A brain functional network feature extraction method based on directed transfer function and graph theory for MI-BCI decoding tasks.

Background: The development of Brain-Computer Interface (BCI) technology has brought tremendous potential to various fields. In recent years, prominent research has focused on enhancing the accuracy of BCI decoding algorithms by effectively utilizing meaningful features extracted from electroencephalographic (EEG) signals. Objective: This paper proposes a method for extracting brain functional network features based on directed transfer function (DTF) and graph theory. The method incorporates the extracted brain network features with common spatial pattern (CSP) to enhance the performance of motor imagery (MI) classification task. Methods: The signals from each electrode of the EEG, utilizing a total of 32 channels, are used as input signals for the network nodes. In this study, 26 healthy participants were recruited to provide EEG data. The brain functional network is constructed in Alpha and Beta bands using the DTF method. The node degree (ND), clustering coefficient (CC), and global efficiency (GE) of the brain functional network are obtained using graph theory. The DTF network features and graph theory are combined with the traditional signal processing method, the CSP algorithm. The redundant network features are filtered out using the Lasso method, and finally, the fused features are classified using a support vector machine (SVM), culminating in a novel approach we have termed CDGL. Results: For Beta frequency band, with 8 electrodes, the proposed CDGL method achieved an accuracy of 89.13%, a sensitivity of 90.15%, and a specificity of 88.10%, which are 14.10, 16.69, and 11.50% percentage higher than the traditional CSP method (75.03, 73.46, and 76.60%), respectively. Furthermore, the results obtained with 8 channels were superior to those with 4 channels (82.31, 83.35, and 81.74%), and the result for the Beta frequency band were better than those for the Alpha frequency band (87.42, 87.48, and 87.36%). Similar results were also obtained on two public datasets, where the CDGL algorithm's performance was found to be optimal. Conclusion: The feature fusion of DTF network and graph theory features enhanced CSP algorithm's performance in MI task classification. Increasing the number of channels allows for more EEG signal feature information, enhancing the model's sensitivity and discriminative ability toward specific activities in brain regions. It should be noted that the functional brain network features in the Beta band exhibit superior performance improvement for the algorithm compared to those in the Alpha band.

A fused multi-subfrequency bands and CBAM SSVEP-BCI classification method based on convolutional neural network.

For the brain-computer interface (BCI) system based on steady-state visual evoked potential (SSVEP), it is difficult to obtain satisfactory classification performance for short-time window SSVEP signals by traditional methods. In this paper, a fused multi-subfrequency bands and convolutional block attention module (CBAM) classification method based on convolutional neural network (CBAM-CNN) is proposed for discerning SSVEP-BCI tasks. This method extracts multi-subfrequency bands SSVEP signals as the initial input of the network model, and then carries out feature fusion on all feature inputs. In addition, CBAM is embedded in both parts of the initial input and feature fusion for adaptive feature refinement. To verify the effectiveness of the proposed method, this study uses the datasets of Inner Mongolia University of Technology (IMUT) and Tsinghua University (THU) to evaluate the performance of the proposed method. The experimental results show that the highest accuracy of CBAM-CNN reaches 0.9813 percentage point (pp). Within 0.1-2 s time window, the accuracy of CBAM-CNN is 0.0201-0.5388 (pp) higher than that of CNN, CCA-CWT-SVM, CCA-SVM, CCA-GNB, FBCCA, and CCA. Especially in the short-time window range of 0.1-1 s, the performance advantage of CBAM-CNN is more significant. The maximum information transmission rate (ITR) of CBAM-CNN is 503.87 bit/min, which is 227.53 bit/min-503.41 bit/min higher than the above six EEG decoding methods. The study further results show that CBAM-CNN has potential application value in SSVEP decoding.

Research on Physiological Characteristics and Differential Gene Expression of Rice Hybrids and Their Parents under Salt Stress at Seedling Stage.

Soil salinization is one of the most important abiotic stresses which can seriously affect the growth and development of rice, leading to the decrease in or even loss of a rice harvest. Increasing the rice yield of saline soil is a key issue for agricultural production. The utilization of heterosis could significantly increase crop biomass and yield, which might be an effective way to meet the demand for rice cultivation in saline soil. In this study, to elucidate the regulatory mechanisms of rice hybrids and their parents that respond to salt stress, we investigated the phenotypic characteristics, physiological and biochemical indexes, and expression level of salt-related genes at the seedling stage. In this study, two sets of materials, encapsulating the most significant differences between the rice hybrids and their parents, were screened using the salt damage index and a hybrid superiority analysis. Compared with their parents, the rice hybrids Guang-Ba-You-Hua-Zhan (BB1) and Y-Liang-You-900 (GD1) exhibited much better salt tolerance, including an increased fresh weight and higher survival rate, a better scavenging ability towards reactive oxygen species (ROS), better ionic homeostasis with lower content of Na+ in their Na+/K+ ratio, and a higher expression of salt-stress-responsive genes. These results indicated that rice hybrids developed complex regulatory mechanisms involving multiple pathways and genes to adapt to salt stress and provided a physiological basis for the utilization of heterosis for improving the yield of rice under salt stress.

Influence of high natural field temperature during grain filling stage on the morphological structure and physicochemical properties of rice (Oryza sativa L.) starch.

This study investigated the effects of natural high temperature in the field during grain filling stage on the morphological structure and physicochemical properties of rice starch. High natural field temperature during rice grain filling stage resulted in poor processing and appearance quality, higher gelatinization properties including gelatinization temperature, gelatinization enthalpy, swelling power, and water solubility due to the reduction of amylose content. High temperature decreased the setback and trough viscosities, and increased breakdown, implying that the pasting properties were slightly better. High temperature did not change the starch crystalline type, while it significantly affected relative crystallinity, as well as pitting and unevenness on the surface of the starch granules with lower granule size. The above results imply that high temperature can degrade cooking and eating quality, and increase pasting properties of starch slightly.

Identification of heat-sensitive QTL derived from common wild rice (Oryza rufipogon Griff.).

Understanding the responses of rice plants to heat-stress is a challenging, yet crucial, endeavor. A set of introgression lines was previously developed using an advanced backcrossing strategy that involved the elite indica cultivar Teqing as the recipient and an accession of common wild rice (Oryza rufipongon Griff.) as the donor. In this study, we evaluated the responses of 90 of these previously developed introgression lines to heat stress. Five quantitative trait loci (QTLs) related to heat response were detected. The phenotypic variances explained by these QTLs ranged from 6.83% to 14.63%, and O. rufipogon-derived alleles at one locus reduced sensitivity to heat. A heat-sensitive introgression line, YIL106, was identified and characterized. Genotypic analysis demonstrated that YIL106 contained four introgressed segments derived from O. rufipongon and two QTLs (qHTS1-1 and qHTS3) related to heat response. Physiological tests, including measurements of chlorophyll content, electrolyte leakage, malondialdehyde content, and soluble sugar content, were consistent with the heat sensitivity observed in YIL106. Ultrastructural analysis of YIL106 mesophyll cells showed that they were severely damaged following heat stress. This suggests that modification of the cell membrane system is a primary response to heat stress in plants. Identification and characterization of the heat-sensitive line YIL106 may facilitate the isolation of genes associated with the response of rice plants to heat stress.