinsic similarity in EEG signals. We conducted extensive experiments on the DEAP and DREAMER databases. The experimental results demonstrate that the proposed ACRNN outperforms state-of-the-art methods.

Due to the increasing fatal traffic accidents, there are strong desire for more effective and convenient techniques for driving fatigue detection. Here, we propose a unified frameworkE-Keyto simultaneously perform personal identification (PI) and driving fatigue detection using a convolutional attention neural network (CNN-Attention). The performance was assessed using EEG data collected through a wearable dry-sensor system from 31 healthy subjects undergoing a 90-min simulated driving task. In comparison with three widely-used competitive models (including CNN, CNN-LSTM, and Attention), the proposed scheme achieved the best (p < 0.01) performance in both PI (98.5%) and fatigue detection (97.8%). Besides, the spatial-temporal structure of the proposed framework exhibits an optimal balance between classification performance and computational efficiency. Additional validation analyses were conducted to assess the reliability and practicability of the model via re-configuring the kernel size and manipulating the input data, showing that it can achieve a satisfactory performance using a subset of the input data. In sum, these findings would pave the way for further practical implementation of in-vehicle expert system, showing great potential in autonomous driving and car-sharing where currently monitoring of PI and driving fatigue are of particular interest.

In this article, we formulate lifelong learning as an online transfer learning procedure over consecutive tasks, where learning a given task depends on the accumulated knowledge. We propose a novel theoretical principled framework, lifelong online learning, where the learning process for each task is in an incremental manner. Specifically, our framework is composed of two-level predictions: the prediction information that is solely from the current task; and the prediction from the knowledge base by previous tasks. Moreover, this article tackled several fundamental challenges: arbitrary or even non-stationary task generation process, an unknown number of instances in each task, and constructing an efficient accumulated knowledge base. Notably, we provide a provable bound of the proposed algorithm, which offers insights on the how the accumulated knowledge improves the predictions. Finally, empirical evaluations on both synthetic and real datasets validate the effectiveness of the proposed algorithm.

In this paper, we study two dimensional metric learning (2DML) for matrix data from both theoretical and algorithmic perspectives. We first investigate the generalization bounds of 2DML based on the notion of Rademacher complexity, which theoretically justifies the benefits of learning from matrices directly. Furthermore, we present a novel boosting-based algorithm that scales well with the feature dimension. Finally, we introduce an efficient rank-one correction algorithm, which is tailored to our boosting learning procedure to produce a low-rank solution to 2DML. As our algorithm works directly on the data in matrix representation, it scales well with the feature dimension, keeps the structure and dependence in the data, and has a more compact structure and much fewer parameters to optimize. Extensive evaluations on several benchmark data sets also empirically verify the effectiveness and efficiency of our algorithm.

Decision response and feedback in gambling are interrelated. Different decisions lead to different ranges of feedback, which in turn influences subsequent decisions. However, the mechanism underlying the continuous decision-feedback process is still left unveiled. To fulfill this gap, we applied the hidden Markov model (HMM) to the gambling electroencephalogram (EEG) data to characterize the dynamics of this process. Furthermore, we explored the differences between distinct decision responses (i.e. choose large or small bets) or distinct feedback (i.e. win or loss outcomes) in corresponding phases. We demonstrated that the processing stages in decision-feedback process including strategy adjustment and visual information processing can be characterized by distinct brain networks. Moreover, time-varying networks showed, after decision response, large bet recruited more resources from right frontal and right center cortices while small bet was more related to the activation of the left frontal lobe. Concerning feedback, networks of win feedback showed a strong right frontal and right center pattern, while an information flow originating from the left frontal lobe to the middle frontal lobe was observed in loss feedback. Taken together, these findings shed light on general principles of natural decision-feedback and may contribute to the design of biologically inspired, participant-independent decision-feedback systems.

Learning from subject's calibration data can significantly improve the performance of a steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI), for example, the state-of-the-art target recognition methods utilize the learned subject-specific and stimulus-specific model parameters. Unfortunately, when dealing with new stimuli or new subjects, new calibration data must be acquired, thus requiring laborious calibration sessions, which becomes a major challenge in developing high-performance BCIs for real-life applications. This study investigates the feasibility of transferring the model parameters (i.e., the spatial filters and the SSVEP templates) across two different groups of visual stimuli in SSVEP-based BCIs. According to our exploration, we can extract a common spatial filter from the spatial filters across different stimulus frequencies and a common impulse response from the SSVEP templates across different neighboring stimulus frequencies, in which the common spatial filter is considered as the transferred spatial filter and the common impulse response is utilized to reconstruct the transferred SSVEP template according to the theory that an SSVEP is a superposition of the impulse responses. Then, we develop a transfer learning canonical correlation analysis (tlCCA) incorporating the transferred model parameters. For evaluation, we compare the recognition performance of the calibration-free, the calibration-based, and the proposed tlCCA on an SSVEP data set with 60 subjects. Experiment results prove that the spatial filters share commonality across different frequencies and the impulse responses share commonality across neighboring frequencies. More importantly, the tlCCA performs significantly better than the calibration-free algorithms, comparably to the calibration-based algorithm. Note to Practitioners-This work is motivated by the long calibration time problem in using an steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI) because most state-of-the-art frequency recognition methods consider merely the situation that the calibration data and the test data are from the same subject and the same visual stimulus. This article assumes that the model parameters share the stimulus-nonspecific knowledge in a limited stimulus frequency range, and thus, the subject's old calibration data can be reused to learn new model parameters for new visual stimuli. First, the model parameters can be decomposed into the stimulus-nonspecific knowledge (or subject-specific knowledge) and stimulus-specific knowledge. Second, the new model parameters can be generated via transferring the knowledge across stimulus frequencies. Then, a new recognition algorithm is developed using the transferred model parameters. Experiment results validate the assumptions, and moreover, the proposed scheme could be extended to other scenarios, such as when facing new subjects, or adopting new signal acquisition equipment, which would be helpful to the future development of zero-calibration SSVEP-based BCIs for real-life healthcare applications.

Common spatial pattern (CSP) is one of the most successful feature extraction algorithms for brain-computer interfaces (BCIs). It aims to find spatial filters that maximize the projected variance ratio between the covariance matrices of the multichannel electroencephalography (EEG) signals corresponding to two mental tasks, which can be formulated as a generalized eigenvalue problem (GEP). However, it is challenging in principle to impose additional regularization onto the CSP to obtain structural solutions (e.g., sparse CSP) due to the intrinsic nonconvexity and invariance property of GEPs. This article reformulates the CSP as a constrained minimization problem and establishes the equivalence of the reformulated and the original CSPs. An efficient algorithm is proposed to solve this optimization problem by alternately performing singular value decomposition (SVD) and least squares. Under this new formulation, various regularization techniques for linear regression can then be easily implemented to regularize the CSPs for different learning paradigms, such as the sparse CSP, the transfer CSP, and the multisubject CSP. Evaluations on three BCI competition datasets show that the regularized CSP algorithms outperform other baselines, especially for the high-dimensional small training set. The extensive results validate the efficiency and effectiveness of the proposed CSP formulation in different learning contexts.

Data-driven classification approaches have substantially boosted the classification performance in steady-state visual evoked potentials (SSVEP)-based brain-computer interface (BCI). However, as a tradeoff to classification accuracy, a long calibration session is required to collect training data, which greatly reduces the applicability of BCI. In order to minimize the calibration effort while retaining good performance, this paper considers the problem of transferring knowledge from historical subjects to new subject, i.e., subject-independent SSVEP-based BCI. To tackle the problem, we propose a novel way to learn the transferable spatial filters by estimating the invariant task-related spatial filter subspace. The bases of the invariant subspace, which we call prototype spatial filters, are robust estimation of the task-related spatial filters. They can be generalized to the unseen subject for better recovering the latent signals. A new classification approach based on the prototype filters, namely transfer template and filter canonical correlation analysis (ttf-CCA), is then proposed and compared with the state-of-art approaches on the SSVEP benchmark data set. The feasibility of the proposed method is validated by the significant improvement on the classification accuracy and information transfer rate (ITR).

The adaptive Fourier decomposition (AFD) is a greedy iterative signal decomposition algorithm in the viewpoint of energy. Instead of using a fixed basis for decomposition, AFD uses an adaptive basis to achieve efficient energy extraction. In the conventional searching method, a new basis is searched from a large dictionary at every decomposition level. This usually results in a slow searching speed. To improve the efficiency, a fast searching method based on Nelder-Mead algorithm is proposed in this paper. The AFD with the proposed searching method is applied for electrocardiography (ECG) signals in which the selection ranges of four key parameters in the proposed searching method are determined based on simulation results of an artificial ECG signal. The simulation results of real ECG data shows that the computational time of the AFD based on the proposed searching method is just half of that based on the conventional searching method with similar reconstruction error.

Among the EEG-based BCIs, SSVEP-based BCIs have gained much attention due to the advantages of relatively high information transfer rate (ITR) and short calibration time. Although in SSVEP-based BCIs the frequency recognition methods using multiple channels EEG signals may provide better accuracy, using single channel would be preferable in a practical scenario since it can make the system simple and easy-to-use. To this goal, we propose a new single channel method based on wavelet-independent component analysis (WICA) in the SSVEP-based BCI, in which wavelet transform (WT) is applied to decompose a single channel signal into several wavelet components and then independent component analysis (ICA) is applied to separate the independent sources from the wavelet components. Experimental results show that most of the time the recognition accuracy of the proposed single channel method is higher than the conventional single channel method, power spectrum (PS) method.

Electroencephalogram (EEG) signals are often contaminated with various artifacts, especially electrooculogram (EOG) or ocular artifacts that cannot be avoided consciously and largely degrade the clinical interpretation of the signals. This paper presents a study on adaptive noise cancellation (ANC) based on adaputive neuro-fuzzy inference system (ANFIS) for EOG artifacts removal, especially when time delay is significant and on real contaminated EEG signal The performance is first evaluated using simulated EEG and EOG signals, further investigation on the effect of time delay and tests on real data are also performed. The results illustrate that ANFIS provides a promising approach to ocular artifact removal with the best performance in comparison with ANC using adaptive filtering andADALINE.

The reduction of the muscle and electrode motion artifacts in ECG using the adaptive Fourier decomposition (AFD) is investigated. This is an extension of our previous work, in which AFD is first proposed for ECG denoising and its effectiveness in filtering out the additive Gaussian white noise is tested. This paper studies the AFD-based ECG denoising method for two types of ECG noise due to the electrode movement and the muscle contraction which are common and important in practice. In addition, some rules on the selection and adjustment of the AFD decomposition level are proposed. The tests on the MIT-BIH Arrhythmia Database indicate that this AFD-based denoising scheme performs better than the Butterworth lowpass filter, the wavelet transform and the empirical mode decomposition methods for ECG denoising with the muscle movement and electrode motion artifacts.

An improvement is presented for the tunnel algorithm introduced in [17] for determining the minimum number of rules required by a fuzzy system for modeling and identification in the SISO case. The original tunnel algorithm can deal with only Mamdani type fuzzy systems, while the Testing Point algorithm proposed in this paper, can be used to construct Takagi-Sugeno type fuzzy systems with consequent parts of any order and has the potential to be further extended to the MISO case. Numerical examples are given to illustrate the idea and improvement.

In this paper, we propose an entropy penalized approach to address the problem of learning the parameters of Gaussian mixture models (GMMs) with components of small weights. In addition, since the method is based on minimum message length (MML) criterion, it can also determine the number of components of the mixture model. The simulation results demonstrate that our method outperform several other state-of-art model selection algorithms especially for the mixtures with components of very different weights.

In this paper, we propose a modified visual stimulus generation method and feature detection algorithm to design a frequency and phase coding steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI). By utilizing both frequency and phase information, we solve the harmonic frequency problem in our proposed SSVEP-BCI system. The offline experimental results show that the proposed feature detection algorithm can enhance the classification rate over 10% (from 69%±12% to 82%±8%) even though only one signal electrode is used and the harmonic frequencies (6.67Hz, 13.33Hz, 8.57Hz and 17.14Hz) are employed.

Input selection is a crucial step for learning systems especially when in system modeling and identification the dataset is with a large number of variables, as a redundant input usually impairs the transparency of the underlying model and also increases the complexity of computation. The primary objective of input selection is to select the relevant inputs under the available information. This paper gives a brief review of some important issues and recent developments in the literature.

This year, the competition challenge is to develop a fuzzy controller for a nonlinear multi-input multi-output (MIMO) magnetic suspension system with satisfactory performance under different initial conditions. This paper aims at developing a concise but effective fuzzy controller, for the reason that the MIMO system can be divided into four physically independent single-input single-output (SISO) magnetic suspension systems which can be successfully controlled by a fuzzy controller with simple structure that is easy to be created, modified and understood. More specifically, a two-stage control strategy is adopted, consisting of an individual control stage that each SISO subsystem is controlled by a simple Mamdani-type fuzzy controller with intuitive rules, and a coordination stage to balance the four subsystems for the overall performance requirement. Simulation results are provided to show the performance for the required tasks.

This paper describes a 90 nm CMOS low-noise low-power biopotential signal readout front-end (RFE). The front-stage instrumentation amplifier (IA) features a chopper; an AC-coupler and a novel chopper notch filter for minimizing the DC-offset; transistors' flicker noise and 50 Hz powerline interference concurrently. A noise-aware transistor selection (thin- and thick-oxide) in the IA enables a flexible tradeoff between noise and input impedance performances. The 2ndstage is a spike filter clocked by a parallel use of two non-overlapping clock generators, effectively tracking and suppressing the chopper spikes. The last stage is a gain-bandwidth-controllable amplifier for boosting the gain and alleviating different bio-potential signal measurements through simple digital controls. Simulation results showed that the RFE is capable of tolerating a differential electrode offset up to plusmn50 mV, while achieving 140 dB CMRR and 51.4 nV/radicHz inputreferred noise density. The notch at 50 Hz achieves 41dB rejection. The entire RFE consumes 16.55 to 35.5 muA at 3V.

In a control chart, unnatural patterns are always associated with some specific assignable causes that should be eliminated. The identification of control chart pattern (CCP) is therefore important and further estimation of the unnatural pattern parameters can improve the manufacturing process. In this paper, a modified counter-propagation network (m-CPN) is developed to classify the mean shift and simultaneously estimate the shift magnitude. The m-CPN is compared with five existing networks through numerical simulation and the result shows a better performance of the m-CPN in terms of classification accuracy, as well as both Type I and Type II errors.

The process of pH process control is a challenging problem due to the strong nonlinearity and extreme sensitivity to disturbances of the process. This paper presents an application of one-step-ahead adaptive fuzzy control scheme for a strong acid-strong base neutralization process. The controller is designed based on a Mamdani type fuzzy system constructed to model the dynamics of the process. The fuzzy system model can take advantage of both a priori linguistic human knowledge through parameter initialization, and process measurements through online parameter adjustment using the least square algorithm with deadzone. In both setpoint tracking and disturbance rejection tasks, simulation experiments show satisfactory performances of the resulted pH control scheme as well as performance improvements owing to the linguistic information.

This paper discusses chaos control in discrete-time nonlinear systems using one-step-ahead adaptive fuzzy controller. The chaotic system in a general form is modeled by a Mamdani type fuzzy system with parameters tuned on-line using system input-output data by the least square algorithm with deadzone. Based on this fuzzy model, a one-step-ahead controller is designed to minimize the error between the desired and the real system outputs. Performance analysis and simulation results in control of the Sin and Lozi systems are given to show the effectiveness of the scheme.

In the last two decades, various approximation approaches, such as dispatching rules, shifting bottleneck heuristic and local search methods, are proposed for solving the job shop scheduling problem. As one of the local search methods, taboo search provides a promising alternative for the job shop scheduling problem; however, it has to be tailored each time with respect to parameters for every instance in order to produce desirable solution. In order to improve its search efficiency, an approach is proposed for the job shop scheduling problem by using taboo search with fuzzy reasoning. There are two parts in this approach: taboo search module and fuzzy reasoning module that performs the function of adaptive parameter adjustment in taboo search. The performance issues of this approach are also discussed by means of commonly used benchmarks.

This article addresses parameter convergence problem in identification of nonlinear dynamic systems using fuzzy models. We first establish persistent excitation conditions and then propose several detailed algorithms to generate input signals that guarantee the convergence of the parameter estimates in the fuzzy system models to the true values in identifications of second-order nonlinear moving-average and auto-regressive-moving-average systems. Numerical example is given to illustrate the ideas and results.

Fuzzy systems have been proved to be universal approximators, yet a large number of fuzzy rules may be needed for high approximation accuracy. In this paper, we consider how to determine the minimum number of fuzzy rules required in a fuzzy system for approximation to achieve a given accuracy and how to construct this fuzzy system when there are only a limited number of input-output data pairs of the unknown system. The key point is to partition the input space nonuniformly. In particular, a tunnel algorithm is utilized for the single-input case. Numerical examples are given to demonstrate the proposed idea and algorithm.

Fuzzy systems are proved to be universal approximators, yet they may need a large number of fuzzy rules for high approximation accuracy. For this rule-explosion problem, we introduce the idea on design of economical fuzzy systems. Given a specified architecture, a fuzzy system is called economical if it uses least fuzzy rules and at the same time it approximates the given function at a pre-required approximation accuracy. The essence of our solution is to partition the domain of the function nonuniformly. We investigate the approximation formulations of two commonly used fuzzy systems: the Mamdani and the TSK fuzzy systems with linear consequent. Then the economical fuzzy system design problem is formulated mathematically. Finally, an approximate algorithms is proposed toward designing Mamdani type economical fuzzy systems.