Multi-scale 3D-CRU for EEG emotion recognition.

In this paper, we propose a novel multi-scale 3D-CRU model, with the goal of extracting more discriminative emotion feature from EEG signals. By concurrently exploiting the relative electrode locations and different frequency subbands of EEG signals, a three-dimensional feature representation is reconstructed wherein the Delta (δ) frequency pattern is included. We employ a multi-scale approach, termed 3D-CRU, to concurrently extract frequency and spatial features at varying levels of granularity within each time segment. In the proposed 3D-CRU, we introduce a multi-scale 3D Convolutional Neural Network (3D-CNN) to effectively capture discriminative information embedded within the 3D feature representation. To model the temporal dynamics across consecutive time segments, we incorporate a Gated Recurrent Unit (GRU) module to extract temporal representations from the time series of combined frequency-spatial features. Ultimately, the 3D-CRU model yields a global feature representation, encompassing comprehensive information across time, frequency, and spatial domains. Numerous experimental assessments conducted on publicly available DEAP and SEED databases provide empirical evidence supporting the enhanced performance of our proposed model in the domain of emotion recognition. These findings underscore the efficacy of the features extracted by the proposed multi-scale 3D-GRU model, particularly with the incorporation of the Delta (δ) frequency pattern. Specifically, on the DEAP dataset, the accuracy of Valence and Arousal are 93.12% and 94.31%, respectively, while on the SEED dataset, the accuracy is 92.25%.

Phosphate deficiency responsive TaSPX3 is involved in the regulation of shoot phosphorus in Arabidopsis plants.

SPX (SYG/PHO81/XPR1) domain genes have been reported to play vital roles in the Phosphorus (Pi) signaling network in Arabidopsis thaliana and rice. However, the functions of SPX proteins in wheat remain largely unknown. In this study, the full-length cDNA sequence of the TaSPX3 gene was cloned from the common wheat variety Zhengmai9023. The expression of TaSPX3 was up-regulated in eight different genotypes of wheat under low phosphorus (LP) stress, indicating that TaSPX3 responds to Pi limitation in multiple wheat genotypes. The transcription level of TaSPX3 was also detected in the absence of seven different elements, showing certain specificity for Pi deficiency in wheat. Over expressing TaSPX3 in Arabidopsis can alleviate Pi deficiency symptoms at the seedling stage and promote the growth of plant, and advance the flowering period at the adult stage. The expression of 7 genes associated with the Pi starvation signal pathways was analyzed using qRT-PCR. The results showed that TaSPX3, along with AtSPX1, AtRNS1, AtIPS1, AtPAP2, AtPAP17 and AtAT4, were all induced by Pi deficiency. This study reveals that the TaSPX3 gene in wheat is involved in the response to phosphorus stress and may affect shoot phosphorus levels through AT4 or PAPs-related pathways. Overall, our study provides new insights into the regulation of plant response under LP conditions and the molecular mechanism underlying the role of the wheat SPX gene in coping with LP stress.

Cross Domain Correlation Maximization for Enhancing the Target Recognition of SSVEP-Based Brain-Computer Interfaces.

The target recognition performance of steady-state visual evoked potential (SSVEP)-based brain-computer interfaces can be significantly improved with a training-based approach. However, the training procedure is time consuming and often causes fatigue. Consequently, the number of training data should be limited, which may reduce the classification performance. Thus, how to improve classification accuracy without increasing the training time is crucial to SSVEP-based BCI system. This study proposes a transfer-related component analysis (TransRCA) method for addressing the above issue. In this method, the SSVEP-related components are extracted from a small number of training data of the current individual and combined with those extracted from a large number of existing training data of other individuals. The TransRCA method maximizes not only the inter-trial covariances between the source and target subjects, but also the correlation between the reference signals and SSVEP signals from the source and target subjects. The proposed method was validated on the SSVEP public Benchmark and BETA datasets, and the classification accuracy and information transmission rate of the ensemble version of the proposed TransRCA method were compared with those of the state-of-the-art eCCA, eTRCA, ttCCA, LSTeTRCA, and eIISMC methods on both datasets. The comparison results indicate that the proposed method provides a superior performance compared with these state-of-the-art methods, and thus has high potential for the development of a SSVEP-based brain-computer interface system with high classification performance that only uses a small number of training data.

CC Chemokine 2 Promotes Ovarian Cancer Progression through the MEK/ERK/MAP3K19 Signaling Pathway.

Ovarian cancer is a gynecological tumor with an incidence rate lower than those of other gynecological tumor types and the second-highest death rate. CC chemokine 2 (CCL2) is a multifunctional factor associated with the progression of numerous cancers. However, the effect of CCL2 on ovarian cancer progression is unclear. Here, we found that exogenous CCL2 and the overexpression of CCL2 promoted the proliferation and metastasis of ovarian cancer cells. On the other hand, CCL2 knockdown via CRISPR/Cas9 inhibited ovarian cancer cell proliferation, migration, and invasion. The present study demonstrated that mitogen-activated protein three kinase 19 (MAP3K19) was the key CCL2 target for regulating ovarian cancer progression through transcriptome sequencing. Additionally, MAP3K19 knockout inhibited ovarian cancer cell proliferation, migration, and invasion. Furthermore, CCL2 increased MAP3K19 expression by activating the mitogen-activated protein kinase kinase (MEK)/extracellular signal-regulated kinase (ERK) pathway. The present study showed the correlation between CCL2 and ovarian cancer, suggesting that CCL2 may be a novel target for ovarian cancer therapy.

EEG-based major depressive disorder recognition by selecting discriminative features via stochastic search.

Objective. Major depressive disorder (MDD) is a prevalent psychiatric disorder whose diagnosis relies on experienced psychiatrists, resulting in a low diagnosis rate. As a typical physiological signal, electroencephalography (EEG) has indicated a strong association with human beings' mental activities and can be served as an objective biomarker for diagnosing MDD.Approach. The basic idea of the proposed method fully considers all the channel information in EEG-based MDD recognition and designs a stochastic search algorithm to select the best discriminative features for describing the individual channels.Main results. To evaluate the proposed method, we conducted extensive experiments on the MODMA dataset (including dot-probe tasks and resting state), a 128-electrode public EEG-based MDD dataset including 24 patients with depressive disorder and 29 healthy controls. Under the leave-one-subject-out cross-validation protocol, the proposed method achieved an average accuracy of 99.53% in the fear-neutral face pairs cued experiment and 99.32% in the resting state, outperforming state-of-the-art MDD recognition methods. Moreover, our experimental results also indicated that negative emotional stimuli could induce depressive states, and high-frequency EEG features contributed significantly to distinguishing between normal and depressive patients, which can be served as a marker for MDD recognition.Significance. The proposed method provided a possible solution to an intelligent diagnosis of MDD and can be used to develop a computer-aided diagnostic tool to aid clinicians in early diagnosis for clinical purposes.

Gapless Genome Assembly of Puccinia triticina Provides Insights into Chromosome Evolution in Pucciniales.

Chromosome evolution drives species evolution, speciation, and adaptive radiation. Accurate genome assembly is crucial to understanding chromosome evolution of species, such as dikaryotic fungi. Rust fungi (Pucciniales) in dikaryons represent the largest group of plant pathogens, but the evolutionary process of adaptive radiation in Pucciniales remains poorly understood. Here, we report a gapless genome for the wheat leaf rust fungus Puccinia triticina determined using PacBio high-fidelity (HiFi) sequencing. This gapless assembly contains two sets of chromosomes, showing that one contig represents one chromosome. Comparisons of homologous chromosomes between the phased haplotypes revealed that highly frequent small-scale sequence divergence shapes haplotypic variation. Genome analyses of Puccinia triticina along with other rusts revealed that recent transposable element bursts and extensive segmental gene duplications synergistically highlight the evolution of chromosome structures. Comparative analysis of chromosomes indicated that frequent chromosomal rearrangements may act as a major contributor to rapid radiation of Pucciniales. This study presents the first gapless, phased assembly for a dikaryotic rust fungus and provides insights into adaptive evolution and species radiation in Pucciniales. IMPORTANCE Rust fungi (Pucciniales) are the largest group of plant pathogens. Adaptive radiation is a predominant feature in Pucciniales evolution. Chromosome evolution plays an important role in adaptive evolution. Accurate chromosome-scale assembly is required to understand the role of chromosome evolution in Pucciniales. We took advantage of HiFi sequencing to construct a gapless, phased genome for Puccinia triticina. Further analyses revealed that the evolution of chromosome structures in rust lineage is shaped by the combination of transposable element bursts and segmental gene duplications. Chromosome comparisons of Puccinia triticina and other rusts suggested that frequent chromosomal arrangements may make remarkable contributions to high species diversity of rust fungi. Our results present the first gapless genome for Pucciniales and shed light on the feature of chromosome evolution in Pucciniales.

Effective Connectivity Analysis and Classification of Action Observation From Different Perspectives: An fMRI Study.

OBJECTIVE: Analyzing the effective connectivity characteristics of brain networks in the process of action observation is helpful for understanding the neurodynamic mechanisms during action observation. METHOD: In this study, functional magnetic resonance imaging (fMRI) images were obtained from 20 participants who performed hand-object interaction observation tasks from the first-person perspective (1PP) and third-person perspective (3PP). On the basis of a meta-analysis, 11 key brain regions were extracted as nodes to build an action observation network. The weighted and directional connections between all of the nodes were investigated using partial directional coherence (PDC) analysis in five narrow frequency bands. RESULTS: The statistical analysis indicated that the ultra-low frequency band ( ≤ 0.04 Hz) exhibited significant activation compared with other frequency bands for both 1PP and 3PP. In addition, it was found that 3PP induced significantly stronger brain activation than 1PP in the ultra-low frequency band. Moreover, this study attempted to classify fMRI data corresponding to different perspectives using brain network features. A comparative analysis revealed that the weighted and binary PDC matrix methods achieved classification accuracies of 86.3% and 80.8%, respectively. SIGNIFICANCE: The weighted PDC analysis exhibits a more comprehensive understanding of neural mechanisms during action observation in different visual perspectives. It also has potential applications value in human-computer interaction in the future.

Role of CC-chemokine ligand 2 in gynecological cancer.

Gynecological cancer is one of the most severe diseases that threaten the lives and health of women worldwide. Its incidence rate increases with each passing year and becomes more prevalent among young people. The prognosis of gynecological cancer remains poor despite significant advances in surgical removal and systemic chemotherapy. Several chemokines play a role in the progression of gynecologic cancers. CCL2 (CC-chemokine ligand 2), also termed MCP-1 (monocyte chemotactic protein 1), plays a significant physiological role in monocyte cell migration and the inflammatory response. Recent studies have demonstrated that CCL2 plays a pro-tumorigenic function in the tumor microenvironment. According to previous studies, CCL2 plays a significant role in the occurrence and development of gynecological cancers. Furthermore, recent studies noted that CCL2 could be a potential diagnostic biomarker and prognostic predictor. The purpose of this paper is to review the role of CCL2 in the occurrence and development of gynecological cancers and to discuss the potential therapeutic strategy of CCL2 for gynecological cancers, with a primary focus on breast cancer, ovarian cancer, cervical cancer, and endometrial cancer.

Barley GRIK1-SnRK1 kinases subvert a viral virulence protein to upregulate antiviral RNAi and inhibit infection.

Viruses often usurp host machineries for their amplification, but it remains unclear if hosts may subvert virus proteins to regulate viral proliferation. Here, we show that the 17K protein, an important virulence factor conserved in barley yellow dwarf viruses (BYDVs) and related poleroviruses, is phosphorylated by host GRIK1-SnRK1 kinases, with the phosphorylated 17K (P17K) capable of enhancing the abundance of virus-derived small interfering RNAs (vsiRNAs) and thus antiviral RNAi. Furthermore, P17K interacts with barley small RNA-degrading nuclease 1 (HvSDN1) and impedes HvSDN1-catalyzed vsiRNA degradation. Additionally, P17K weakens the HvSDN1-HvAGO1 interaction, thus hindering HvSDN1 from accessing and degrading HvAGO1-carried vsiRNAs. Importantly, transgenic expression of 17K phosphomimetics (17K5D ), or genome editing of SDN1, generates stable resistance to BYDV through elevating vsiRNA abundance. These data validate a novel mechanism that enhances antiviral RNAi through host subversion of a viral virulence protein to inhibit SDN1-catalyzed vsiRNA degradation and suggest new ways for engineering BYDV-resistant crops.

Expression and purification of recombinant human CCL5 and its biological characterization.

C-C motif chemokine ligand 5 (CCL5) is crucial in the tumor microenvironment. It has been previously reported to act as a key role in tumor invasion and metastasis. However, the function of exogenous CCL5 in ovarian cancer has not been well-characterized. The present study attempted to express and purify recombinant CCL5 protein and investigate the exogenous CCL5 in ovarian cancer cell proliferation. The human CCL5 was amplified and inserted into the pET-30a vectors for prokaryotic expression in Escherichia coli BL21. Soluble His-CCL5 was successfully expressed with 0.1 mmol/L of isopropyl-ß-D-1-tiogalactopiranoside at 25 ℃ and purified by affinity chromatography. Additionally, methyl thiazolyl tetrazolium (MTT) assay demonstrated that CCL5 promotes ovarian cancer cell proliferation; increases the phosphorylation levels of extracellular-signal-regulated kinase and mitogen-activated protein kinase/ERK kinase, and increases the mRNA levels of Jun, NF-κB2, Nras, Relb, and Traf2. Furthermore, treatment with the MEK inhibitor reduced the Jun, NF-κB2, and Traf2 mRNA levels, indicating that exogenous CCL5 increased ovarian cancer cell proliferation, through MEK/ERK pathway activation, and Jun, NF-κB2, and Traf2 expression. The present study provided primary data for further studies to discover more CCL5 functions in ovarian cancer.

ECSMP: A dataset on emotion, cognition, sleep, and multi-model physiological signals.

This paper described the collection of multi-modal physiological signals, which include electroencephalography, electrocardiograph (ECG), photoplethysmography, electrodermal activity, temperature, and accelerometer data, recorded from 89 healthy college students during resting state, the emotion induction and recovery, and a set of cognitive function assessment tasks. Emotion, sleep, cognition, depression, mood, and other factors were evaluated through different methods, and were included in this dataset. Six emotions (neutral, fear, sad, happy, anger, and disgust) were induced by movie clips. The cognitive functions such as sustained attention, response inhibition, working memory, and strategy use, were quantitatively measured by Cambridge neuropsychological test automatic battery. The sleep ECG was collected the night before the emotion-induction experiment, and the sleep quality was analysed based on the sleep ECG. After the experiment, the participants were required to fill in questionnaires to evaluate the emotion regulation strategies, depression score, recent mood, and sleep quality index. The database can not only be directly used for the research of emotion recognition on multi-modal physiological signals, but also can further explore the interactions between emotion, cognition, and sleep.

Identification of SPX family genes in the maize genome and their expression under different phosphate regimes.

Many studies have revealed that SPX (SYG1/Pho81/XPR1) family genes play a key role in signal transduction related to phosphorus (P) deficiency in plants. Here, we identified 33 SPX gene family members in maize through genome-wide analysis and classified them into 4 subfamilies according to SPX structural characteristics (SPX, SPX-MFS, SPX-EXS and SPX-RING). The promoter regions of ZmSPXs are rich in biotic/abiotic-related stress elements. The quantitative real-time PCR analysis of 33 ZmSPXs revealed that all members except for ZmSPX3 of the SPX subfamily were significantly induced under P-deficient conditions, especially ZmSPX4.1 and ZmSPX4.2, which showed strong responses to low P stress and exhibited remarkably different expression patterns in low Pi sensitive and insensitive cultivars of maize. These results suggested that the SPX subfamily might play pivotal roles in P stress sensing and response. Experimental observations of subcellular localization in maize protoplasts indicated the following results, implying multiple roles in cell metabolism: ZmSPX2, ZmSPX5 and ZmSPX6 localized in the nucleus; ZmSPX1 and ZmSPX3 localized in the nucleus and cytoplasm; and ZmSPX4.2 localized in the chloroplast. A Y2H assay suggested that ZmPHR1 could interact with ZmSPX3, ZmSPX4.2, ZmSPX5, and ZmSPX6, indicating the involvement of these proteins in the P stress response in a ZmPHR1-mediated manner.

First Report of Root Rot of Tobacco Caused by Fusarium brachygibbosum in China.

Tobacco (Nicotiana tabacum L.) is an important cash crop in China, with an estimated production of 2.2 million tons every year (Berbec and Matyka, 2020). In June 2020, a root rot disease was observed on tobacco (cv. Zhongyan 100) in four surveyed counties (Mianchi, Lushi, Duguan and Lingbao) in Sanmenxia. Diseased plants exhibited leaf chlorosis and purplish to brown vascular discoloration of stem, taproot and lateral roots. The disease incidence ranged from 15% to 40% in 11 surveyed fields, 36.7 ha in total. Twenty five diseased tissues were surface sterilized in 75% ethanol and placed on potato dextrose agar (PDA) medium. Fifteen single-spore isolates were obtained from 25 diseased tissue samples. All cultures growing on PDA had white colonies with abundant aerial mycelia initially, turning into yellow to orange in the center and produced red pigmentation after seven days of growth. The 7-day-old cultures grown on carnation leaf agar (CLA) produced macroconidia that were curved with 3-5 septa, had wide central cells, slightly pointy apex, and measured 17.0-45.9 µm long×3.0-4.6 µm wide (n=50). The microconidia formed on CLA were slightly curved, ovoid with zero to two septa, measuring 5.4-15.5 µm long×2.0-3.2 µm wide (n=50). Spherical chlamydospores (7.58-13.52 µm; n=50) were terminal or intercalary, single or in chains. Such characteristics were typical of Fuarium brachygibbosum (Tirado-Ramírez et al. 2018). DNA from one representative single-spore isolate (MC1) was extracted, and the translation elongation factor 1-alpha (EF1-α), RNA polymerase I largest subunit (RPB1) and second largest subunit (RPB2) genes were amplified with primers EF1/EF2, F5/G2R and RPB2F/R respectively (O'Donnell et al. 1998, 2010), and sequenced. Sequences were submitted to GenBank under accession numbers MT947796 (EF1-α), MW679536 (RPB1) and MW430664 (RPB2). The consensus sequences showed 99.70%, 99.94% and 100% identity to the sequences of F. brachygibbosum strain NRRL 34033 (accession no. GQ505418.1, HM347172.1 and GQ505482.1, Wang et al 2021). Morphological and molecular results confirmed this species as F. brachygibbosum (Al-Mahmooli, et al., 2013, Rentería -Martínez, et al., 2018). Pathogenicity tests were performed on tobacco seedlings grown on autoclaved tobacco specific substrate (Tobacco specific matrix, Ainong Biotechnology Co. Ltd, China). Healthy six-leaf stage tobacco seedlings (n=30; Zhongyan 100) were inoculated by placing 7-days old wheat seed (15 seeds per plant) infested with MC1 around the root. Thirty seedlings inoculated with sterile wheat seeds served as controls. All the plants were maintained in a growth chamber at 25±0.5℃ and 70% relative humidity. The assay was conducted three times. Typical symptoms of foliage chlorosis and root browning were observed 7-14 days after inoculation. The pathogen was reisolated from the necrotic tissue from all inoculated seedlings and was identified by sequencing partial EF1-α and RPB2 genes. Control plants remained asymptomatic and no pathogen was recovered from the control plants. Fusarium brachygibbosum is known as a pathogen of grains and cash crops in China (Shan, et al., 2017, Xia, et al., 2018). To our knowledge, this is the first report of F. brachygibbosum causing root rot on tobacco. We believe that our results will help to better understand rhizome fungal diseases affecting tobacco production in China. Acknowledgements: Funding was provided by the Science and Technology Project of Henan Provincial Tobacco Company (2020410000270012), Independent Innovation Project of Hennan Academy of Agricultural Sciences (2020ZC18) and Research and Development project of Henan Academy of Agricultural Sciences (2020CY010). References: Al-Mahmooli, I. H., et al. 2013. Plant Dis. 97:687; https://doi.org/10.1094/PDIS-09-12-0828-PDN Berbec A. K. and Matyka M. 2020. Agric. 10(11), 551; https://doi.org/10.3390/agriculture10110551 O'Donnell, K., et al. 1998. P. Natl. Acad. Sci. USA. 95(5):2044-2049; https://doi.org/10.1073/pnas.95.5.2044 O'Donnell, K., et al. 2010. J. Clin. Microbiol. 48(10)3708-3718; https://doi.org/10.1128/JCM.00989-10 Rentería -Martínez M.E., et al. 2018. Mex. J. of Phytopathol. 36(2):1-23; https://doi.org/10.18781/R.MEX.FIT.1710-1 Shan, L. Y., et al. 2017. Plant Dis. 101:837; https://doi.org/10.1094/PDIS-10-16-1465-PDN Tirado-Ramírez, M. A., et al. 2018. Plant Dis. 103; https://doi.org/10.1094/PDIS-04-18-0710-PDN Wang, S., et al. 2021. Plant Dis. 2021 Jan 6. doi: 10.1094/PDIS-05-20-0941-PDN. Epub ahead of print. PMID: 33406862. Xia, B., et al. 2018. Plant Dis. 102(11):2372; https://doi.org/10.1094/PDIS-12-17-1939-PDN The author(s) declare no conflict of interest.

SSVEP-Based Brain-Computer Interface With a Limited Number of Frequencies Based on Dual-Frequency Biased Coding.

How to encode as many targets as possible with a limited-frequency resource is a difficult problem in the practical use of a steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) speller. To solve this problem, this study developed a novel method called dual-frequency biased coding (DFBC) to tag targets in a SSVEP-based 48-character virtual speller, in which each target is encoded with a permutation sequence consisting of two permuted flickering periods that flash at different frequencies. The proposed paradigm was validated by 11 participants in an offline experiment and 7 participants in an online experiment. Three occipital channels (O1, Oz, and O2) were used to obtain the SSVEP signals for identifying the targets. Based on the coding characteristics of the DFBC method, the proposed approach has the ability of self-correction and thus achieves an accuracy of 76.6% and 79.3% for offline and online experiments, respectively, which outperforms the traditional multiple frequencies sequential coding (MFSC) method. This study demonstrates that DFBC is an efficient method for coding a high number of SSVEP targets with a small number of available frequencies.

Attentional focus modulates automatic finger-tapping movements.

The majority of human behaviors are composed of automatic movements (e.g., walking or finger-tapping) which are learned during nurturing and can be performed simultaneously without interfering with other tasks. One critical and yet to be examined assumption is that the attention system has the innate capacity to modulate automatic movements. The present study tests this assumption. Setting no deliberate goals for movement, we required sixteen participants to perform personalized and well-practiced finger-tapping movements in three experiments while focusing their attention on either different component fingers or away from movements. Using cutting-edge pose estimation techniques to quantify tapping trajectory, we showed that attention to movement can disrupt movement automaticity, as indicated by decreased inter-finger and inter-trial temporal coherence; facilitate the attended and inhibit the unattended movements in terms of tapping amplitude; and re-organize the action sequence into distinctive patterns according to the focus of attention. These findings demonstrate compelling evidence that attention can modulate automatic movements and provide an empirical foundation for theories based on such modulation in controlling human behavior.

Purification of recombinant human chemokine CCL2 in E. coli and its function in ovarian cancer.

Chemokine (CC-motif) ligand 2 (CCL2) is an inflammatory cytokine that regulates the infiltration and migration of monocytes. It is highly expressed by both tumor and stromal cells and has been associated with tumorigenesis. However, the effect of the exogenous administration of CCL2 on ovarian cancer remains largely unknown. In this report, we attempted to establish an expression system in Escherichia coli to produce recombinant hCCL2. The recombinant plasmid containing the hCCL2 cDNA was prepared using the prokaryotic-expression plasmid pGEX-5X-3 and transformed into E. coli BL21. GST-hCCL2 was successfully induced by 0.1 mmol/L IPTG at 20 °C for 6 h, and the recombinant protein was purified using affinity chromatography. The purified protein was identified by SDS-PAGE and Western Blot. In vitro experiments revealed that rhCCL2 promoted the proliferation of ovarian cancer cells and increased the levels of phosphorylation of MEK and ERK1/2, and the levels of JUN, RELB and NF-κB2 mRNA. Furthermore, inhibition of ERK signaling by treatment with PD98059 decreased ovarian cancer cell proliferation and levels of JUN, RELB, and NF-κB2 mRNA, indicating that exogenous rhCCL2 increased the proliferation of ovarian cancer cells, partially by activating the MAPK/ERK pathway, and by targeting JUN, RELB, and NF-κB2. Our study uncovered a promoting role of exogenous CCL2 on ovarian cancer cell proliferation through the MAPK/ERK signaling pathway, which may facilitate the discovery of more potential roles of CCL2 in ovarian cancer. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13205-020-02571-0.

Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network.

The main characteristic of depression is emotional dysfunction, manifested by increased levels of negative emotions and decreased levels of positive emotions. Therefore, accurate emotion recognition is an effective way to assess depression. Among the various signals used for emotion recognition, electroencephalogram (EEG) signal has attracted widespread attention due to its multiple advantages, such as rich spatiotemporal information in multi-channel EEG signals. First, we use filtering and Euclidean alignment for data preprocessing. In the feature extraction, we use short-time Fourier transform and Hilbert-Huang transform to extract time-frequency features, and convolutional neural networks to extract spatial features. Finally, bi-directional long short-term memory explored the timing relationship. Before performing the convolution operation, according to the unique topology of the EEG channel, the EEG features are converted into 3D tensors. This study has achieved good results on two emotion databases: SEED and Emotional BCI of 2020 WORLD ROBOT COMPETITION. We applied this method to the recognition of depression based on EEG and achieved a recognition rate of more than 70% under the five-fold cross-validation. In addition, the subject-independent protocol on SEED data has achieved a state-of-the-art recognition rate, which exceeds the existing research methods. We propose a novel EEG emotion recognition framework for depression detection, which provides a robust algorithm for real-time clinical depression detection based on EEG.

Toward Measuring Target Perception: First-Order and Second-Order Deep Network Pipeline for Classification of Fixation-Related Potentials.

The topdown determined visual object perception refers to the ability of a person to identify a prespecified visual target. This paper studies the technical foundation for measuring the target-perceptual ability in a guided visual search task, using the EEG-based brain imaging technique. Specifically, it focuses on the feature representation learning problem for single-trial classification of fixation-related potentials (FRPs). The existing methods either capture only first-order statistics while ignoring second-order statistics in data, or directly extract second-order statistics with covariance matrices estimated with raw FRPs that suffer from low signal-to-noise ratio. In this paper, we propose a new representation learning pipeline involving a low-level convolution subnetwork followed by a high-level Riemannian manifold subnetwork, with a novel midlevel pooling layer bridging them. In this way, the discriminative power of the first-order features can be increased by the convolution subnetwork, while the second-order information in the convolutional features could further be deeply learned with the subsequent Riemannian subnetwork. In particular, the temporal ordering of FRPs is well preserved for the components in our pipeline, which is considered to be a valuable source of discriminant information. The experimental results show that proposed approach leads to improved classification performance and robustness to lack of data over the state-of-the-art ones, thus making it appealing for practical applications in measuring the target-perceptual ability of cognitively impaired patients with the FRP technique.

Automatic Identification of High-Risk Autism Spectrum Disorder: A Feasibility Study Using Video and Audio Data Under the Still-Face Paradigm.

It is reported that the symptoms of autism spectrum disorder (ASD) could be improved by effective early interventions, which arouses an urgent need for large-scale early identification of ASD. Until now, the screening of ASD has relied on the child psychiatrist to collect medical history and conduct behavioral observations with the help of psychological assessment tools. Such screening measures inevitably have some disadvantages, including strong subjectivity, relying on experts and low-efficiency. With the development of computer science, it is possible to realize a computer-aided screening for ASD and alleviate the disadvantages of manual evaluation. In this study, we propose a behavior-based automated screening method to identify high-risk ASD (HR-ASD) for babies aged 8-24 months. The still-face paradigm (SFP) was used to elicit baby's spontaneous social behavior through a face-to-face interaction, in which a mother was required to maintain a normal interaction to amuse her baby for 2 minutes (a baseline episode) and then suddenly change to the no-reaction and no-expression status with 1 minute (a still-face episode). Here, multiple cues derived from baby's social stress response behavior during the latter episode, including head-movements, facial expressions and vocal characteristics, were statistically analyzed between HR-ASD and typical developmental (TD) groups. An automated identification model of HR-ASD was constructed based on these multi-cue features and the support vector machine (SVM) classifier; moreover, its screening performance was satisfied, for all the accuracy, specificity and sensitivity exceeded 90% on the cases included in this study. The experimental results suggest its feasibility in the early screening of HR-ASD.

Pain in the default mode network: a voxel-based morphometry study on thermal pain sensitivity.

During nociceptive processing of pain, activated regions, specified as the 'pain matrix', have been proven not selectively or preferentially tied to pain. Counterintuitively, the deactivated regions, especially the default mode network (DMN), are recently revealed to be simultaneously and functionally involved. In this study, we searched for pain-specific structural correlates among pain-free young adults using the voxel-based morphometry (VBM) approach within regions of interest comprising the pain matrix and DMN. Variances in confounding factors, namely the thermal detection threshold, thermal pain tolerance threshold and pain-related psychological traits, were statistically controlled to obtain pain-specific structural correlates. As a result, we found that less grey matter volume (GMV) of a critical DMN region, the precuneus, predicts enhanced thermal pain sensitivity (i.e., lower threshold). In contrast, this relationship is absent in all regions within the pain matrix. Such a dissociation between pain matrix and precuneus highlights the significance of precuneus in processing of pain, and is discussed with a conception taking pain as a salience detection system for the body, rather than as a nociceptive-specific system restricted within the so-called pain matrix.