The Long and the Short of BRD4: Two Tales in Breast Cancer.

In this issue of Molecular Cell, Wu et al. (2020) describe studies that establish oncogenic versus tumor-suppressive functions of two BRD4 isoforms in the regulation of gene expression and breast cancer development.

A novel and ubiquitous miRNA-involved regulatory module ensures precise phosphorylation of RNA polymerase II and proper transcription.

Proper transcription orchestrated by RNA polymerase II (RNPII) is crucial for cellular development, which is rely on the phosphorylation state of RNPII's carboxyl-terminal domain (CTD). Sporangia, developed from mycelia, are essential for the destructive oomycetes Phytophthora, remarkable transcriptional changes are observed during the morphological transition. However, how these changes are rapidly triggered and their relationship with the versatile RNPII-CTD phosphorylation remain enigmatic. Herein, we found that Phytophthora capsici undergone an elevation of Ser5-phosphorylation in its uncanonical heptapeptide repeats of RNPII-CTD during sporangia development, which subsequently changed the chromosomal occupation of RNPII and primarily activated transcription of certain genes. A cyclin-dependent kinase, PcCDK7, was highly induced and phosphorylated RNPII-CTD during this morphological transition. Mechanistically, a novel DCL1-dependent microRNA, pcamiR1, was found to be a feedback modulator for the precise phosphorylation of RNPII-CTD by complexing with PcAGO1 and regulating the accumulation of PcCDK7. Moreover, this study revealed that the pcamiR1-CDK7-RNPII regulatory module is evolutionarily conserved and the impairment of the balance between pcamiR1 and PcCDK7 could efficiently reduce growth and virulence of P. capsici. Collectively, this study uncovers a novel and evolutionary conserved mechanism of transcription regulation which could facilitate correct development and identifies pcamiR1 as a promising target for disease control.

Filter bank second-order underdamped stochastic resonance analysis for implementing a short-term high-speed SSVEP detection.

OBJECTIVE: The progression of brain-computer interfaces (BCIs) has been propelled by breakthroughs in neuroscience, signal processing, and machine learning, marking it as a dynamic field of study over the past few decades. Nevertheless, the nonlinear and non-stationary characteristics of steady-state visual evoked potentials (SSVEPs), coupled with the incongruity between frequently employed linear techniques and nonlinear signal attributes, resulted in the subpar performance of mainstream non-training algorithms like canonical correlation analysis (CCA), multivariate synchronization index (MSI), and filter bank CCA (FBCCA) in short-term SSVEP detection. METHODS: To tackle this problem, the novel fusions of common filter bank analysis, CCA dimensionality reduction methods, USSR models, and MSI recognition models are used in SSVEP signal recognition. RESULTS: Unlike conventional linear techniques such as CCA, MSI, and FBCCA, the filter bank second-order underdamped stochastic resonance (FBUSSR) analysis demonstrates superior efficacy in the detection of short-term high-speed SSVEPs. CONCLUSION: This research enlists 32 subjects and uses a public dataset to assess the proposed approach, and the experimental outcomes indicate that the non-training method can attain greater recognition precision and stability. Furthermore, under the conditions of the newly proposed fusion method and light stimulation, the USSR model exhibits the most optimal enhancement effect. SIGNIFICANCE: The findings of this study underscore the expansive potential for the application of BCI systems in the realm of neuroscience and signal processing.

Intelligent ankle-foot prosthesis based on human structure and motion bionics.

The ankle-foot prosthesis aims to compensate for the missing motor functions by fitting the motion characteristics of the human ankle, which contributes to enabling the lower-limb amputees to take care of themselves and improve mobility in daily life. To address the problems of poor bionic motion of the ankle-foot prosthesis and the lack of natural interaction among the patient, prosthesis, and the environment, we developed a complex reverse-rolling conjugate joint based on the human ankle-foot structure and motion characteristics, the rolling joint was used to simulate the rolling-sliding characteristics of the knee joint. Meanwhile, we established a segmental dynamics model of the prosthesis in the stance phase, and the prosthetic structure parameters were obtained with the optimal prosthetic structure dimensions and driving force. In addition, a carbon fiber energy-storage foot was designed based on the human foot profile, and the dynamic response of its elastic strain energy at different thicknesses was simulated and analyzed. Finally, we integrated a bionic ankle-foot prosthesis and experiments were conducted to verify the bionic nature of the prosthetic joint motion and the energy-storage characteristics of the carbon fiber prosthetic foot. The proposed ankle-foot prosthesis provides ambulation support to assist amputees in returning to social life normally and has the potential to help improve clinical viability to reduce medical rehabilitation costs.

Distributed Vibration Monitoring System for 10 kV-400 kVA 3D Wound Core Transformer under Progressive Short-Circuit Impulses.

As large-scale, high-proportion, and efficient distribution transformers surge into the grids, anti-short circuit capability testing of transformer windings in efficient distribution seems necessary and prominent. To deeply explore the influence of progressively short-circuit shock impulses on the core winding deformation of efficient power transformers, a finite element theoretical model was built by referring to a three-phase three-winding 3D wound core transformer with a model of S20-MRL-400/10-NX2. The distributions of internal equivalent force and total deformation of the 3D wound core transformer along different paths under progressively short-circuit shock impulses varying from 60% to 120% were investigated. Results show that the equivalent stress and total deformation change rate reach their maximum as the short-circuit current increases from 60% to 80%, and the maximum and average variation rate for the equivalent stress reach 177.75% and 177.43%, while the maximum and average variation rate for the total deformation corresponds to 178.30% and 177.45%, respectively. Meanwhile, the maximum equivalent stress and maximum total deformation reach 29.81 MPa and 38.70 µm, respectively, as the applied short-circuit current increased to 120%. In light of the above observations, the optimization and deployment of wireless sensor nodes was suggested. Therefore, a distributed monitoring system was developed for acquiring the vibration status of the windings in a 3D wound core transformer, which is a beneficial supplement to the traditional short-circuit reactance detection methods for an efficient grid access spot-check of distribution transformers.

The CAP superfamily protein PsCAP1 secreted by Phytophthora triggers immune responses in Nicotiana benthamiana through a leucine-rich repeat receptor-like protein.

The role of cysteine-rich secretory proteins, antigen 5, and pathogenesis-related 1 (CAP) superfamily proteins in the innate immune responses of mammals is well characterized. However, the biological function of CAP superfamily proteins in plant-microbe interactions is poorly understood. We used proteomics and transcriptome analyses to dissect the apoplastic effectors secreted by the oomycete Phytophthora sojae during early infection of soybean leaves. By transiently expressing these effectors in Nicotiana benthamiana, we identified PsCAP1, a novel type of secreted CAP protein that triggers immune responses in multiple solanaceous plants including N. benthamiana. This secreted CAP protein is conserved among oomycetes, and multiple PsCAP1 homologs can be recognized by N. benthamiana. PsCAP1-triggered immune responses depend on the N-terminal immunogenic fragment (aa 27-151). Pretreatment of N. benthamiana with PsCAP1 or the immunogenic fragment increases plant resistance against Phytophthora. The recognition of PsCAP1 and different homologs requires the leucine-rich repeat receptor-like protein RCAP1, which associates with two central receptor-like kinases BRI1-associated receptor kinase 1 (BAK1) and suppressor of BIR1-1 (SOBIR1) in planta. These findings suggest that the CAP-type apoplastic effectors act as an important player in plant-microbe interactions that can be perceived by plant membrane-localized receptor to activate plant resistance.

CRISPR/Cas9-mediated editing of GmTAP1 confers enhanced resistance to Phytophthora sojae in soybean.

Soybean root rot disease caused by Phytophthora sojae seriously constrains soybean yield. Knocking out the susceptibility gene GmTAP1 in soybean created new soybean lines resistant to several P. sojae strains and these lines showed no agronomic penalties in the field.

Tracking the evolution of untreated high-intermediate/high-risk diffuse large B-cell lymphoma by circulating tumour DNA.

Diffuse large B-cell lymphoma (DLBCL) is a highly heterogenous malignancy, early identification of patients for relapse remains challenging. The potential to non-invasively monitor tumour evolutionary dynamics of DLBCL needs to be further established. In the present study, 17 tumour biopsy and 38 plasma samples from 38 patients with high-intermediate/high-risk DLBCL were evaluated at baseline. Longitudinal blood samples were also collected during therapy. Circulating tumour DNA (ctDNA) was analysed using targeted sequencing based on a gene panel via a recently developed methodology, circulating single-molecule amplification and re-sequencing technology (cSMART). We found that the most frequently mutated genes were tumour protein p53 (TP53; 42·1%), histone-lysine N-methyltransferase 2D (KMT2D; 28·9%), caspase recruitment domain family member 11 (CARD11; 21·1%), cAMP response element-binding protein binding protein (CREBBP; 15·8%), ß2 -microglobulin (B2M; 15·8%), and tumour necrosis factor alpha-induced protein 3 (TNFAIP3; 15·8%). The mutation profiles between ctDNA and matched tumour tissue showed good concordance; however, more mutation sites were detected in ctDNA samples. Either TP53 or B2M mutations before treatment predicted poor prognosis. Analysis of dynamic blood samples confirmed the utility of ctDNA for the real-time assessment of treatment response and revealed that the increases in ctDNA levels and changes in KMT2D mutation status could be useful predictors of disease progression. Our present results suggest that ctDNA is a promising method for the detection of mutation spectrum and serves as a biomarker for disease monitoring and predicting clinical recurrence.

Sodium dichloroacetate stimulates cardiac mitochondrial metabolism and improves cardiac conduction in the ovine fetus during labor.

Previous studies in our laboratory have suggested that the increase in stillbirth in pregnancies complicated by chronic maternal stress or hypercortisolemia is associated with cardiac dysfunction in late stages of labor and delivery. Transcriptomics analysis of the overly represented differentially expressed genes in the fetal heart of hypercortisolemic ewes indicated involvement of mitochondrial function. Sodium dichloroacetate (DCA) has been used to improve mitochondrial function in several disease states. We hypothesized that administration of DCA to laboring ewes would improve both cardiac mitochondrial activity and cardiac function in their fetuses. Four groups of ewes and their fetuses were studied: control, cortisol-infused (1 g/kg/day from 115 to term; CORT), DCA-treated (over 24 h), and DCA + CORT-treated; oxytocin was delivered starting 48 h before the DCA treatment. DCA significantly decreased cardiac lactate, alanine, and glucose/glucose-6-phosphate and increased acetylcarnitine/isobutyryl-carnitine. DCA increased mitochondrial activity, increasing oxidative phosphorylation (PCI, PCI + II) per tissue weight or per unit of citrate synthase. DCA also decreased the duration of the QRS, attenuating the prolongation of the QRS observed in CORT fetuses. The effect to reduce QRS duration with DCA treatment correlated with increased glycerophosphocholine and serine and decreased phosphorylcholine after DCA treatment. There were negative correlations of acetylcarnitine/isobutyryl-carnitine to both heart rate (HR) and mean arterial pressure (MAP). These results suggest that improvements in mitochondrial respiration with DCA produced changes in the cardiac lipid metabolism that favor improved conduction in the heart. DCA may therefore be an effective treatment of fetal cardiac metabolic disturbances in labor that can contribute to impairments of fetal cardiac conduction.

Interaction of High-Sugar Diet and History of Stroke with Risk of Cognitive Decline in Older Adults.

BACKGROUND Cognitive decline has become a public health concern as it causes adverse economic and socio-psychological outcomes. Studies have assessed the effects of history of stroke or high-sugar diet on cognitive decline of older adults, but whether there was interaction between high-sugar diet and history of stroke in affecting cognitive decline was still unclear. The present study explored the interaction between high-sugar diet and history of stroke in affecting the risk of cognitive decline in older adults. MATERIAL AND METHODS This cross-sectional study included 2710 subjects. Univariate analysis was applied to explore the associations of high-sugar diet or history of stroke in affecting cognitive decline. The relative excess risk of interaction (RERI), synergy index (SI), and attributable proportion of interaction (API) were used to assess the interaction of high-sugar diet and history of stroke in risk of cognitive decline. RESULTS An increased risk of cognitive decline was observed in people with history of stroke [odds ratio (OR)=1.826, 95% confidence interval (CI): 1.124-2.968] and high-sugar diet (OR=1.509, 95% CI: 1.109-2.052). The confidence intervals of interaction indicators RERI=1.257 (95% CI: 0.188-2.326) and API=0.386 (95% CI: 0.135-0.638) did not contain 0 and were both >0; the confidence interval of SI=2.261 (95% CI: 1.063-4.809) did not contain 1 and were >1. CONCLUSIONS A high-sugar diet and history of stroke interacted synergically in association with cognitive decline in older adults, which might provide a reference for management of cognition in older adults.

Poincaré Plot Nonextensive Distribution Entropy: A New Method for Electroencephalography (EEG) Time Series.

As a novel form of visual analysis technique, the Poincaré plot has been used to identify correlation patterns in time series that cannot be detected using traditional analysis methods. In this work, based on the nonextensive of EEG, Poincaré plot nonextensive distribution entropy (NDE) is proposed to solve the problem of insufficient discrimination ability of Poincaré plot distribution entropy (DE) in analyzing fractional Brownian motion time series with different Hurst indices. More specifically, firstly, the reasons for the failure of Poincaré plot DE in the analysis of fractional Brownian motion are analyzed; secondly, in view of the nonextensive of EEG, a nonextensive parameter, the distance between sector ring subintervals from the original point, is introduced to highlight the different roles of each sector ring subinterval in the system. To demonstrate the usefulness of this method, the simulated time series of the fractional Brownian motion with different Hurst indices were analyzed using Poincaré plot NDE, and the process of determining the relevant parameters was further explained. Furthermore, the published sleep EEG dataset was analyzed, and the results showed that the Poincaré plot NDE can effectively reflect different sleep stages. The obtained results for the two classes of time series demonstrate that the Poincaré plot NDE provides a prospective tool for single-channel EEG time series analysis.

Effects of Paradigm Color and Screen Brightness on Visual Fatigue in Light Environment of Night Based on Eye Tracker and EEG Acquisition Equipment.

Nowadays, more people tend to go to bed late and spend their sleep time with various electronic devices. At the same time, the BCI (brain−computer interface) rehabilitation equipment uses a visual display, thus it is necessary to evaluate the problem of visual fatigue to avoid the impact on the training effect. Therefore, it is very important to understand the impact of using electronic devices in a dark environment at night on human visual fatigue. This paper uses Matlab to write different color paradigm stimulations, uses a 4K display with an adjustable screen brightness to jointly design the experiment, uses eye tracker and g.tec Electroencephalogram (EEG) equipment to collect the signal, and then carries out data processing and analysis, finally obtaining the influence of the combination of different colors and different screen brightness on human visual fatigue in a dark environment. In this study, subjects were asked to evaluate their subjective (Likert scale) perception, and objective signals (pupil diameter, θ + α frequency band data) were collected in a dark environment (<3 lx). The Likert scale showed that a low screen brightness in the dark environment could reduce the visual fatigue of the subjects, and participants preferred blue to red. The pupil data revealed that visual perception sensitivity was more vulnerable to stimulation at a medium and high screen brightness, which is easier to deepen visual fatigue. EEG frequency band data concluded that there was no significant difference between paradigm colors and screen brightness on visual fatigue. On this basis, this paper puts forward a new index­the visual anti-fatigue index, which provides a valuable reference for the optimization of the indoor living environment, the improvement of satisfaction with the use of electronic equipment and BCI rehabilitation equipment, and the protection of human eyes.

Nitrate and nitrite pathways and dynamic changes in bacterial communities during beet sugar processing.

BACKGROUND: Bacterial community successions were surveyed during the processing stages of sugar production using high-throughput sequencing methods. Furthermore, the correlation between bacterial community and nitrate/nitrite content in beet sugar processing were investigated. RESULTS: In an analysis of the V3-V4 region of the 16S rDNA gene, 254 122 effective sequences were obtained from samples, which included sugar beet, cossettes, diffusion juice, second-phase diffusion juice, light juice and thick juice. The results showed that dominant genera included Pantoea, Pseudomonas, Leuconostoc and Burkholderia. Moreover, significant changes in bacterial communities were observed in samples. Regarding the relevant nitrogen metabolic potential, this study revealed communities with the ability for nitrate and nitrite metabolism. Furthermore, a shaking experiment involving diffusion juice and second-phase diffusion juice was performed, and results showed that the nitrate level declined 73% and 98% in 36 h, respectively. These results suggested that the bacterial communities contribute to nitrate and nitrite transformation. CONCLUSION: This study illustrated that the bacterial communities and their specific effects on the formation of nitrate and nitrite during beet sugar processing. The results presented the basic concept involving the nitrate- and nitrite-forming pathways directly related to the mechanism of bacterial community growth. This study could facilitate an understanding of the correlation between nitrite content and microorganisms to guide beet sugar manufacturers regarding the control of nitrite and nitrate content. © 2021 Society of Chemical Industry.

A Three-Phase Current Tacholess Envelope Order Analysis Method for Feature Extraction of Planetary Gearbox under Variable Speed Conditions.

Planetary gearboxes are the key components of large equipment, such as wind turbines, shield machines, etc. The operating state of the planetary gearbox is related to the safety of the equipment as a whole, and its feature extraction technology is essential. In assessing the problem of the non-stationarity of the current signal under variable speed conditions and the difficulty of evaluating the operating state of the planetary gearbox under a tacholess condition, a three-phase current, variable-speed tacholess envelope order analysis method is proposed. Firstly, a tacholess rotation speed estimation is completed by extracting the trend term of the instantaneous frequency of the asynchronous motor's three-phase currents. The motor slip rate is assumed to be constant. Then, the envelope order analysis signal is obtained by re-sampling in the angular domain. Finally, the features of the envelope order signal are extracted, and a linear discriminant analysis (LDA) algorithm is used to fuse multiple indexes to generate a comprehensive feature reflecting the operating status of the planetary gearbox. The results of the simulation analysis and experimental verification show that the proposed method is effective in evaluating the operating state of the planetary gearbox under variable speed conditions. Compared with the traditional time-frequency ridge extraction method, the tacholess speed estimation method can improve the instantaneous speed estimation accuracy. The comprehensive index of envelope order completes the planetary gearbox state identification process, and a 95% classification accuracy rate is achieved.

Quantitative and objective diagnosis of color vision deficiencies based on steady-state visual evoked potentials.

PURPOSE: Traditional color vision tests depend on subjective judgments and are not suitable for infant children and subjects with cognitive dysfunction. We aimed to explore an objective and quantitative color vision testing method based on sweep steady-state visual evoked potentials (sweep SSVEPs) and compare the results with subjective Farnsworth-Munsell (FM) 100-hue test results. METHODS: A red-green SSVEP pattern reversal checkboard paradigm at different luminance ratios was used to induce visual evoked potentials (VEPs) from 15 color vision deficiencies (CVDs) and 11 normal color vision subjects. After electroencephalography signals were processed by canonical correlation analysis, an equiluminance turning curve corresponding to the activation of the L-cones and M-cones at different levels of color vision was established. Then, we obtained different equiluminance T and proposed the SSVEP color vision severity index (ICVD) to quantify color vision function and the severity of CVDs. In addition, the FM 100-hue test was used to obtain subjective data for the diagnosis of color vision. RESULTS: The value of ICVD can be an indicator of the level of color vision. Both the total error scores (TES) and confusion index (C-index) of the FM 100-hue test were significantly correlated with ICVD values (P < 0.001, respectively). ICVD also had a good classification effect in detecting normals, anomalous trichromats and dichromats. Moreover, equiluminance T had a good effect on classifying protans and deutans in subjects with CVDs. CONCLUSION: Color vision evaluation with sweep SSVEPs showed a good correlation with subjective psychophysical methods. SSVEPs can be an objective and quantitative method to test color vision and diagnose CVDs.

Maternal hypercortisolemia alters placental metabolism: a multiomics view.

Previous studies have suggested that increases in maternal cortisol or maternal stress in late pregnancy increase the risk of stillbirth at term. In an ovine model with increased maternal cortisol over the last 0.20 of gestation, we have previously found evidence of disruption of fetal serum and cardiac metabolomics and altered expression of genes related to mitochondrial function and metabolism in biceps femoris, diaphragm, and cardiac muscle. The present studies were designed to test for effects of chronically increased maternal cortisol on gene expression and metabolomics in placentomes near term. We hypothesized that changes in placenta might underlie or contribute to the alterations in fetal serum metabolomics and thereby contribute to changes in striated muscle metabolism. Placentomes were collected from pregnancies in early labor (143 ± 1 days gestation) of control ewes (n = 7) or ewes treated with cortisol (1 mg·kg-1·day-1 iv; n = 5) starting at day 115 of gestation. Transcriptomics and metabolomics were performed using an ovine gene expression microarray (Agilent 019921) and HR-MAS NMR, respectively. Multiomic analysis indicates that amino acid metabolism, particularly of branched-chain amino acids and glutamate, occur in placenta; changes in amino acid metabolism, degradation, or biosynthesis in placenta were consistent with changes in valine, isoleucine, leucine, and glycine in fetal serum. The analysis also indicates changes in glycerophospholipid metabolism and suggests changes in endoplasmic reticulum stress and antioxidant status in the placenta. These findings suggest that changes in placental function occurring with excess maternal cortisol in late gestation may contribute to metabolic dysfunction at birth.

Wnt-induced deubiquitination FoxM1 ensures nucleus ß-catenin transactivation.

A key step of Wnt signaling activation is the recruitment of ß-catenin to the Wnt target-gene promoter in the nucleus, but its mechanisms are largely unknown. Here, we identified FoxM1 as a novel target of Wnt signaling, which is essential for ß-catenin/TCF4 transactivation. GSK3 phosphorylates FoxM1 on serine 474 which induces FoxM1 ubiquitination mediated by FBXW7. Wnt signaling activation inhibits FoxM1 phosphorylation by GSK3-Axin complex and leads to interaction between FoxM1 and deubiquitinating enzyme USP5, thereby deubiquitination and stabilization of FoxM1. FoxM1 accumulation in the nucleus promotes recruitment of ß-catenin to Wnt target-gene promoter and activates the Wnt signaling pathway by protecting the ß-catenin/TCF4 complex from ICAT inhibition. Subsequently, the USP5-FoxM1 axis abolishes the inhibitory effect of ICAT and is required for Wnt-mediated tumor cell proliferation. Therefore, Wnt-induced deubiquitination of FoxM1 represents a novel and critical mechanism for controlling canonical Wnt signaling and cell proliferation.

Comparison of the performance of six stimulus paradigms in visual acuity assessment based on steady-state visual evoked potentials.

PURPOSE: There are several stimulus paradigms used in objective visual acuity assessment based on steady-state visual evoked potentials (SSVEPs). The aim of this study was to explore the difference and performance of common used six stimulus paradigms (reverse vertical sinusoidal gratings, reverse horizontal sinusoidal gratings, reverse vertical square-wave gratings, brief-onset vertical sinusoidal gratings, reversal checkerboards and oscillating expansion-contraction concentric-rings) of SSVEP acuity assessment. METHODS: We tested subjective visual acuity both by tumbling E and Freiburg Visual Acuity and Contrast Test (FrACT) in 11 subjects. SSVEPs were induced by 11 spatial frequencies for each paradigm, and then a threshold determination criterion was used to define the objective SSVEP visual acuity. RESULTS: After SSVEP signal analysis, we found there was difference in SSVEP response of harmonic components and no difference in sensitive electrode placement for the six paradigms. We selected six electrodes (PO3, POz, PO4, O1, Oz and O2) as the sensitive electrodes to use in data processing for each paradigm. The results showed that except for brief-onset vertical sinusoidal gratings, the correlation and agreement between objective SSVEP and subjective FrACT acuity were all quite good, demonstrating good performance in acuity detection for the rest five paradigms. CONCLUSION: Except for brief-onset vertical sinusoidal gratings, all the five stimulus paradigms of reverse vertical sinusoidal gratings, reverse horizontal sinusoidal gratings, reverse vertical square-wave gratings, reversal checkerboards and oscillating expansion-contraction concentric-rings performed quite well in objective SSVEP visual acuity assessment.

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review.

The algorithms of electroencephalography (EEG) decoding are mainly based on machine learning in current research. One of the main assumptions of machine learning is that training and test data belong to the same feature space and are subject to the same probability distribution. However, this may be violated in EEG processing. Variations across sessions/subjects result in a deviation of the feature distribution of EEG signals in the same task, which reduces the accuracy of the decoding model for mental tasks. Recently, transfer learning (TL) has shown great potential in processing EEG signals across sessions/subjects. In this work, we reviewed 80 related published studies from 2010 to 2020 about TL application for EEG decoding. Herein, we report what kind of TL methods have been used (e.g., instance knowledge, feature representation knowledge, and model parameter knowledge), describe which types of EEG paradigms have been analyzed, and summarize the datasets that have been used to evaluate performance. Moreover, we discuss the state-of-the-art and future development of TL for EEG decoding. The results show that TL can significantly improve the performance of decoding models across subjects/sessions and can reduce the calibration time of brain-computer interface (BCI) systems. This review summarizes the current practical suggestions and performance outcomes in the hope that it will provide guidance and help for EEG research in the future.

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network.

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.