A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification.

A Brain-Computer Interface (BCI) is a medium for communication between the human brain and computers, which does not rely on other human neural tissues, but only decodes Electroencephalography (EEG) signals and converts them into commands to control external devices. Motor Imagery (MI) is an important BCI paradigm that generates a spontaneous EEG signal without external stimulation by imagining limb movements to strengthen the brain's compensatory function, and it has a promising future in the field of computer-aided diagnosis and rehabilitation technology for brain diseases. However, there are a series of technical difficulties in the research of motor imagery-based brain-computer interface (MI-BCI) systems, such as: large individual differences in subjects and poor performance of the cross-subject classification model; a low signal-to-noise ratio of EEG signals and poor classification accuracy; and the poor online performance of the MI-BCI system. To address the above problems, this paper proposed a combined virtual electrode-based EEG Source Analysis (ESA) and Convolutional Neural Network (CNN) method for MI-EEG signal feature extraction and classification. The outcomes reveal that the online MI-BCI system developed based on this method can improve the decoding ability of multi-task MI-EEG after training, it can learn generalized features from multiple subjects in cross-subject experiments and has some adaptability to the individual differences of new subjects, and it can decode the EEG intent online and realize the brain control function of the intelligent cart, which provides a new idea for the research of an online MI-BCI system.

Therapeutic Effect of Acupotomy at Sanheyang for Cartilage Collagen Damage in Moderate Knee Osteoarthritis: A Rabbit Model.

Objective: Acupotomy based on the meridian-sinew theory of traditional Chinese medicine has benefits in treating knee osteoarthritis (KOA). The current study aims to prove that acupotomy at the sinew points of Sanheyang protect the knee joint and alleviate the progression of moderate KOA by evaluating KOA symptoms, cartilage structure, and analyzing the changes of cytokines in rabbit cartilage. Methods: The model used was mono-iodoacetate-induced moderate KOA in the rabbit's right leg. Rabbits were divided into the model group, the acupotomy group, and the control group, with each group receiving two parts of treatment for 2 weeks and 4 weeks. We evaluated pain in the knee joint and range of motion. The articular cartilage sections were stained with Safranin O/Fast Green and Masson. We used immunohistochemistry and real-time PCR to detect the protein and mRNA expressions of collagen prototype II (COL-II), matrix metalloproteinase 13 (MMP13), and integrin-ß1 (ITG-ß1). Results: Compared with the model group, the acupotomy group had higher body weight, lower pain score, higher range of motion, lower Mankin score, and significantly lower protein and mRNA expression of MMP13. After 4 weeks of treatment, Col-II expression in the acupotomy group was significantly higher than that in the model group and the expression of ITG-ß1 in the model group was abnormally increased. Conclusion: Acupotomy at Sanheyang improved the pain symptoms and range of joint motion in rabbits with moderate KOA, and could protect Col-II by regulating MMP13, which may be related to ITG-ß1-mediated mechanical force transmission, thus reducing the damage to cartilage structure and delaying the progression of moderate KOA.

An In Situ Prepared Comb-like Polycaprolactone-Based Gel Electrolyte for High-Performance Lithium Metal Batteries.

Herein, we present the synthesis and electrochemical performance of a comb-like polycaprolactone-based gel electrolyte from acrylate terminated polycaprolactone oligomers and liquid electrolyte for high-voltage lithium metal batteries. The ionic conductivity of this gel electrolyte at room temperature was measured to be 8.8 × 10-3 S cm-1, which is an exceptionally high value that is more than sufficient for the stable cycling of solid-state lithium metal batteries. The Li+ transference number was detected to be 0.45, facilitating the prohibition of concentration gradients and polarization, thereby prohibiting lithium dendrite formation. In addition, the gel electrolyte exhibits high oxidation voltage up to 5.0 V vs. Li+/Li and perfect compatibility against metallic lithium electrodes. The superior electrochemical properties provide the LiFePO4-based solid-state lithium metal batteries with excellent cycling stability, displaying a high initial discharge capacity of 141 mAh g-1 and an extraordinary capacity retention exceeding 74% of its initial specific capacity after being cycled for 280 cycles at 0.5C at room temperature. This paper presents a simple and effective in situ preparation process yielding an excellent gel electrolyte for high-performance lithium metal battery applications.

GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-Resolved EEG Motor Imagery Signals.

Toward the development of effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by an electroencephalogram (EEG) is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning (DL) framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected (FC) softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and groupwise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet dataset), 96.24% and 80.89% (high gamma dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step toward better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain MI. A DL library for EEG task classification including the code for this study is open source at https://github.com/SuperBruceJia/ EEG-DL for scientific research.

Gastrocnemius Muscle Injury Is the Condition to Induce Cartilage Degeneration of the Rabbit Tibiofemoral Joint: A New Perspective.

The knee osteoarthritis is a common joint disease that causes pain and inconvenience. Clinically, patients with knee osteoarthritis often have response points on the gastrocnemius. Gastrocnemius plays an essential role in stabilizing joints and changing gait and pace, which also has a close relationship with the knee joint. The objective of this study is to determine changes in the tibiofemoral joint after medial and lateral gastrocnemius injury. Rabbits were divided into a medial gastrocnemius injury group, a lateral gastrocnemius injury group, and a control group with two intervals: 6 and 8 weeks after modeling of the semisevered gastrocnemius. The gastrocnemius was weighed and sectioned for histology. The joint space and subchondral bone were observed using X-ray and microcomputed tomography. The cartilage was observed histologically using Safranin O fast green and Masson and immunohistochemically using antibodies to collagen type II, matrix metalloproteinase 13, and integrin beta1. Results showed muscle fiber atrophy, and fibrotic changes occurred after gastrocnemius semidissociation. After gastrocnemius injury, the femoral condyle of the tibiofemoral joint produced abnormal sclerosis and bone degeneration. The pathological changes of cartilage included disordered or reduced cell alignment, cartilage matrix loss, and collagen loss due to decreased collagen type II and increased matrix metalloproteinase 13 activity. The increase of integrin beta1 in the injured group may be related to mechanical conduction process. The results suggest that gastrocnemius injury is an essential factor in tibiofemoral arthritis.

A Motor Imagery Signals Classification Method via the Difference of EEG Signals Between Left and Right Hemispheric Electrodes.

Brain-computer interface (BCI) based on motor imagery (MI) can help patients with limb movement disorders in their normal life. In order to develop an efficient BCI system, it is necessary to decode high-accuracy motion intention by electroencephalogram (EEG) with low signal-to-noise ratio. In this article, a MI classification approach is proposed, combining the difference in EEG signals between the left and right hemispheric electrodes with a dual convolutional neural network (dual-CNN), which effectively improved the decoding performance of BCI. The positive and inverse problems of EEG were solved by the boundary element method (BEM) and weighted minimum norm estimation (WMNE), and then the scalp signals were mapped to the cortex layer. We created nine pairs of new electrodes on the cortex as the region of interest. The time series of the nine electrodes on the left and right hemispheric are respectively used as the input of the dual-CNN model to classify four MI tasks. The results show that this method has good results in both group-level subjects and individual subjects. On the Physionet database, the averaged accuracy on group-level can reach 96.36%, while the accuracies of four MI tasks reach 98.54, 95.02, 93.66, and 96.19%, respectively. As for the individual subject, the highest accuracy is 98.88%, and its four MI accuracies are 99.62, 99.68, 98.47, and 97.73%, respectively.

Supramolecular Thixotropic Ionogel Electrolyte for Sodium Batteries.

Owing to the potential of sodium as an alternative to lithium as charge carrier, increasing attention has been focused on the development of high-performance electrolytes for Na batteries in recent years. In this regard, gel-type electrolytes, which combine the outstanding ionic conductivity of liquid electrolytes and the safety of solid electrolytes, demonstrate immense application prospects. However, most gel electrolytes not only need a number of specific techniques for molding, but also typically suffer from breakage, leading to a short service life and severe safety issues. In this study, a supramolecular thixotropic ionogel electrolyte is proposed to address these problems. This thixotropic electrolyte is formed by the supramolecular self-assembly of D-gluconic acetal-based gelator (B8) in an ionic liquid solution of a Na salt, which exhibits moldability, a high ionic conductivity, and a rapid self-healing property. The ionogel electrolyte is chemically stable to Na and exhibits a good Na+ transference number. In addition, the self-assembly mechanism of B8 and thixotropic mechanism of ionogel are investigated. The safe, low-cost and multifunctional ionogel electrolyte developed herein supports the development of future high-performance Na batteries.

A novel method for classification of multi-class motor imagery tasks based on feature fusion.

Motor imagery based brain computer interface (MI-BCI) has the advantage of strong independence that can rely on the spontaneous brain activity of the user to operate external devices. However, MI-BCI still has the problem of poor control effect, which requires more effective feature extraction algorithms and classification methods to extract distinctly separable features from electroencephalogram (EEG) signals. This paper proposes a novel framework based on Bispectrum, Entropy and common spatial pattern (BECSP). Here we use three methods of bispectrum in higher order spectra, entropy and CSP to extract MI-EEG signal features, and then select the most contributing features through tree-based feature selection algorithm. By comparing the classification results of SVM, Random Forest, Naive Bayes, LDA, KNN, Xgboost and Adaboost, we finally decide to use the SVM algorithm based on RBF kernel function which obtained the best result among them for classification. The proposed method is applied to the BCI competition IV data set 2a and BCI competition III data set IVa. On data set 2a, the highest accuracy on the evaluation data set reaches 85%. The experiment on data set IVa can also achieve good results. Compared with other algorithms that use the same data set, the performance of our algorithm has also been improved.

[Unity and separation of lifting-thrusting and twirling reinforcing-reducing manipulation].

To analyze the collaborative use and separation reasons of lifting-thrusting and twirling reinforcing and reducing manipulation. Lifting-thrusting manipulation and twirling manipulation are two important contents of acupuncture methods. In traditional acupuncture and moxibustion, the two methods were used in reinforcing and reducing concert, which was mainly related to the therapeutic thought guided by the qi-blood theory and the influence of the human body structure on the technique manipulation. After the Republic of China, the separation of lifting-thrusting manipulation and twirling manipulation gradually appeared. It was related to the widespread use of "scientific acupuncture method" in later generations and the integration of neuroscience into the acupuncture treatment system.

Deep Feature Mining via the Attention-Based Bidirectional Long Short Term Memory Graph Convolutional Neural Network for Human Motor Imagery Recognition.

Recognition accuracy and response time are both critically essential ahead of building the practical electroencephalography (EEG)-based brain-computer interface (BCI). However, recent approaches have compromised either the classification accuracy or the responding time. This paper presents a novel deep learning approach designed toward both remarkably accurate and responsive motor imagery (MI) recognition based on scalp EEG. Bidirectional long short-term memory (BiLSTM) with the attention mechanism is employed, and the graph convolutional neural network (GCN) promotes the decoding performance by cooperating with the topological structure of features, which are estimated from the overall data. Particularly, this method is trained and tested on the short EEG recording with only 0.4 s in length, and the result has shown effective and efficient prediction based on individual and groupwise training, with 98.81% and 94.64% accuracy, respectively, which outperformed all the state-of-the-art studies. The introduced deep feature mining approach can precisely recognize human motion intents from raw and almost-instant EEG signals, which paves the road to translate the EEG-based MI recognition to practical BCI systems.

Human-in-the-Loop Low-Shot Learning.

We consider a human-in-the-loop scenario in the context of low-shot learning. Our approach was inspired by the fact that the viability of samples in novel categories cannot be sufficiently reflected by those limited observations. Some heterogeneous samples that are quite different from existing labeled novel data can inevitably emerge in the testing phase. To this end, we consider augmenting an uncertainty assessment module into low-shot learning system to account into the disturbance of those out-of-distribution (OOD) samples. Once detected, these OOD samples are passed to human beings for active labeling. Due to the discrete nature of this uncertainty assessment process, the whole Human-In-the-Loop Low-shot (HILL) learning framework is not end-to-end trainable. We hence revisited the learning system from the aspect of reinforcement learning and introduced the REINFORCE algorithm to optimize model parameters via policy gradient. The whole system gains noticeable improvements over existing low-shot learning approaches.

Gated Value Network for Multilabel Classification.

We introduce a gated value network (GVN) for general multilabel classification (MLC) tasks. GVN was motivated by deep value network (DVN) that directly exploits the "compatibility" metric as the learning pursuit for MLC. Meanwhile, it further improves traditional DVN on twofold. First, GVN relaxes the complex variable optimization steps in DVN inference by incorporating a feedforward predictor for straightforward multilabel prediction. Second, GVN also introduces the gating mechanism to block confounding factors from the input data that allows more precise compatibility evaluations for data and their potential multilabels. The whole GVN framework is trained in an end-to-end manner with policy gradient approaches. We show the effectiveness and generalization of GVN on diverse learning tasks, including document classification, audio tagging, and image attribute prediction.

A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals.

A brain-computer interface (BCI) based on electroencephalography (EEG) can provide independent information exchange and control channels for the brain and the outside world. However, EEG signals come from multiple electrodes, the data of which can generate multiple features. How to select electrodes and features to improve classification performance has become an urgent problem to be solved. This paper proposes a deep convolutional neural network (CNN) structure with separated temporal and spatial filters, which selects the raw EEG signals of the electrode pairs over the motor cortex region as hybrid samples without any preprocessing or artificial feature extraction operations. In the proposed structure, a 5-layer CNN has been applied to learn EEG features, a 4-layer max pooling has been used to reduce dimensionality, and a fully-connected (FC) layer has been utilized for classification. Dropout and batch normalization are also employed to reduce the risk of overfitting. In the experiment, the 4 s EEG data of 10, 20, 60, and 100 subjects from the Physionet database are used as the data source, and the motor imaginations (MI) tasks are divided into four types: left fist, right fist, both fists, and both feet. The results indicate that the global averaged accuracy on group-level classification can reach 97.28%, the area under the receiver operating characteristic (ROC) curve stands out at 0.997, and the electrode pair with the highest accuracy on 10 subjects dataset is FC3-FC4, with 98.61%. The research results also show that this CNN classification method with minimal (2) electrode can obtain high accuracy, which is an advantage over other methods on the same database. This proposed approach provides a new idea for simplifying the design of BCI systems, and accelerates the process of clinical application.

A novel approach of decoding EEG four-class motor imagery tasks via scout ESI and CNN.

OBJECTIVE: To develop and implement a novel approach which combines the technique of scout EEG source imaging (ESI) with convolutional neural network (CNN) for the classification of motor imagery (MI) tasks. APPROACH: The technique of ESI uses a boundary element method (BEM) and weighted minimum norm estimation (WMNE) to solve the EEG forward and inverse problems, respectively. Ten scouts are then created within the motor cortex to select the region of interest (ROI). We extract features from the time series of scouts using a Morlet wavelet approach. Lastly, CNN is employed for classifying MI tasks. MAIN RESULTS: The overall mean accuracy on the Physionet database reaches 94.5% and the individual accuracy of each task reaches 95.3%, 93.3%, 93.6%, 96% for the left fist, right fist, both fists and both feet, correspondingly, validated using ten-fold cross validation. We report an increase of up to 14.4% for overall classification compared with the competitive results from the state-of-the-art MI classification methods. Then, we add four new subjects to verify the validity of the method and the overall mean accuracy is 92.5%. Furthermore, the global classifier was adapted to single subjects improving the overall mean accuracy to 94.54%. SIGNIFICANCE: The combination of scout ESI and CNN enhances BCI performance of decoding EEG four-class MI tasks.

Distinguishing Different Emotions Evoked by Music via Electroencephalographic Signals.

Music can evoke a variety of emotions, which may be manifested by distinct signals on the electroencephalogram (EEG). Many previous studies have examined the associations between specific aspects of music, including the subjective emotions aroused, and EEG signal features. However, no study has comprehensively examined music-related EEG features and selected those with the strongest potential for discriminating emotions. So, this paper conducted a series of experiments to identify the most influential EEG features induced by music evoking different emotions (calm, joy, sad, and angry). We extracted 27-dimensional features from each of 12 electrode positions then used correlation-based feature selection method to identify the feature set most strongly related to the original features but with lowest redundancy. Several classifiers, including Support Vector Machine (SVM), C4.5, LDA, and BPNN, were then used to test the recognition accuracy of the original and selected feature sets. Finally, results are analyzed in detail and the relationships between selected feature set and human emotions are shown clearly. Through the classification results of 10 random examinations, it could be concluded that the selected feature sets of Pz are more effective than other features when using as the key feature set to classify human emotion statues.

A highly selective fluorescent probe for Cu2+ based on rhodamine B derivative.

A new fluorescent probe 1 for Cu(2+) based on a rhodamine B derivative was designed and synthesized. Probe 1 displays high sensitivity toward Cu(2+) and about a 37-fold increase in fluorescence emission intensity is observed upon the addition of 10 equiv. Cu(2+) in 50% water/ethanol buffered at pH 7.10. Besides, upon binding Cu(2+) a remarkable color change from colorless to pink was easily observed by the naked eyes. The reversible dual chromo- and fluorogenic response toward Cu(2+) is likely due to the chelation-induced ring-opening of rhodamine spirolactam. The linear response range covers a concentration range of Cu(2+) from 8.0×10(-7) to 1.0×10(-4) mol/L and the detection limit is 3.0×10(-7) mol/L. Except Co(2+), the probe exhibits high selectivity for Cu(2+) over a large number of cations such as alkaline, alkaline earth and transitional metal ions. The accuracy and precision of the method were evaluated by the analysis of the standard reference material, copper in water (1.0 mol/L HNO3). The proposed probe has been used for direct measurement of Cu(2+) content in river water samples and imaging of Cu(2+) in living cells with satisfying results, which further demonstrates its value of practical applications in environmental and biological systems.

Novel pyrrolopyridinone derivatives as anticancer inhibitors towards Cdc7: QSAR studies based on dockings by solvation score approach.

A series of pyrrolopyridinone derivatives as specific inhibitors towards the cell division cycle 7 (Cdc7) was taken into account, and the efficacy of these compounds was analyzed by QSAR and docking approaches to gain deeper insights into the interaction mechanism and ligands selectivity for Cdc7. By regression analysis the prediction models based on Grid score and Zou-GB/SA score were found, respectively with good quality of fits (r(2)=0.748, 0.951; r(cv)(2)=0.712, 0.839). The accuracy of the models was validated by test set and the deviation of the predicted values in validation set using Zou-GB/SA score was smaller than that using Grid score, suggesting that the model based on Zou-GB/SA score provides a more effective method for predicting potencies of Cdc7 inhibitors.

A highly selective fluorescent sensor for Fe3+ based on covalently immobilized derivative of naphthalimide.

In this paper, the fabrication and analytical characteristics of fluorescence-based ferric ion-sensing glass slides were described. To fabricate the sensor, a naphthalimide derivative (compound 1) with a terminal double bond was synthesized and copolymerized with 2-hydroxyethyl methacrylate (HEMA) on the activated surface of glass slides by UV irradiation. Upon the addition of Fe(3+) in 0.05 mol/L Tris/HCl (pH 6.02) at 25 °C, the fluorescence intensity of the resulting optical sensor decrease, which has been utilized as the basis for the selective detection of Fe(3+). The sensor can be applied to the quantification of Fe(3+) with a linear range covering form 1.0×10(-5) to 1.0×10(-3) M and a detection limit of 4.5×10(-6) M. The experiment results show that the response behavior of the sensor to Fe(3+) is pH-independent in medium condition (pH 5.00-8.00) and exhibits high selectivity for Fe(3+) over a large number of cations such as alkali, alkaline earth and transitional metal ions. Moreover, satisfactory reproducibility, reversibility and a rapid response were realized. The sensing membrane was found to have a lifetime at least 2 months. The accuracy and the precision of the method were evaluated by the analysis of the standard reference material, iron in water (1.0 mol/L HNO3). The developed sensor is applied for the determination of iron in pharmaceutical preparation samples with satisfactory results.

2-Meth-oxy-N-[(S)-3-methyl-butan-2-yl]-6-{[(S)-3-methyl-butan-2-yl]amino}-3,5-dinitro-benzamide.

The title compound, C(18)H(28)N(4)O(6), crystallizes with two mol-ecules in the asymmetric unit which differ slightly in conformation. The dihedral angle between the amide plane and the benzene ring are 72.6 (2) and 66.8 (2)° in the two mol-ecules. A strong intra-molecular N-H⋯O hydrogen bond between the amino and nitro groups occurs in each mol-ecule. The crystal structure features two symmetry-independent polymeric chains along [010] generated by N-H⋯O hydrogen bonds between the amide groups.

Methyl 2-(4-chloro-3,5-dinitro-benz-amido)-acetate.

The title mol-ecule, C(10)H(8)ClN(3)O(7), is twisted with the dihedral angle between the amide and benzene ring being 38.75 (11)°. The C-N-C-C torsion angle between the amide and acetyl groups is -150.1 (2)°. Finally, each nitro group is twisted out of the plane of the benzene ring to which it is connected [O-N-C-C torsion angles = 34.0 (3) and -64.5 (3)°]. Linear supra-molecular chains along [010] and mediated by N-H⋯O hydrogen bonds between successive amide groups dominate the crystal packing. The chains are consolidated into the three-dimensional structure by C-H⋯O contacts.