Yaqi Chu

Bio: Yaqi Chu is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Brain–computer interface & Computer science. The author has an hindex of 7, co-authored 14 publications receiving 165 citations. Previous affiliations of Yaqi Chu include Shenyang Ligong University & Shenyang Institute of Automation.

SSVEP-Based Brain–Computer Interface Controlled Functional Electrical Stimulation System for Upper Extremity Rehabilitation

Abstract: Traditional rehabilitation techniques have limited effects on the recovery of patients with tetraplegia A brain–computer interface (BCI) provides an interactive channel that does not depend on the normal output of peripheral nerves and muscles In this paper, an integrated framework of a noninvasive electroencephalogram (EEG)-based BCI with a noninvasive functional electrical stimulation (FES) is established, which can potentially enable the upper limbs to achieve more effective motor rehabilitation The EEG signals based on steady-state visual evoked potential are used in the BCI Their frequency domain characteristics identified by the pattern recognition method are utilized to recognize intentions of five subjects with average accuracy of 739% Furthermore the movement intentions are transformed into instructions to trigger FES, which is controlled with iterative learning control method, to stimulate the relevant muscles of upper limbs tracking desired velocity and position It is a useful technology with potential to restore, reinforce or replace lost motor function of patients with neurological injuries Experiments with five healthy subjects demonstrate the feasibility of BCI integrated with upper extremity FES toward improved function restoration for an individual with upper limb disabilities, especially for patients with tetraplegia

Physiological Signal-Based Method for Measurement of Pain Intensity.

Abstract: The standard method for prediction of the absence and presence of pain has long been self-report However, for patients with major cognitive or communicative impairments, it would be better if clinicians could quantify pain without having to rely on the patient’s self-description Here, we present a newly pain intensity measurement method based on multiple physiological signals, including blood volume pulse (BVP), electrocardiogram (ECG) and skin conductance (SC), all of which are induced by external electrical stimulation The proposed pain prediction system consists of signal acquisition and preprocessing, feature extraction, feature selection and feature reduction, and three types of pattern classifiers Feature extraction phase is devised to extract pain-related characteristics from short-segment signals A hybrid procedure of genetic algorithm-based feature selection and principal component analysis-based feature reduction was established to obtain high-quality features combination with significant discriminatory information Three types of classification algorithms—linear discriminant analysis, k-nearest neighbor algorithm, and support vector machine—are adopted during various scenarios, including multi-signal scenario, multi-subject and between-subject scenario, and multi-day scenario The classifiers gave correct classification ratios much higher than chance probability, with the overall average accuracy of 75% above for four pain intensity Our experimental results demonstrate that the proposed method can provide an objective and quantitative evaluation of pain intensity The method might be used to develop a wearable device that is suitable for daily use in clinical settings

A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network.

Abstract: High accuracy decoding of electroencephalogram (EEG) signal is still a major challenge that can hardly be solved in the design of an effective motor imagery-based brain-computer interface (BCI), especially when the signal contains various extreme artifacts and outliers arose from data loss. The conventional process to avoid such cases is to directly reject the entire severely contaminated EEG segments, which leads to a drawback that the BCI has no decoding results during that certain period. In this study, a novel decoding scheme based on the combination of Lomb-Scargle periodogram (LSP) and deep belief network (DBN) was proposed to recognize the incomplete motor imagery EEG. Particularly, instead of discarding the entire segment, two forms of data removal were adopted to eliminate the EEG portions with extreme artifacts and data loss. The LSP was utilized to steadily extract the power spectral density (PSD) features from the incomplete EEG constructed by the remaining portions. A DBN structure based on the restricted Boltzmann machine (RBM) was exploited and optimized to perform the classification task. Various comparative experiments were conducted and evaluated on simulated signal and real incomplete motor imagery EEG, including the comparison of three PSD extraction methods (fast Fourier transform, Welch and LSP) and two classifiers (DBN and support vector machine, SVM). The results demonstrate that the LSP can estimate relative robust PSD features and the proposed scheme can significantly improve the decoding performance for the incomplete motor imagery EEG. This scheme can provide an alternative decoding solution for the motor imagery EEG contaminated by extreme artifacts and data loss. It can be beneficial to promote the stability, smoothness and maintain consecutive outputs without interruption for a BCI system that is suitable for the online and long-term application.

Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression.

Abstract: Objective Due to low spatial resolution and poor signal-to-noise ratio of electroencephalogram (EEG), high accuracy classifications still suffer from lots of obstacles in the context of motor imagery (MI)-based brain-machine interface (BMI) systems. Particularly, it is extremely challenging to decode multiclass MI EEG from the same upper limb. This research proposes a novel feature learning approach to address the classification problem of 6-class MI tasks, including imaginary elbow flexion/extension, wrist supination/pronation, and hand close/open within the unilateral upper limb. Approach Instead of the traditional common spatial pattern (CSP) or filter-bank CSP (FBCSP) manner, the Riemannian geometry (RG) framework involving Riemannian distance and Riemannian mean was directly adopted to extract tangent space (TS) features from spatial covariance matrices of the MI EEG trials. Subsequently, to reduce the dimensionality of the TS features, the algorithm of partial least squares regression was applied to obtain more separable and compact feature representations. Main results The performance of the learned RG feature representations was validated by a linear discriminative analysis and support vector machine classifier, with an average accuracy of 80.50% and 79.70% on EEG dataset collected from 12 participants, respectively. Significance These results demonstrate that compared with CSP and FBCSP features, the proposed approach can significantly increase the decoding accuracy for multiclass MI tasks from the same upper limb. This approach is promising and could potentially be applied in the context of MI-based BMI control of a robotic arm or a neural prosthesis for motor disabled patients with highly impaired upper limb.

SSVEP based brain-computer interface controlled functional electrical stimulation system for upper extremity rehabilitation

Abstract: Brain-computer interface (BCI) is currently developed as an alternative technology with a potential to restore lost motor function in patients with neurological injuries. In this paper, we describe an integrated system of a non-invasive electroencephalogram (EEG)-based BCI with a non-invasive functional electrical stimulation (FES). This system enables the direct brain control of upper limbs to achieve motor rehabilitation. The EEG signals based on steady-state visual evoked potential (SSVEP) were used in the BCI. The classifier of linear discriminant analysis was applied to deal with the frequency domain characteristics and recognize intentions. The identified intentions were transformed into instructions to trigger FES which was controlled with iterative learning control method to stimulate the relevant muscles of upper limbs for motor recovery. Results show that the integration of BCI with an upper-extremity FES is feasible with an average accuracy of about 73.9% over five able-bodied subjects.

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Abstract: Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Optimized Deep Learning for EEG Big Data and Seizure Prediction BCI via Internet of Things

Abstract: A brain-computer interface (BCI) for seizure prediction provides a means of controlling epilepsy in medically refractory patients whose site of epileptogenicity cannot be resected but yet can be defined sufficiently to be selectively influenced by strategically implanted electrodes. Challenges remain in offering real-time solutions with such technology because of the immediacy of electrographic ictal behavior. The nonstationary nature of electroencephalographic (EEG) and electrocorticographic (ECoG) signals results in wide variation of both normal and ictal patterns among patients. The use of manually extracted features in a prediction task is impractical and the large amount of data generated even among a limited set of electrode contacts will create significant processing delays. Big data in such circumstances not only must allow for safe storage but provide high computational resources for recognition, capture and real-time processing of the preictal period in order to execute the timely abrogation of the ictal event. By leveraging the potential of cloud computing and deep learning, we develop and deploy BCI seizure prediction and localization from scalp EEG and ECoG big data. First, a new method for epileptic seizure prediction and localization of the seizure focus is presented. Second, an extended optimization approach on existing deep-learning structures, Stacked Auto-encoder and Convolutional Neural Network (CNN), is proposed based on principle component analysis (PCA), independent component analysis (ICA), and Differential Search Algorithm (DSA). Third, a cloud-computing solution (i.e., Internet of Things (IoT)), is developed to define the proposed structures for real-time processing, automatic computing and storage of big data. The ECoG clinical datasets on 11 patients illustrate the superiority of the proposed patient-specific BCI as an alternative to current methodology to offer support for patients with intractable focal epilepsy.

Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review

Abstract: Brain computer interfaces (BCI) for the rehabilitation of motor impairments exploit sensorimotor rhythms (SMR) in the electroencephalogram (EEG). However, the neurophysiological processes underpinning the SMR often vary over time and across subjects. Inherent intra- and inter-subject variability causes covariate shift in data distributions that impede the transferability of model parameters amongst sessions/subjects. Transfer learning includes machine learning-based methods to compensate for inter-subject and inter-session (intra-subject) variability manifested in EEG-derived feature distributions as a covariate shift for BCI. Besides transfer learning approaches, recent studies have explored psychological and neurophysiological predictors as well as inter-subject associativity assessment, which may augment transfer learning in EEG-based BCI. Here, we highlight the importance of measuring inter-session/subject performance predictors for generalized BCI frameworks for both normal and motor-impaired people, reducing the necessity for tedious and annoying calibration sessions and BCI training.

Automatic Recognition Methods Supporting Pain Assessment: A Survey

Abstract: Automated tools for pain assessment have great promise but have not yet become widely used in clinical practice. In this survey paper, we review the literature that proposes and evaluates automatic pain recognition approaches, and discuss challenges and promising directions for advancing this field. Prior to that, we give an overview on pain mechanisms and responses, discuss common clinically used pain assessment tools, and address shared datasets and the challenge of validation in the context of pain recognition.