Search

Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain computer interfaces (BCI). In view of the characteristics of non-stationarity, time-variability and individual diversity of EEG signals, a novel framework based on graph neural network is proposed for MI-EEG classification. First, an adaptive graph convolutional layer (AGCL) is constructed, by which the electrode channel information are integrated dynamically. We further propose an adaptive spatiotemporal graph convolutional network (ASTGCN), which fully exploits the characteristics of EEG signals in time domain and the channel correlations in spatial domain simultaneously. We execute the experiments using EEG signals recorded at motor imagery scenarios, where twenty-five healthy subjects performed MI movements of the right hand and feet to generate motor commands. Experimental results reveal that the proposed method outperforms state-of-the-art methods in terms of both classification quality and robustness. The advantages of ASTGCN include high accuracy, high efficiency, and robustness to cross-trial and cross-subject variations, making it an ideal candidate for long-term MI-EEG applications. [ABSTRACT FROM AUTHOR]

SUMMARY: Stigma characteristics are important factors affecting the seed yield of hybrid rice per unit area. Natural variation of stigma characteristics has been reported in rice, but the genetic basis for this variation is largely unknown. We performed a genome‐wide association study on three stigma characteristics in six environments using 1.3 million single‐nucleotide polymorphism (SNPs) characterized in 353 diverse accessions of Oryza sativa. An abundance of phenotypic variation was present in the three stigma characteristics of these collections. We identified four significant SNPs associated with stigma length, 20 SNPs with style length (SYL), and 17 SNPs with the sum of stigma and style length, which were detected repeatedly in more than four environments. Of these SNPs, 28 were novel. We identified two causal gene loci for SYL, OsSYL3 and OsSYL2; OsSYL3 was co‐localized with the grain size gene GS3. The SYL of accessions carrying allele OsSYL3AA was significantly longer than that of those carrying allele OsSYL3CC. We also demonstrated that the outcrossing rate of female parents carrying allele OsSYL2AA increased by 5.71% compared with that of the isogenic line carrying allele OsSYL2CC in an F1 hybrid seed production field. The allele frequencies of OsSYL3AA and OsSYL2AA decreased gradually with an increase in latitude in the Northern Hemisphere. Our results should facilitate the improvement in stigma characteristics of parents of hybrid rice. Significance Statement: The utilization of heterosis in rice is an effective strategy to enhance the grain yield. However, this entails the production of F1 hybrid seeds every year. The yield of F1 hybrid seeds is affected by stigma characteristics. The cloning of OsSYL2AA filled a gap in the genetic study of style length and could be used for improving stigma characteristics to increase the yield of F1 seeds. [ABSTRACT FROM AUTHOR]

Energy consumption is an important issue for resource-constrained wireless neural recording applications with limited data bandwidth. Compressed sensing (CS) is a promising framework for addressing this challenge because it can compress data in an energy-efficient way. Recent work has shown that deep neural networks (DNNs) can serve as valuable models for CS of neural action potentials (APs). However, these models typically require impractically large datasets and computational resources for training, and they do not easily generalize to novel circumstances. Here, we propose a new CS framework, termed APGen, for the reconstruction of APs in a training-free manner. It consists of a deep generative network and an analysis sparse regularizer. We validate our method on two in vivo datasets. Even without any training, APGen outperformed model-based and data-driven methods in terms of reconstruction accuracy, computational efficiency, and robustness to AP overlap and misalignment. The computational efficiency of APGen and its ability to perform without training make it an ideal candidate for long-term, resource-constrained, and large-scale wireless neural recording. It may also promote the development of real-time, naturalistic brain-computer interfaces.

Stigma characteristics are important factors affecting the seed yield of hybrid rice per unit area. Natural variation of stigma characteristics has been reported in rice, but the genetic basis for this variation is largely unknown. We performed a genome-wide association study on three stigma characteristics in six environments using 1.3 million single-nucleotide polymorphism (SNPs) characterized in 353 diverse accessions of Oryza sativa. An abundance of phenotypic variation was present in the three stigma characteristics of these collections. We identified four significant SNPs associated with stigma length, 20 SNPs with style length (SYL), and 17 SNPs with the sum of stigma and style length, which were detected repeatedly in more than four environments. Of these SNPs, 28 were novel. We identified two causal gene loci for SYL, OsSYL3 and OsSYL2; OsSYL3 was co-localized with the grain size gene GS3. The SYL of accessions carrying allele OsSYL3 AA was significantly longer than that of those carrying allele OsSYL3 CC . We also demonstrated that the outcrossing rate of female parents carrying allele OsSYL2 AA increased by 5.71% compared with that of the isogenic line carrying allele OsSYL2 CC in an F 1 hybrid seed production field. The allele frequencies of OsSYL3 AA and OsSYL2 AA decreased gradually with an increase in latitude in the Northern Hemisphere. Our results should facilitate the improvement in stigma characteristics of parents of hybrid rice., (© 2020 The Authors. The Plant Journal published by Society for Experimental Biology and John Wiley & Sons Ltd.)