Chromosome-level genome assembly and characterization of the Calophaca sinica genome.

Calophaca sinica is a rare plant endemic to northern China which belongs to the Fabaceae family and possesses rich nutritional value. To support the preservation of the genetic resources of this plant, we have successfully generated a high-quality genome of C. sinica (1.06 Gb). Notably, transposable elements (TEs) constituted ~73% of the genome, with long terminal repeat retrotransposons (LTR-RTs) dominating this group of elements (~54% of the genome). The average intron length of the C. sinica genome was noticeably longer than what has been observed for closely related species. The expansion of LTR-RTs and elongated introns emerged had the largest influence on the enlarged genome size of C. sinica in comparison to other Fabaceae species. The proliferation of TEs could be explained by certain modes of gene duplication, namely, whole genome duplication (WGD) and dispersed duplication (DSD). Gene family expansion, which was found to enhance genes associated with metabolism, genetic maintenance, and environmental stress resistance, was a result of transposed duplicated genes (TRD) and WGD. The presented genomic analysis sheds light on the genetic architecture of C. sinica, as well as provides a starting point for future evolutionary biology, ecology, and functional genomics studies centred around C. sinica and closely related species.

Decoding Multi-Brain Motor Imagery From EEG Using Coupling Feature Extraction and Few-Shot Learning.

Electroencephalography (EEG)-based motor imagery (MI) is one of brain computer interface (BCI) paradigms, which aims to build a direct communication pathway between human brain and external devices by decoding the brain activities. In a traditional way, MI BCI replies on a single brain, which suffers from the limitations, such as low accuracy and weak stability. To alleviate these limitations, multi-brain BCI has emerged based on the integration of multiple individuals' intelligence. Nevertheless, the existing decoding methods mainly use linear averaging or feature integration learning from multi-brain EEG data, and do not effectively utilize coupling relationship features, resulting in undesired decoding accuracy. To overcome these challenges, we proposed an EEG-based multi-brain MI decoding method, which utilizes coupling feature extraction and few-shot learning to capture coupling relationship features among multi-brains with only limited EEG data. We performed an experiment to collect EEG data from multiple persons who engaged in the same task simultaneously and compared the methods on the collected data. The comparison results showed that our proposed method improved the performance by 14.23% compared to the single-brain mode in the 10-shot three-class decoding task. It demonstrated the effectiveness of the proposed method and usability of the method in the context of only small amount of EEG data available.

Classification of the Epileptic Seizure Onset Zone Based on Partial Annotation.

Epilepsy is a chronic disorder caused by excessive electrical discharges. Currently, clinical experts identify the seizure onset zone (SOZ) channel through visual judgment based on long-time intracranial electroencephalogram (iEEG), which is a very time-consuming, difficult and experience-based task. Therefore, there is a need for high-accuracy diagnostic aids to reduce the workload of clinical experts. In this article, we propose a method in which, the iEEG is split into the 20-s segment and for each patient, we ask clinical experts to label a part of the data, which is used to train a model and classify the remaining iEEG data. In recent years, machine learning methods have been successfully applied to solve some medical problems. Filtering, entropy and short-time Fourier transform (STFT) are used for extracting features. We compare them to wavelet transform (WT), empirical mode decomposition (EMD) and other traditional methods with the aim of obtaining the best possible discriminating features. Finally, we look for their medical interpretation, which is important for clinical experts. We achieve high-performance results for SOZ and non-SOZ data classification by using the labeled iEEG data and support vector machine (SVM), fully connected neural network (FCNN) and convolutional neural network (CNN) as classification models. In addition, we introduce the positive unlabeled (PU) learning to further reduce the workload of clinical experts. By using PU learning, we can learn a binary classifier with a small amount of labeled data and a large amount of unlabeled data. This can greatly reduce the amount and difficulty of annotation work by clinical experts. All together, we show that using 105 minutes of labeled data we achieve a classification result of 91.46% on average for multiple patients.

EEG-based real-time diagnostic system with developed dynamic 2TEMD and dynamic ApEn algorithms.

In real-time electroencephalography (EEG) analysis, the problem of observing dynamic changes and the problem of binary classification is a promising direction. EEG energy and complexity are important evaluation metrics in brain death determination in the field of EEG analysis. We developed two algorithms, dynamic turning tangent empirical mode decomposition to compute EEG energy and dynamic approximate entropy to compute EEG complexity for brain death determination. The developed algorithm is applied to analyze 50 EEG data of coma patients and 50 EEG data of brain death patients. The validity of the dynamic analysis is confirmed by the accuracy rate derived from the comparison with turning tangent empirical mode decomposition and approximate entropy algorithms. We evaluated the EEG data of three patients using the built diagnostic system. The experimental results visually showed that the EEG energy ratio was higher in a coma state than that in brain death, while the complexity was lower than that in brain death.

Brain-Machine Coupled Learning Method for Facial Emotion Recognition.

Neural network models of machine learning have shown promising prospects for visual tasks, such as facial emotion recognition (FER). However, the generalization of the model trained from a dataset with a few samples is limited. Unlike the machine, the human brain can effectively realize the required information from a few samples to complete the visual tasks. To learn the generalization ability of the brain, in this article, we propose a novel brain-machine coupled learning method for facial emotion recognition to let the neural network learn the visual knowledge of the machine and cognitive knowledge of the brain simultaneously. The proposed method utilizes visual images and electroencephalogram (EEG) signals to couple training the models in the visual and cognitive domains. Each domain model consists of two types of interactive channels, common and private. Since the EEG signals can reflect brain activity, the cognitive process of the brain is decoded by a model following reverse engineering. Decoding the EEG signals induced by the facial emotion images, the common channel in the visual domain can approach the cognitive process in the cognitive domain. Moreover, the knowledge specific to each domain is found in each private channel using an adversarial strategy. After learning, without the participation of the EEG signals, only the concatenation of both channels in the visual domain is used to classify facial emotion images based on the visual knowledge of the machine and the cognitive knowledge learned from the brain. Experiments demonstrate that the proposed method can produce excellent performance on several public datasets. Further experiments show that the proposed method trained from the EEG signals has good generalization ability on new datasets and can be applied to other network models, illustrating the potential for practical applications.

A novel classification method for EEG-based motor imagery with narrow band spatial filters and deep convolutional neural network.

The Common Spatial Pattern (CSP) algorithm is the most widely used method for decoding Electroencephalography (EEG) signals from motor imagery (MI) paradigm. However, due to the inter-subject variability, the CSP algorithm heavily relies on the selection of filter bands and extensive analytical processing time required to build an effective model, which has been a challenge in current research. In this paper, we propose a narrow filter bank CSP (NFBCSP) algorithm, which automatically determines the optimal narrow band for two-class motor imagery by band search tree, and a high-performance classification model dedicated to each subject can be obtained in a short time for online processing or further offline analysis. The optimal narrow band is combined with the CSP algorithm to extract the dynamic features in the EEG signals. For the multi-class motor imagery task, it is first transformed into multiple One-Versus-Rest (OVR) tasks and determines the corresponding optimal narrow bands. After extracting the features of each optimal narrow band separately, the Deep Convolutional Neural Network (DCNN) is used for the fusion of band features and classification of multi-class motor imagery. Finally, we verified our method using two different motor imagery datasets, the BCI-VR dataset with two classes of motor imagery and the BCI Competition IV dataset 2a with four classes of motor imagery. The experimental results show that the proposed method achieves an average classification accuracy of 86.43% for the two-class motor imagery task, and 76.87% for the four-class motor imagery task, which outperforms other recent methods. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-021-09721-x.

Genome Sequence of Elaeagnus mollis, the First Chromosome-Level Genome of the Family Elaeagnaceae.

Elaeagnus mollis Diels (Elaeagnaceae) is a species of shrubs and/or dwarf trees that produces highly nutritious nuts with abundant oil and pharmaceutical properties. It is endemic to China but endangered. Therefore, to facilitate the protection of its genetic resources and the development of its commercially attractive traits we generated a high-quality genome of E. mollis. The contig version of the genome (630.96 Mb long) was assembled into 14 chromosomes using Hi-C data, with contig and scaffold N50 values of 18.40 and 38.86 Mb, respectively. Further analyses identified 397.49 Mb (63.0%) of repetitive sequences and 27,130 protein-coding genes, of which 26,725 (98.5%) were functionally annotated. Benchmarking Universal Single-Copy Ortholog assessment indicated that 98.0% of highly conserved plant genes are completely present in the genome. This is the first reference genome for any species of Elaeagnaceae and should greatly facilitate future efforts to conserve, utilize, and elucidate the evolution of this endangered endemic species.

[Aerosol salt damage is the main problem of landscaping in the coastal areas of southern China]. / 盐雾危害是南方滨海地区园林绿化的主要困难.

Both the growth and survival of landscape plants are difficult due to the harsh natural conditions in coastal areas of southern China. Many plants suffer from symptoms of salt damage. Different from the damages by salt in the soil, the symptoms of windblown salt are damage to young shoots and leaves. Plants at the windward side are damaged more than the leeward side. These cha-racteristics imply that the damage is due to salt in aerosols instead of salt in the soil. To test this hypothesis, we measured plant growth, soil and climate factors in 24 frontline coastal counties and cities of China. The results showed that the first-line coastal plants showed strong symptoms of salt damage, especially in the Taiwan Strait area (85.4% belonged to desalinized soil), and that the damage level was highly correlated with wind speed. Our results confirmed that aerosol salt is the major cause of plant damage in the coastal areas of southern China. We constructed the first distribution map of salt damage along frontline coastal regions of southern China and proposed methods for diagnosing aerosol salt damage. Selecting and configuring aerosol salt-tolerant plants, greening engineering measures, and follow-up maintenance were suggested for improving the overall effect and level of landscaping in the coastal areas of southern China.

Two brains, one target: Design of a multi-level information fusion model based on dual-subject RSVP.

BACKGROUND: Rapid serial visual presentation (RSVP) based brain-computer interface (BCI) is widely used to categorize the target and non-target images. The available information limits the prediction accuracy of single-trial using single-subject electroencephalography (EEG) signals. New Method. Hyperscanning is a new manner to record two or more subjects' signals simultaneously. So we designed a multi-level information fusion model for target image detection based on dual-subject RSVP, namely HyperscanNet. The two modules of this model fuse the data and features of the two subjects at the data and feature layers. A chunked long and short-term memory artificial neural network (LSTM) was used in the time dimension to extract features at different periods separately, completing fine-grained underlying feature extraction. While the feature layer is fused, some plain operations are used to complete the fusion of the data layer to ensure that important information is not missed. RESULTS: Experimental results show that the F1-score (the harmonic mean of precision and recall) of this method with best group of channels and segment length is 82.76%. Comparison with existing methods. This method improves the F1-score by at least 5% compared to single-subject target detection. CONCLUSIONS: Target detection can be accomplished by the two subjects' collaboration to achieve a higher and more stable F1-score than a single subject.

Hybrid Convolutional Neural Network for Localization of Epileptic Focus Based on iEEG.

Epileptic focus localization by analysing intracranial electroencephalogram (iEEG) plays a critical role in successful surgical therapy of resection of the epileptogenic lesion. However, manual analysis and classification of the iEEG signal by clinicians are arduous and time-consuming and excessively depend on the experience. Due to individual differences of patients, the iEEG signal from different patients usually shows very diverse features even if the features belong to the same class. Accordingly, automatic detection of epileptic focus is required to improve the accuracy and to shorten the time for treatment. In this paper, we propose a novel feature fusion-based iEEG classification method, a deep learning model termed Time-Frequency Hybrid Network (TF-HybridNet), in which short-time Fourier transform (STFT) and 1d convolution layers are performed on the input iEEG in parallel to extract features of the time-frequency domain and feature maps. And then, the time-frequency features and feature maps are fused and fed to a 2d convolutional neural network (CNN). We used the Bern-Barcelona iEEG dataset for evaluating the performance of TF-HybridNet, and the experimental results show that our approach is able to differentiate the focal from nonfocal iEEG signal with an average classification accuracy of 94.3% and demonstrates an improved accuracy rate compared to the model using only STFT or one-dimensional convolutional layers as feature extraction.

CTNN: A Convolutional Tensor-Train Neural Network for Multi-Task Brainprint Recognition.

Brainprint is a new type of biometric in the form of EEG, directly linking to intrinsic identity. Currently, most methods for brainprint recognition are based on traditional machine learning and only focus on a single brain cognition task. Due to the ability to extract high-level features and latent dependencies, deep learning can effectively overcome the limitation of specific tasks, but numerous samples are required for model training. Therefore, brainprint recognition in realistic scenes with multiple individuals and small amounts of samples in each class is challenging for deep learning. This article proposes a Convolutional Tensor-Train Neural Network (CTNN) for the multi-task brainprint recognition with small number of training samples. Firstly, local temporal and spatial features of the brainprint are extracted by the convolutional neural network (CNN) with depthwise separable convolution mechanism. Afterwards, we implement the TensorNet (TN) via low-rank representation to capture the multilinear intercorrelations, which integrates the local information into a global one with very limited parameters. The experimental results indicate that CTNN has high recognition accuracy over 99% on all four datasets, and it exploits brainprint under multi-task efficiently and scales well on training samples. Additionally, our method can also provide an interpretable biomarker, which shows specific seven channels are dominated for the recognition tasks.

A Hybrid System for Distinguishing between Brain Death and Coma Using Diverse EEG Features.

Electroencephalography (EEG) signals may provide abundant information reflecting the developmental changes in brain status. It usually takes a long time to finally judge whether a brain is dead, so an effective pre-test of brain states method is needed. In this paper, we present a hybrid processing pipeline to differentiate brain death and coma patients based on canonical correlation analysis (CCA) of power spectral density, complexity features, and feature fusion for group analysis. In addition, time-varying power spectrum and complexity were observed based on the analysis of individual patients, which can be used to monitor the change of brain status over time. Results showed three major differences between brain death and coma groups of EEG signal: slowing, increased complexity, and the improvement on classification accuracy with feature fusion. To the best of our knowledge, this is the first scheme for joint general analysis and time-varying state monitoring. Delta-band relative power spectrum density and permutation entropy could effectively be regarded as potential features of discrimination analysis on brain death and coma patients.

Single-trial discrimination of EEG signals for stroke patients: a general multi-way analysis.

It has been demonstrated that Brain-Computer Interface (BCI), combined with Functional Electrical Stimulation (FES), is an effective and efficient way for post-stroke patients to restore motor function. However, traditional feature extraction methods, such as Common Spatial Pattern (CSP), do not work well for post-stroke patients' EEG data due to its irregular patterns. In this study, we introduce a novel tensorbased feature extraction algorithm, which takes both spatial-spectral-temporal features of EEG data into consideration. EEG data recorded from post-stroke patients is used for simulation experiments to assess the effectiveness of the proposed algorithm. The results show that the the proposed algorithm outperforms some traditional algorithms.

Gaussian mixture modeling in stroke patients' rehabilitation EEG data analysis.

Traditional 2-class Motor Imagery (MI) Electroencephalography (EEG) classification approaches like Common Spatial Pattern (CSP) and Support Vector Machine (SVM) usually underperform when processing stroke patients' rehabilitation EEG which are flooded with unknown irregular patterns. In this paper, the classical CSP-SVM schema is improved and a feature learning method based on Gaussian Mixture Model (GMM) is utilized for depicting patients' imagery EEG distribution features. We apply the proposed modeling program in two different modules of our online BCI-FES rehabilitation platform and achieve a relatively higher discrimination accuracy. Sufficient observations and test cases on patients' MI data sets have been implemented for validating the GMM model. The results also reveal some working mechanisms and recovery appearances of impaired cortex during the rehabilitation training period.

An EEG diagnosis system for quasi brain death based on complexity and energy analyses.

Electroencephalogram (EEG) is often used in confirmatory test for brain death determination in clinical practice. Because the EEG measuring and monitoring is relatively safe and reliable for deep comatose patients, it is believed to be valuable for reducing the risk of diagnosis or prevent mistaken diagnosis of brain death. In this paper, we present EEG complexity analysis and EEG energy analyses for the EEG acquisition of 35 adult patients. In EEG complexity analysis, we firstly report statistically significant differences of quantitative statistics in this clinical study. Next, for the patient-wise case study, we develop a dynamical calculating entropy method to monitor the symptom change of patients. In EEG energy analysis, we firstly accumulate the EEG energy from the extracted components that are related to the brain activities. Then, we evaluate the energy differences between deep comatose patients and brain death. The empirical results reported in this paper suggest some promising directions and valuable clues for clinical practice.

Analyzing EEG of quasi-brain-death based on dynamic sample entropy measures.

To give a more definite criterion using electroencephalograph (EEG) approach on brain death determination is vital for both reducing the risks and preventing medical misdiagnosis. This paper presents several novel adaptive computable entropy methods based on approximate entropy (ApEn) and sample entropy (SampEn) to monitor the varying symptoms of patients and to determine the brain death. The proposed method is a dynamic extension of the standard ApEn and SampEn by introducing a shifted time window. The main advantages of the developed dynamic approximate entropy (DApEn) and dynamic sample entropy (DSampEn) are for real-time computation and practical use. Results from the analysis of 35 patients (63 recordings) show that the proposed methods can illustrate effectiveness and well performance in evaluating the brain consciousness states.

Synchronization study in ring-like and grid-like neuronal networks.

In this paper, we study the synchronization status of both two gap-junction coupled neurons and neuronal network with two different network connectivity patterns. One of the network connectivity patterns is a ring-like neuronal network, which only considers nearest-neighbor neurons. The other is a grid-like neuronal network, with all nearest neighbor couplings. We show that by varying some key parameters, such as the coupling strength and the external current injection, the neuronal network will exhibit various patterns of firing synchronization. Different types of firing synchronization are diagnosed by means of a mean field potential, a bifurcation diagram, a correlation coefficient and the ISI-distance method. Numerical simulations demonstrate that the synchronization status of multiple neurons is much dependent on the network patters, when the number of neurons is the same. It is also demonstrated that the synchronization status of two coupled neurons is similar with the grid-like neuronal network, but differs radically from that of the ring-like neuronal network. These results may be instructive in understanding synchronization transitions in neuronal systems.

Phase-based brain consciousness analysis.

This work provides a novel framework for identifying coma and brain death consciousness states by analysing frequency power and phase synchrony features from electroencephalogram (EEG). The proposed analysis of pairs of EEG electrodes using complex extensions of Empirical Mode Decomposition (EMD) permits the extraction of information related to the state of the brain function. Analysis on 34 subjects in the coma and quasi-brain-death states suggests that phase synchrony constitutes a feasible feature to discriminate quasi-brain-death from coma state. Thus, illustrate the effectiveness of the proposed methods for brain consciousness identification. The predictive power of the features extracted is evaluated by building classification models using support vector machine (SVM) and evaluation the models through receiver operating characteristic (ROC) analysis.

Phase synchronization motion and neural coding in dynamic transmission of neural information.

In order to explore the dynamic characteristics of neural coding in the transmission of neural information in the brain, a model of neural network consisting of three neuronal populations is proposed in this paper using the theory of stochastic phase dynamics. Based on the model established, the neural phase synchronization motion and neural coding under spontaneous activity and stimulation are examined, for the case of varying network structure. Our analysis shows that, under the condition of spontaneous activity, the characteristics of phase neural coding are unrelated to the number of neurons participated in neural firing within the neuronal populations. The result of numerical simulation supports the existence of sparse coding within the brain, and verifies the crucial importance of the magnitudes of the coupling coefficients in neural information processing as well as the completely different information processing capability of neural information transmission in both serial and parallel couplings. The result also testifies that under external stimulation, the bigger the number of neurons in a neuronal population, the more the stimulation influences the phase synchronization motion and neural coding evolution in other neuronal populations. We verify numerically the experimental result in neurobiology that the reduction of the coupling coefficient between neuronal populations implies the enhancement of lateral inhibition function in neural networks, with the enhancement equivalent to depressing neuronal excitability threshold. Thus, the neuronal populations tend to have a stronger reaction under the same stimulation, and more neurons get excited, leading to more neurons participating in neural coding and phase synchronization motion.

Selecting EEG components using time series analysis in brain death diagnosis.

In diagnosis of brain death for human organ transplant, EEG (electroencephalogram) must be flat to conclude the patient's brain death but it has been reported that the flat EEG test is sometimes difficult due to artifacts such as the contamination from the power supply and ECG (electrocardiogram, the signal from the heartbeat). ICA (independent component analysis) is an effective signal processing method that can separate such artifacts from the EEG signals. Applying ICA to EEG channels, we obtain several separated components among which some correspond to the brain activities while others contain artifacts. This paper aims at automatic selection of the separated components based on time series analysis. In the flat EEG test in brain death diagnosis, such automatic component selection is helpful.