Attention-based multi-semantic dynamical graph convolutional network for eeg-based fatigue detection.

Introduction: Establishing a driving fatigue monitoring system is of utmost importance as severe fatigue may lead to unimaginable consequences. Fatigue detection methods based on physiological information have the advantages of reliable and accurate. Among various physiological signals, EEG signals are considered to be the most direct and promising ones. However, most traditional methods overlook the functional connectivity of the brain and fail to meet real-time requirements. Methods: To this end, we propose a novel detection model called Attention-Based Multi-Semantic Dynamical Graph Convolutional Network (AMD-GCN). AMD-GCN consists of a channel attention mechanism based on average pooling and max pooling (AM-CAM), a multi-semantic dynamical graph convolution (MD-GC), and a spatial attention mechanism based on average pooling and max pooling (AM-SAM). AM-CAM allocates weights to the input features, helping the model focus on the important information relevant to fatigue detection. MD-GC can construct intrinsic topological graphs under multi-semantic patterns, allowing GCN to better capture the dependency between physically connected or non-physically connected nodes. AM-SAM can remove redundant spatial node information from the output of MD-GC, thereby reducing interference in fatigue detection. Moreover, we concatenate the DE features extracted from 5 frequency bands and 25 frequency bands as the input of AMD-GCN. Results: Finally, we conduct experiments on the public dataset SEED-VIG, and the accuracy of AMD-GCN model reached 89.94%, surpassing existing algorithms. Discussion: The findings indicate that our proposed strategy performs more effectively for EEG-based driving fatigue detection.

Reconstruction of Adaptive Leaky Integrate-and-Fire Neuron to Enhance the Spiking Neural Networks Performance by Establishing Complex Dynamics.

Since digital spiking signals can carry rich information and propagate with low computational consumption, spiking neural networks (SNNs) have received great attention from neuroscientists and are regarded as the future development object of neural networks. However, generating the appropriate spiking signals remains challenging, which is related to the dynamics property of neurons. Most existing studies imitate the biological neurons based on the correlation of synaptic input and output, but these models have only one time constant, thus ignoring the structural differentiation and versatility in biological neurons. In this article, we propose the reconstruction of adaptive leaky integrate-and-fire (R-ALIF) neuron to perform complex behaviors similar to real neurons. First, a synaptic cleft time constant is introduced into the membrane voltage charging equation to distinguish the leakage degree between the neuron membrane and the synaptic cleft, which can expand the representation space of spiking neurons to facilitate SNNs to obtain better information expression way. Second, R-ALIF constructs a voltage threshold adjustment equation to balance the firing rate of output signals. Third, three time constants are transformed into learnable parameters, enabling the adaptive adjustment of dynamics equation and enhancing the information expression ability of SNNs. Fourth, the computational graph of R-ALIF is optimized to improve the performance of SNNs. Moreover, we adopt a temporal dropout (TemDrop) method to solve the overfitting problem in SNNs and propose a data augmentation method for neuromorphic datasets. Finally, we evaluate our method on CIFAR10-DVS, ASL-DVS, and CIFAR-100, and achieve top1 accuracy of 81.0% , 99.8% , and 67.83% , respectively, with few time steps. We believe that our method will further promote the development of SNNs trained by spatiotemporal backpropagation (STBP).

An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN.

OBJECTIVES: Electroencephalogram (EEG) is often used to detect mental fatigue because of its real-time characteristic and objective nature. However, because of the individual variability of EEG among different individuals, tedious and time-consuming calibration sessions are needed. METHODS: Therefore, we propose a multi-source domain adaptation network for inter-subject mental fatigue detection named FLDANN, which is short for focal loss based domain-adversarial training of neural network. As for mental state feature extraction, power spectrum density is extracted based on the Welch method from four sub-bands of EEG signals. The features of the source domain and target domain are fed into the FLDANN network. The contributions of FLDANN include: (1) It uses the idea of adversarial to reduce feature differences between the source and target domain. (2) A loss function named focal loss is used to assign weights to source and target domain samples. RESULTS: The experiment result shows that when the number of the source domains increases, the classification accuracy of domain-adversarial training of neural network (DANN) gradually decreases and finally tends to be stable. The proposed method achieves an accuracy of 84.10% ± 8.75% on the SEED-VIG dataset and 65.42% ± 7.47% on the self-designed dataset. In addition, the proposed method is compared with other domain adaptation methods and the results show that the proposed method outperforms those state-of-the-art methods. CONCLUSIONS: The result proves that the proposed method is able to solve the problem of individual differences across subjects and to solve the problem of low classification performance of multi-source domain transfer learning.

Enhanced compensation control of pneumatic muscle actuator with high-order modified dynamic model.

Dynamic behaviour of the pneumatic muscle actuator (PMA) is conventionally modelled as a pressure-based first-order equation under discrete loads, which cannot exactly describe its dynamic features. Considering PMA's nonlinear, time-varying and hysteresis characteristics, we propose a novel high-order modified dynamic model of PMA based on its physical properties and working principle, with coefficients being identified under external dynamic loads. To tackle PMA's nonlinear hysteresis problem in high-frequency movements, a global fast terminal sliding mode controller with the modified model-based radial basis function (RBF) neural network disturbance compensator (RBF-GFTSMC) is designed. Comparison experimental studies are carried on a designed PMA platform that can provide continuously changing loads. Results show that the RBF-GFTSMC has superior trajectory tracking performance and disturbance compensation capability under wide-ranged frequencies and external loads, which can be potentially used to achieve precise control of PMA-actuated robots.

EEG-based mental fatigue detection using linear prediction cepstral coefficients and Riemann spatial covariance matrix.

Objective. Establishing a mental fatigue monitoring system is of great importance as for severe fatigue may cause unimaginable consequences. Electroencephalogram (EEG) is often utilized for mental fatigue detection because of its high temporal resolution and ease of use. However, many EEG-based approaches for detecting mental fatigue only take into account the feature extraction of a single domain and do not fully exploit the information that EEG may offer.Approach. In our work, we propose a new algorithm for mental fatigue detection based on multi-domain feature extraction and fusion. EEG components representing fatigue are closely related in the past and present because fatigue is a dynamic and gradual process. Accordingly, the idea of linear prediction is used to fit the current value with a set of sample values in the past to calculate the linear prediction cepstral coefficients (LPCCs) as the time domain feature. Moreover, in order to better capture fatigue-related spatial domain information, the spatial covariance matrix of the original EEG signal is projected into the Riemannian tangent space using the Riemannian geometric method. Then multi-domain features are fused to obtain comprehensive spatio-temporal information.Main results. Experimental results prove the suggested algorithm outperforms existing state-of-the-art methods, achieving an average accuracy of 87.10% classification on the public dataset SEED-VIG (three categories) and 97.40% classification accuracy (two categories) on the dataset made by self-designed experiments.Significance. These findings show that our proposed strategy perform more effectively for mental fatigue detection based on EEG.

Flexible coding scheme for robotic arm control driven by motor imagery decoding.

Objective. Brain computer interface (BCI) technology is an innovative way of information exchange, which can effectively convert physiological signals into control instructions of machines. Due to its spontaneity and device independence, the motor imagery (MI) electroencephalography (EEG) signal is used as a common BCI signal source to achieve direct control of external devices. Several online MI EEG-based systems have shown potential for rehabilitation. However, the generalization ability of the current classification model of MI tasks is still limited and the real-time prototype is far from widespread in practice.Approach. To solve these problems, this paper proposes an optimized neural network architecture based on our previous work. Firstly, the artifact components in the MI-EEG signal are removed by using the threshold and threshold function related to the artifact removal evaluation index, and then the data is augmented by the empirical mode decomposition (EMD) algorithm. Furthermore, the ensemble learning (EL) method and fine-tuning strategy in transfer learning (TL) are used to optimize the classification model. Finally, combined with the flexible binary encoding strategy, the EEG signal recognition results are mapped to the control commands of the robotic arm, which realizes multiple degrees of freedom control of the robotic arm.Main results. The results show that EMD has an obvious data amount enhancement effect on a small dataset, and the EL and TL can improve intra-subject and inter-subject model evaluation performance, respectively. The use of a binary coding method realizes the expansion of control instructions, i.e. four kinds of MI-EEG signals are used to complete the control of 7 degrees of freedom of the robotic arm.Significance. Our work not only improves the classification accuracy of the subject and the generality of the classification model while also extending the BCI control instruction set.

A Two-Stream Graph Convolutional Network Based on Brain Connectivity for Anesthetized States Analysis.

Investigating neural mechanisms of anesthesia process and developing efficient anesthetized state detection methods are especially on high demand for clinical consciousness monitoring. Traditional anesthesia monitoring methods are not involved with the topological changes between electrodes covering the prefrontal-parietal cortices, by investigating electrocorticography (ECoG). To fill this gap, a framework based on the two-stream graph convolutional network (GCN) was proposed, i.e., one stream for extracting topological structure features, and the other one for extracting node features. The two-stream graph convolutional network includes GCN Model 1 and GCN Model 2. For GCN Model 1, brain connectivity networks were constructed by using phase lag index (PLI), representing different structure features. A common adjacency matrix was founded through the dual-graph method, the structure features were expressed on nodes. Therefore, the traditional spectral graph convolutional network can be directly applied on the graphs with changing topological structures. On the other hand, the average of the absolute signal amplitudes was calculated as node features, then a fully connected matrix was constructed as the adjacency matrix of these node features, as the input of GCN Model 2. This method learns features of both topological structure and nodes of the graph, and uses a dual-graph approach to enhance the focus on topological structure features. Based on the ECoG signals of monkeys, results show that this method which can distinguish awake state, moderate sedation and deep sedation achieved an accuracy of 92.75% in group-level experiments and mean accuracy of 93.50% in subject-level experiments. Our work verifies the excellence of the graph convolutional network in anesthesia monitoring, the high recognition accuracy also shows that the brain network may carry neurological markers associated with anesthesia.

Bioinspired Stretchable Fiber-Based Sensor toward Intelligent Human-Machine Interactions.

Wearable integrated sensing devices with flexible electronic elements exhibit enormous potential in human-machine interfaces (HMI), but they have limitations such as complex structures, poor waterproofness, and electromagnetic interference. Herein, inspired by the profile of Lindernia nummularifolia (LN), a bionic stretchable optical strain (BSOS) sensor composed of an LN-shaped optical fiber incorporated with a stretchable substrate is developed for intelligent HMI. Such a sensor enables large strain and bending angle measurements with temperature self-compensation by the intensity difference of two fiber Bragg gratings' (FBGs') center wavelength. Such configurations enable an excellent tensile strain range of up to 80%, moreover, leading to ultrasensitivity, durability (≥20,000 cycles), and waterproofness. The sensor is also capable of measuring different human activities and achieving HMI control, including immersive virtual reality, robot remote interactive control, and personal hands-free communication. Combined with the machine learning technique, gesture classification can be achieved using muscle activity signals captured from the BSOS sensor, which can be employed to obtain the motion intention of the prosthetic. These merits effectively indicate its potential as a solution for medical care HMI and show promise in smart medical and rehabilitation medicine.

CNN-Based Hand Grasping Prediction and Control via Postural Synergy Basis Extraction.

The prediction of hand grasping and control of a robotic manipulator for hand activity training is of great significance to assist stroke patients to recover their biomechanical functions. However, the human hand and the figure joints have multiple degrees of freedom; therefore, it is complex to process and analyze all the collected data in hand modeling. To simplify the description of grasping activities, it is necessary to extract and decompose the principal components of hand actions. In this paper, the relationships among hand grasping actions are explored by extracting the postural synergy basis of hand motions, aiming to simplify hand grasping actions and reduce the data dimensions for robot control. A convolutional neural network (CNN)-based hand activity prediction method is proposed, which utilizes motion data to estimate hand grasping actions. The prediction results were then used to control a stimulated robotic model according to the extracted postural synergy basis. The prediction accuracy of the proposed method for the selected hand motions could reach up to 94% and the robotic model could be operated naturally based on patient's movement intention, so as to complete grasping tasks and achieve active rehabilitation.

Brain Connectivity Analysis in Anesthetized and Awake States: an ECoG Study in Monkeys.

Increasingly, studies have shown that changes in brain network topology accompany loss of consciousness such that the functional connectivity of the prefrontal-parietal network differs significantly in anesthetized and awake states. In this work, anesthetized and awake segments of electrocorticography were selected from two monkeys. Using phase lag index, functional connectivity matrices were built in multiple frequency bands. Quantifying topological changes in brain network through graph-theoretic properties revealed significant differences between the awake and anesthetized states. Compared to the awake state, there were distinct increases in overall and Delta prefrontal-frontal connectivity, and decreases in Alpha, Beta1 and Beta2 prefrontal-frontal connectivity during the anesthetized state, which indicate a change in the topology of the small-world network. Using functional connectivity features we achieved a satisfactory classification accuracy (93.68%). Our study demonstrates that functional connectivity features are of sufficient power to distinguish awake versus anesthetized state.Clinical Relevance- This explores the brain network topology in awake and anesthetized states, and provides new ideas for clinical depth of anesthesia monitoring.

Path Planning and Impedance Control of a Soft Modular Exoskeleton for Coordinated Upper Limb Rehabilitation.

The coordinated rehabilitation of the upper limb is important for the recovery of the daily living abilities of stroke patients. However, the guidance of the joint coordination model is generally lacking in the current robot-assisted rehabilitation. Modular robots with soft joints can assist patients to perform coordinated training with safety and compliance. In this study, a novel coordinated path planning and impedance control method is proposed for the modular exoskeleton elbow-wrist rehabilitation robot driven by pneumatic artificial muscles (PAMs). A convolutional neural network-long short-term memory (CNN-LSTM) model is established to describe the coordination relationship of the upper limb joints, so as to generate adaptive trajectories conformed to the coordination laws. Guided by the planned trajectory, an impedance adjustment strategy is proposed to realize active training within a virtual coordinated tunnel to achieve the robot-assisted upper limb coordinated training. The experimental results showed that the CNN-LSTM hybrid neural network can effectively quantify the coordinated relationship between the upper limb joints, and the impedance control method ensures that the robotic assistance path is always in the virtual coordination tunnel, which can improve the movement coordination of the patient and enhance the rehabilitation effectiveness.

Research on Channel Selection and Multi-Feature Fusion of EEG Signals for Mental Fatigue Detection.

With the rapid development of modern social science and technology, the pace of life is getting faster, and brain fatigue has become a sub-health state that seriously affects the normal life of people. Electroencephalogram (EEG) signals reflect changes in the central nervous system. Using EEG signals to assess mental fatigue is a research hotspot in related fields. Most existing fatigue detection methods are time-consuming or don't achieve satisfactory results due to insufficient features extracted from EEG signals. In this paper, a 2-back task is designed to induce fatigue. The weight value of each channel under a single feature is calculated by ReliefF algorithm. The classification accuracy of each channel under the corresponding features is analyzed. The classification accuracy of each single channel is combined to perform weighted summation to obtain the weight value of each channel. The first half channels sorted in descending order based on the weight value is chosen as the common channels. Multi-features in frequency and time domains are extracted from the common channel data, and the sparse representation method is used to perform feature fusion to obtain sparse fused features. Finally, the SRDA classifier is used to detect the fatigue state. Experimental results show that the proposed methods in our work effectively reduce the number of channels for computation and also improve the mental fatigue detection accuracy.

Characteristics of Onefold Clocks of GPS, Galileo, BeiDou and GLONASS Systems.

This research is focused on searching for frequency and noise characteristics for available GNSS (Global Navigation Satellite Systems). The authors illustrated frequency stability and noise characteristics for a selected set of data from four different GNSS systems. For this purpose, 30-s-interval clock corrections were used for the GPS weeks 1982-2034 (the entirety of 2018). Firstly, phase data (raw clock corrections) were preprocessed for shifts and removal of outliers; GLONASS and GPS satellites characterize a smaller number of outliers than BeiDou and Galileo clock products. Secondly, frequency and Hadamard deviation were calculated. This study concludes that the stability of GPS and Galileo is better than that of BDS (BeiDou Navigation Satellite System) and GLONASS. Regarding noise, the GPS, Galileo, and BDS clocks are affected by the random walk modulation noise (RWFM), flashing frequency modulation noise (FFM), and white frequency modulation noise (WFM), whereas the GLONASS clocks are mainly affected only by WFM.

Online detection of class-imbalanced error-related potentials evoked by motor imagery.

Objective.Error-related potentials (ErrPs) are spontaneous electroencephalogram signals related to the awareness of erroneous responses within brain domain. ErrPs-based correction mechanisms can be applied to motor imagery-brain-computer interface (MI-BCI) to prevent incorrect actions and ultimately improve the performance of the hybrid BCI. Many studies on ErrPs detection are mostly conducted under offline conditions with poor classification accuracy and the error rates of ErrPs are preset in advance, which is too ideal to apply in realistic applications. In order to solve these problems, a novel method based on adaptive autoregressive (AAR) model and common spatial pattern (CSP) is proposed for ErrPs feature extraction. In addition, an adaptive threshold classification method based spectral regression discriminant analysis (SRDA) is suggested for class-unbalanced ErrPs data to reduce the false positives and false negatives.Approach.As for ErrPs feature extraction, the AAR coefficients in the temporal domain and CSP in the spatial domain are fused. Given that the performance of different subjects' MI tasks is different but stable, and the samples of ErrPs are class-imbalanced, an adaptive threshold based SRDA is suggested for classification. Two datasets are used in this paper. The open public clinical neuroprosthetics and brain interaction (CNBI) dataset is used to validate the performance of the proposed feature extraction algorithm and the real-time data recorded in our self-designed system is used to validate the performance of the proposed classification algorithm under class-imbalanced situations. Different from the pseudo-random paradigm, the ErrPs signals collected in our experiments are all elicited by four-class of online MI-BCI tasks, and the sample distribution is more natural and suitable for practical tests.Main results.The experimental results on the CNBI dataset show that the average accuracy and false positive rate for ErrPs detection are 94.1% and 8.1%, which outperforms methods using features extracted from a single domain. What's more, although the ErrPs induction rate is affected by the performance of subjects' MI-BCI tasks, experimental results on data recorded in the self-designed system prove that the ErrPs classification algorithm based on an adaptive threshold is robust under different ErrPs data distributions. Compared with two other methods, the proposed algorithm has advantages in all three measures which are accuracy, F1-score and false positive rate. Finally, ErrPs detection results were used to prevent wrong actions in a MI-BCI experiment, and it leads to a reduction of the hybrid BCI error rate from 48.9% to 24.3% in online tests.Significance.Both the AAR-CSP fused feature extraction and the adaptive threshold based SRDA classification methods suggested in our work are efficient in improving the ErrPs detection accuracy and reducing the false positives. In addition, by introducing ErrPs to multi-class MI-BCIs, the MI decoding results can be corrected after ErrPs are detected to avoid executing wrong instructions, thereby improving the BCI accuracy and lays the foundation for using MI-BCIs in practical applications.

Feature extraction of four-class motor imagery EEG signals based on functional brain network.

OBJECTIVE: A motor-imagery-based brain-computer interface (MI-BCI) provides an alternative way for people to interface with the outside world. However, the classification accuracy of MI signals remains challenging, especially with an increased number of classes and the presence of high variations with data from multiple individual people. This work investigates electroencephalogram (EEG) signal processing techniques, aiming to enhance the classification performance of multiple MI tasks in terms of tackling the challenges caused by the vast variety of subjects. APPROACH: This work introduces a novel method to extract discriminative features by combining the features of functional brain networks with two other feature extraction algorithms: common spatial pattern (CSP) and local characteristic-scale decomposition (LCD). After functional brain networks are established from the MI EEG signals of the subjects, the measures of degree in the binary networks are extracted as additional features and fused with features in the frequency and spatial domains extracted by the CSP and LCD algorithms. A real-time BCI robot control system is designed and implemented with the proposed method. Subjects can control the movement of the robot through four classes of MI tasks. Both the BCI competition IV dataset 2a and real-time data acquired in our designed system are used to validate the performance of the proposed method. MAIN RESULTS: As for the offline data experiment results, the average classification accuracy of the proposed method reaches 79.7%, outperforming the majority of popular algorithms. Experimental results with real-time data also prove the proposed method to be highly promising in its real-time performance. SIGNIFICANCE: The experimental results show that our proposed method is robust in extracting discriminative brain activity features when performing different MI tasks, hence improving the classification accuracy in four-class MI tasks. The high classification accuracy and low computational demand show a considerable practicality for real-time rehabilitation systems.

Frontal EEG Temporal and Spectral Dynamics Similarity Analysis between Propofol and Desflurane Induced Anesthesia Using Hilbert-Huang Transform.

Electroencephalogram (EEG) signal analysis is commonly employed to extract information on the brain dynamics. It mainly targets brain status and communication, thus providing potential to trace differences in the brain's activity under different anesthetics. In this article, two kinds of gamma-amino butyric acid (type A -GABAA) dependent anesthetic agents, propofol and desflurane (28 and 23 patients), were studied and compared with respect to EEG spectrogram dynamics. Hilbert-Huang Transform (HHT) was employed to compute the time varying spectrum for different anesthetic levels in comparison with Fourier based method. Results show that the HHT method generates consistent band power (slow and alpha) dominance pattern as Fourier method does, but exhibits higher concentrated power distribution within each frequency band than the Fourier method during both drugs induced unconsciousness. HHT also finds slow and theta bands peak frequency with better convergence by standard deviation (propofol-slow: 0.46 to 0.24; theta: 1.42 to 0.79; desflurane-slow: 0.30 to 0.25; theta: 1.42 to 0.98) and a shift to relatively lower values for alpha band (propofol: 9.94 Hz to 10.33 Hz, desflurane 8.44 Hz to 8.84 Hz) than Fourier one. For different stage comparisons, although HHT shows significant alpha power increases during unconsciousness stage as the Fourier did previously, it finds no significant high frequency (low gamma) band power difference in propofol whereas it does in desflurane. In addition, when comparing the HHT results within two groups during unconsciousness, high beta band power in propofol is significantly larger than that of desflurane while delta band power behaves oppositely. In conclusion, this study convincingly shows that EEG analyzed here considerably differs between the HHT and Fourier method.

Mutual-Information-Based Incremental Relaying Communications for Wireless Biomedical Implant Systems.

Network lifetime maximization of wireless biomedical implant systems is one of the major research challenges of wireless body area networks (WBANs). In this paper, a mutual information (MI)-based incremental relaying communication protocol is presented where several on-body relay nodes and one coordinator are attached to the clothes of a patient. Firstly, a comprehensive analysis of a system model is investigated in terms of channel path loss, energy consumption, and the outage probability from the network perspective. Secondly, only when the MI value becomes smaller than the predetermined threshold is data transmission allowed. The communication path selection can be either from the implanted sensor to the on-body relay then forwards to the coordinator or from the implanted sensor to the coordinator directly, depending on the communication distance. Moreover, mathematical models of quality of service (QoS) metrics are derived along with the related subjective functions. The results show that the MI-based incremental relaying technique achieves better performance in comparison to our previous proposed protocol techniques regarding several selected performance metrics. The outcome of this paper can be applied to intra-body continuous physiological signal monitoring, artificial biofeedback-oriented WBANs, and telemedicine system design.

Hierarchical Compliance Control of a Soft Ankle Rehabilitation Robot Actuated by Pneumatic Muscles.

Traditional compliance control of a rehabilitation robot is implemented in task space by using impedance or admittance control algorithms. The soft robot actuated by pneumatic muscle actuators (PMAs) is becoming prominent for patients as it enables the compliance being adjusted in each active link, which, however, has not been reported in the literature. This paper proposes a new compliance control method of a soft ankle rehabilitation robot that is driven by four PMAs configured in parallel to enable three degrees of freedom movement of the ankle joint. A new hierarchical compliance control structure, including a low-level compliance adjustment controller in joint space and a high-level admittance controller in task space, is designed. An adaptive compliance control paradigm is further developed by taking into account patient's active contribution and movement ability during a previous period of time, in order to provide robot assistance only when it is necessarily required. Experiments on healthy and impaired human subjects were conducted to verify the adaptive hierarchical compliance control scheme. The results show that the robot hierarchical compliance can be online adjusted according to the participant's assessment. The robot reduces its assistance output when participants contribute more and vice versa, thus providing a potentially feasible solution to the patient-in-loop cooperative training strategy.

Disturbance-Estimated Adaptive Backstepping Sliding Mode Control of a Pneumatic Muscles-Driven Ankle Rehabilitation Robot.

A rehabilitation robot plays an important role in relieving the therapists' burden and helping patients with ankle injuries to perform more accurate and effective rehabilitation training. However, a majority of current ankle rehabilitation robots are rigid and have drawbacks in terms of complex structure, poor flexibility and lack of safety. Taking advantages of pneumatic muscles' good flexibility and light weight, we developed a novel two degrees of freedom (2-DOF) parallel compliant ankle rehabilitation robot actuated by pneumatic muscles (PMs). To solve the PM's nonlinear characteristics during operation and to tackle the human-robot uncertainties in rehabilitation, an adaptive backstepping sliding mode control (ABS-SMC) method is proposed in this paper. The human-robot external disturbance can be estimated by an observer, who is then used to adjust the robot output to accommodate external changes. The system stability is guaranteed by the Lyapunov stability theorem. Experimental results on the compliant ankle rehabilitation robot show that the proposed ABS-SMC is able to estimate the external disturbance online and adjust the control output in real time during operation, resulting in a higher trajectory tracking accuracy and better response performance especially in dynamic conditions.

Feature Selection for Motor Imagery EEG Classification Based on Firefly Algorithm and Learning Automata.

Motor Imagery (MI) electroencephalography (EEG) is widely studied for its non-invasiveness, easy availability, portability, and high temporal resolution. As for MI EEG signal processing, the high dimensions of features represent a research challenge. It is necessary to eliminate redundant features, which not only create an additional overhead of managing the space complexity, but also might include outliers, thereby reducing classification accuracy. The firefly algorithm (FA) can adaptively select the best subset of features, and improve classification accuracy. However, the FA is easily entrapped in a local optimum. To solve this problem, this paper proposes a method of combining the firefly algorithm and learning automata (LA) to optimize feature selection for motor imagery EEG. We employed a method of combining common spatial pattern (CSP) and local characteristic-scale decomposition (LCD) algorithms to obtain a high dimensional feature set, and classified it by using the spectral regression discriminant analysis (SRDA) classifier. Both the fourth brain-computer interface competition data and real-time data acquired in our designed experiments were used to verify the validation of the proposed method. Compared with genetic and adaptive weight particle swarm optimization algorithms, the experimental results show that our proposed method effectively eliminates redundant features, and improves the classification accuracy of MI EEG signals. In addition, a real-time brain-computer interface system was implemented to verify the feasibility of our proposed methods being applied in practical brain-computer interface systems.