[Automatic epilepsy detection with an attention-based multiscale residual network].

The deep learning-based automatic detection of epilepsy electroencephalogram (EEG), which can avoid the artificial influence, has attracted much attention, and its effectiveness mainly depends on the deep neural network model. In this paper, an attention-based multi-scale residual network (AMSRN) was proposed in consideration of the multiscale, spatio-temporal characteristics of epilepsy EEG and the information flow among channels, and it was combined with multiscale principal component analysis (MSPCA) to realize the automatic epilepsy detection. Firstly, MSPCA was used for noise reduction and feature enhancement of original epilepsy EEG. Then, we designed the structure and parameters of AMSRN. Among them, the attention module (AM), multiscale convolutional module (MCM), spatio-temporal feature extraction module (STFEM) and classification module (CM) were applied successively to signal reexpression with attention weighted mechanism as well as extraction, fusion and classification for multiscale and spatio-temporal features. Based on the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) public dataset, the AMSRN model achieved good results in sensitivity (98.56%), F1 score (98.35%), accuracy (98.41%) and precision (98.43%). The results show that AMSRN can make good use of brain network information flow caused by seizures to enhance the difference among channels, and effectively capture the multiscale and spatio-temporal features of EEG to improve the performance of epilepsy detection.

Elucidation of arsenic detoxification mechanism in Marchantia polymorpha: The role of ACR3.

The arsenic-specific ACR3 transporter plays pivotal roles in As detoxification in yeast and a group of ancient tracheophytes, the ferns. Despite putative ACR3 genes being present in the genomes of bryophytes, whether they have the same relevance also in this lineage is currently unknown. In this study, we characterized the MpACR3 gene from the bryophyte Marchantia polymorpha L. through a multiplicity of functional approaches ranging from phylogenetic reconstruction, expression analysis, loss- and gain-of-function as well as genetic complementation with an MpACR3 gene tagged with a fluorescent protein. Genetic complementation demonstrates that MpACR3 plays a pivotal role in As tolerance in M. polymorpha, with loss-of-function Mpacr3 mutants being hypersensitive and MpACR3 overexpressors more tolerant to As. Additionally, MpACR3 activity regulates intracellular As concentration, affects its speciation and controls the levels of intracellular oxidative stress. The MpACR3::3xCitrine appears to localize at the plasma membrane and possibly in other endomembrane systems. Taken together, these results demonstrate the pivotal function of ACR3 detoxification in both sister lineages of land plants, indicating that it was present in the common ancestor to all embryophytes. We propose that Mpacr3 mutants could be used in developing countries as low-cost and low-technology visual bioindicators to detect As pollution in water.

A Novel Isoprene Synthase from the Monocot Tree Copernicia prunifera (Arecaceae) Confers Enhanced Drought Tolerance in Transgenic Arabidopsis.

The capacity to emit isoprene, among other stresses, protects plants from drought, but the molecular mechanisms underlying this trait are only partly understood. The Arecaceae (palms) constitute a very interesting model system to test the involvement of isoprene in enhancing drought tolerance, as their high isoprene emissions may have contributed to make them hyperdominant in neotropical dry forests, characterized by recurrent and extended periods of drought stress. In this study we isolated and functionally characterized a novel isoprene synthase, the gene responsible for isoprene biosynthesis, from Copernicia prunifera, a palm from seasonally dry tropical forests. When overexpressed in the non-emitter Arabidopsis thaliana, CprISPS conferred significant levels of isoprene emission, together with enhanced tolerance to water limitation throughout plant growth and development, from germination to maturity. CprISPS overexpressors displayed higher germination, cotyledon/leaf greening, water usage efficiency, and survival than WT Arabidopsis under various types of water limitation. This increased drought tolerance was accompanied by a marked transcriptional up-regulation of both ABA-dependent and ABA-independent key drought response genes. Taken together, these results demonstrate the capacity of CprISPS to enhance drought tolerance in Arabidopsis and suggest that isoprene emission could have evolved in Arecaceae as an adaptive mechanism against drought.

Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU.

Deep learning has been applied to the recognition of motor imagery electroencephalograms (MI-EEG) in brain-computer interface, and the performance results depend on data representation as well as neural network structure. Especially, MI-EEG is so complex with the characteristics of non-stationarity, specific rhythms, and uneven distribution; however, its multidimensional feature information is difficult to be fused and enhanced simultaneously in the existing recognition methods. In this paper, a novel channel importance (NCI) based on time-frequency analysis is proposed to develop an image sequence generation method (NCI-ISG) for enhancing the integrity of data representation and highlighting the contribution inequalities of different channels as well. Each electrode of MI-EEG is converted to a time-frequency spectrum by utilizing short-time Fourier transform; the corresponding part to 8-30 Hz is combined with random forest algorithm for computing NCI; and it is further divided into three sub-images covered by α (8-13 Hz), ß1 (13-21 Hz), and ß2 (21-30 Hz) bands; their spectral powers are further weighted by NCI and interpolated to 2-dimensional electrode coordinates, producing three main sub-band image sequences. Then, a parallel multi-branch convolutional neural network and gate recurrent unit (PMBCG) is designed to successively extract and identify the spatial-spectral and temporal features from the image sequences. Two public four-class MI-EEG datasets are adopted; the proposed classification method respectively achieves the average accuracies of 98.26% and 80.62% by 10-fold cross-validation experiment; and its statistical performance is also evaluated by multi-indexes, such as Kappa value, confusion matrix, and ROC curve. Extensive experiment results show that NCI-ISG + PMBCG can yield great performance on MI-EEG classification compared to state-of-the-art methods. The proposed NCI-ISG can enhance the feature representation of time-frequency-space domains and match well with PMBCG, which improves the recognition accuracies of MI tasks and demonstrates the preferable reliability and distinguishable ability. This paper proposes a novel channel importance (NCI) based on time-frequency analysis to develop an image sequences generation method (NCI-ISG) for enhancing the integrity of data representation and highlighting the contribution inequalities of different channels as well. Then, a parallel multi-branch convolutional neural network and gate recurrent unit (PMBCG) is designed to successively extract and identify the spatial-spectral and temporal features from the image sequences.

Decoding motor imagery with a simplified distributed dipoles model at source level.

Motor imagery (MI) based brain computer interface significantly oriented the development of neuro-rehabilitation, and the crucial issue is how to accurately detect the changes of cerebral cortex for MI decoding. The brain activity can be calculated based on the head model and observed scalp EEG, providing insights regarding cortical dynamics by using equivalent current dipoles with high spatial and temporal resolution. Now, all the dipoles within entire cortex or partial regions of interest are directly applied to data representation, this may make the key information weakened or lost, and it is worth studying how to choose the most important from numerous dipoles. In this paper, we devote to building a simplified distributed dipoles model (SDDM), which is combined with convolutional neural network (CNN), generating a MI decoding method at source level (called SDDM-CNN). First, all channels of raw MI-EEG signals are subdivided by a series of bandpass filters with width of 1 Hz, the average energies associated with any sub-band signals are calculated and ranked in a descending order to screen the top n sub-bands; then, the MI-EEG signals over each selected sub-band are mapped into source space by using EEG source imaging technology, and for each scout of neuroanatomical Desikan-Killiany partition, a centered dipole is selected as the most relevant dipole and put together to build a SDDM to reflect the neuroelectric activity of entire cerebral cortex; finally, the 4 dimensional (4D) magnitude matrix is constructed for each SDDM and fused into a novel data representation, which is further input to a well-designed 3DCNN with n parallel branches (nB3DCNN) to extract and classify the comprehensive features from time-frequency-space dimensions. Experiments are carried out on three public datasets, and the average ten-fold CV decoding accuracies achieve 95.09%, 97.98% and 94.53% respectively, and the statistical analysis is fulfilled by standard deviation, kappa value and confusion matrix. Experiment results suggest that it is beneficial to pick out the most sensitive sub-bands in sensor domain, and SDDM can sufficiently describe the dynamic changing of entire cortex, improving decoding performance while greatly reducing number of source signals. Also, nB3DCNN is capable of exploring spatial-temporal features from multi sub-bands.

Applying correlation analysis to electrode optimization in source domain.

In brain computer interface-based neurorehabilitation system, a large number of electrodes may increase the difficulty of signal acquisition and the time consumption of decoding algorithm for motor imagery EEG (MI-EEG). The traditional electrode optimization methods were limited by the low spatial resolution of scalp EEG. EEG source imaging (ESI) was further applied to reduce the number of electrodes, in which either the electrodes covering activated cortical areas were selected, or the reconstructed electrodes of EEGs with higher Fisher scores were retained. However, the activated dipoles do not all contribute equally to decoding, and the Fisher score cannot represent the correlations between electrodes and dipoles. In this paper, based on ESI and correlation analysis, a novel electrode optimization method, denoted ECCEO, was developed. The scalp MI-EEG was mapped to cortical regions by ESI, and the dipoles with larger amplitudes were chosen to designate a region of interest (ROI). Then, Pearson correlation coefficients between each dipole of the ROI and the corresponding electrode were calculated, averaged, and ranked to obtain two average correlation coefficient sequences. A small but important group of electrodes for each class were alternately added to the predetermined basic electrode set to form a candidate electrode set. Their features were extracted and evaluated to determine the optimal electrode set. Experiments were conducted on two public datasets, the average decoding accuracies achieved 95.99% and 88.30%, and the reduction of computational cost were 65% and 56%, respectively; statistical significance was examined as well.

CRISPR/Cas9 genome-editing applied to MdPGT1 in apple results in reduced foliar phloridzin without impacting plant growth.

Phloridzin is the most abundant polyphenolic compound in apple (Malus × domestica Borkh.), which results from the action of a key phloretin-specific UDP-2'-O-glucosyltransferase (MdPGT1). Here, we simultaneously assessed the effects of targeting MdPGT1 by conventional transgenesis and clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated protein 9 (Cas9)-mediated genome editing. To this end, we conducted transcriptomic and metabolic analyses of MdPGT1 RNA interference knockdown and genome-edited lines. Knockdown lines exhibited characteristic impairment of plant growth and leaf morphology, whereas genome-edited lines exhibited normal growth despite reduced foliar phloridzin. RNA-sequencing analysis identified a common core of regulated genes, involved in phenylpropanoid and flavonoid pathways. However, we identified genes and processes differentially modulated in stunted and genome-edited lines, including key transcription factors and genes involved in phytohormone signalling. Therefore, we conducted a phytohormone profiling to obtain insight into their role in the phenotypes observed. We found that salicylic and jasmonic acid were increased in dwarf lines, whereas auxin and ABA showed no correlation with the growth phenotype. Furthermore, bioactive brassinosteroids were commonly up-regulated, whereas gibberellin GA4 was distinctively altered, showing a sharp decrease in RNA interference knockdown lines. Expression analysis by reverse transcriptase-quantitative polymerase chain reaction expression analysis further confirmed transcriptional regulation of key factors involved in brassinosteroid and gibberellin interaction. These findings suggest that a differential modulation of phytohormones may be involved in the contrasting effects on growth following phloridzin reduction. The present study also illustrates how CRISPR/Cas9 genome editing can be applied to dissect the contribution of genes involved in phloridzin biosynthesis in apple.

A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification.

Domain adaptation, as an important branch of transfer learning, can be applied to cope with data insufficiency and high subject variabilities in motor imagery electroencephalogram (MI-EEG) based brain-computer interfaces. The existing methods generally focus on aligning data and feature distribution; however, aligning each source domain with the informative samples of the target domain and seeking the most appropriate source domains to enhance the classification effect has not been considered. In this paper, we propose a dual alignment-based multi-source domain adaptation framework, denoted DAMSDAF. Based on continuous wavelet transform, all channels of MI-EEG signals are converted respectively and the generated time-frequency spectrum images are stitched to construct multi-source domains and target domain. Then, the informative samples close to the decision boundary are found in the target domain by using entropy, and they are employed to align and reassign each source domain with normalized mutual information. Furthermore, a multi-branch deep network (MBDN) is designed, and the maximum mean discrepancy is embedded in each branch to realign the specific feature distribution. Each branch is separately trained by an aligned source domain, and all the single branch transfer accuracies are arranged in descending order and utilized for weighted prediction of MBDN. Therefore, the most suitable number of source domains with top weights can be automatically determined. Extensive experiments are conducted based on 3 public MI-EEG datasets. DAMSDAF achieves the classification accuracies of 92.56%, 69.45% and 89.57%, and the statistical analysis is performed by the kappa value and t-test. Experimental results show that DAMSDAF significantly improves the transfer effects compared to the present methods, indicating that dual alignment can sufficiently use the different weighted samples and even source domains at different levels as well as realizing optimal selection of multi-source domains.

[Parameter transfer learning based on shallow visual geometry group network and its application in motor imagery classification].

Transfer learning is provided with potential research value and application prospect in motor imagery electroencephalography (MI-EEG)-based brain-computer interface (BCI) rehabilitation system, and the source domain classification model and transfer strategy are the two important aspects that directly affect the performance and transfer efficiency of the target domain model. Therefore, we propose a parameter transfer learning method based on shallow visual geometry group network (PTL-sVGG). First, Pearson correlation coefficient is used to screen the subjects of the source domain, and the short-time Fourier transform is performed on the MI-EEG data of each selected subject to acquire the time-frequency spectrogram images (TFSI). Then, the architecture of VGG-16 is simplified and the block design is carried out, and the modified sVGG model is pre-trained with TFSI of source domain. Furthermore, a block-based frozen-fine-tuning transfer strategy is designed to quickly find and freeze the block with the greatest contribution to sVGG model, and the remaining blocks are fine-tuned by using TFSI of target subjects to obtain the target domain classification model. Extensive experiments are conducted based on public MI-EEG datasets, the average recognition rate and Kappa value of PTL-sVGG are 94.9% and 0.898, respectively. The results show that the subjects' optimization is beneficial to improve the model performance in source domain, and the block-based transfer strategy can enhance the transfer efficiency, realizing the rapid and effective transfer of model parameters across subjects on the datasets with different number of channels. It is beneficial to reduce the calibration time of BCI system, which promote the application of BCI technology in rehabilitation engineering.

A dynamic directed transfer function for brain functional network-based feature extraction.

Directed transfer function (DTF) is good at characterizing the pairwise interactions from whole brain network and has been applied in discrimination of motor imagery (MI) tasks. Considering the fact that MI electroencephalogram signals are more non-stationary in frequency domain than in time domain, and the activated intensities of α band (8-13 Hz) and ß band [13-30 Hz, with [Formula: see text](13-21 Hz) and [Formula: see text](21-30 Hz) included] have considerable differences for different subjects, a dynamic DTF (DDTF) with variable model order and frequency band is proposed to construct the brain functional networks (BFNs), whose information flows and outflows are further calculated as network features and evaluated by support vector machine. Extensive experiments are conducted based on a public BCI competition dataset and a real-world dataset, the highest recognition rate achieve 100% and 86%, respectively. The experimental results suggest that DDTF can reflect the dynamic evolution of BFN, the best subject-based DDTF appears in one of four frequency sub-bands (α, ß, [Formula: see text] [Formula: see text]) for discrimination of MI tasks and is much more related to the current and previous states. Besides, DDTF is superior compared to granger causality-based and traditional feature extraction methods, the t-test and Kappa values show its statistical significance and high consistency as well.

Metal Detoxification in Land Plants: From Bryophytes to Vascular Plants. STATE of the Art and Opportunities.

Potentially toxic elements are a widespread concern due to their increasing diffusion into the environment. To counteract this problem, the relationship between plants and metal(loid)s has been investigated in the last 30 years. In this field, research has mainly dealt with angiosperms, whereas plant clades that are lower in the evolutive scale have been somewhat overlooked. However, recent studies have revealed the potential of bryophytes, pteridophytes and gymnosperms in environmental sciences, either as suitable indicators of habitat health and elemental pollution or as efficient tools for the reclamation of degraded soils and waters. In this review, we summarize recent research on the interaction between plants and potentially toxic elements, considering all land plant clades. The focus is on plant applicability in the identification and restoration of polluted environments, as well as on the characterization of molecular mechanisms with a potential outlet in the engineering of element tolerance and accumulation.

A Novel Sleep Staging Network Based on Data Adaptation and Multimodal Fusion.

Sleep staging is one of the important methods to diagnosis and treatment of sleep diseases. However, it is laborious and time-consuming, therefore, computer assisted sleep staging is necessary. Most of the existing sleep staging researches using hand-engineered features rely on prior knowledges of sleep analysis, and usually single channel electroencephalogram (EEG) is used for sleep staging task. Prior knowledge is not always available, and single channel EEG signal cannot fully represent the patient's sleeping physiological states. To tackle the above two problems, we propose an automatic sleep staging network model based on data adaptation and multimodal feature fusion using EEG and electrooculogram (EOG) signals. 3D-CNN is used to extract the time-frequency features of EEG at different time scales, and LSTM is used to learn the frequency evolution of EOG. The nonlinear relationship between the High-layer features of EEG and EOG is fitted by deep probabilistic network. Experiments on SLEEP-EDF and a private dataset show that the proposed model achieves state-of-the-art performance. Moreover, the prediction result is in accordance with that from the expert diagnosis.

High-throughput, Robust and Highly Time-flexible Method for Surface Sterilization of Arabidopsis Seeds.

Arabidopsis is by far the plant model species most widely used for functional studies. The surface sterilization of Arabidopsis seeds is a fundamental step required towards this end. Thus, it is paramount to establish high-throughput Arabidopsis seed surface sterilization methods to handle tens to hundreds of samples (e.g., transgenic lines, ecotypes, or mutants) at once. A seed surface sterilization method based on the efficient elimination of liquid in tubes with a homemade suction device constructed from a common vacuum pump is presented in this study. By dramatically reducing labor-intensive hands-on time with this method handling several hundreds of samples in one day is possible with little effort. Series time-course analyses further indicated a highly flexible time range of surface sterilization by maintaining high germination rates. This method could be easily adapted for surface sterilization of other kinds of small seeds with simple customization of the suction device according to the seed size, and the speed desired to eliminate the liquid.

Plant biodiversity assessment through pollen DNA metabarcoding in Natura 2000 habitats (Italian Alps).

Monitoring biodiversity is of increasing importance in natural ecosystems. Metabarcoding can be used as a powerful molecular tool to complement traditional biodiversity monitoring, as total environmental DNA can be analyzed from complex samples containing DNA of different origin. The aim of this research was to demonstrate the potential of pollen DNA metabarcoding using the chloroplast trnL partial gene sequencing to characterize plant biodiversity. Collecting airborne biological particles with gravimetric Tauber traps in four Natura 2000 habitats within the Natural Park of Paneveggio Pale di San Martino (Italian Alps), at three-time intervals in 1 year, metabarcoding identified 68 taxa belonging to 32 local plant families. Metabarcoding could identify with finer taxonomic resolution almost all non-rare families found by conventional light microscopy concurrently applied. However, compared to microscopy quantitative results, Poaceae, Betulaceae, and Oleaceae were found to contribute to a lesser extent to the plant biodiversity and Pinaceae were more represented. Temporal changes detected by metabarcoding matched the features of each pollen season, as defined by aerobiological studies running in parallel, and spatial heterogeneity was revealed between sites. Our results showcase that pollen metabarcoding is a promising approach in detecting plant species composition which could provide support to continuous monitoring required in Natura 2000 habitats for biodiversity conservation.

Automatic feature extraction and fusion recognition of motor imagery EEG using multilevel multiscale CNN.

A motor imagery EEG (MI-EEG) signal is often selected as the driving signal in an active brain computer interface (BCI) system, and it has been a popular field to recognize MI-EEG images via convolutional neural network (CNN), which poses a potential problem for maintaining the integrity of the time-frequency-space information in MI-EEG images and exploring the feature fusion mechanism in the CNN. However, information is excessively compressed in the present MI-EEG image, and the sequential CNN is unfavorable for the comprehensive utilization of local features. In this paper, a multidimensional MI-EEG imaging method is proposed, which is based on time-frequency analysis and the Clough-Tocher (CT) interpolation algorithm. The time-frequency matrix of each electrode is generated via continuous wavelet transform (WT), and the relevant section of frequency is extracted and divided into nine submatrices, the longitudinal sums and lengths of which are calculated along the directions of frequency and time successively to produce a 3 × 3 feature matrix for each electrode. Then, feature matrix of each electrode is interpolated to coincide with their corresponding coordinates, thereby yielding a WT-based multidimensional image, called WTMI. Meanwhile, a multilevel and multiscale feature fusion convolutional neural network (MLMSFFCNN) is designed for WTMI, which has dense information, low signal-to-noise ratio, and strong spatial distribution. Extensive experiments are conducted on the BCI Competition IV 2a and 2b datasets, and accuracies of 92.95% and 97.03% are yielded based on 10-fold cross-validation, respectively, which exceed those of the state-of-the-art imaging methods. The kappa values and p values demonstrate that our method has lower class skew and error costs. The experimental results demonstrate that WTMI can fully represent the time-frequency-space features of MI-EEG and that MLMSFFCNN is beneficial for improving the collection of multiscale features and the fusion recognition of general and abstract features for WTMI.

A novel decoding method for motor imagery tasks with 4D data representation and 3D convolutional neural networks.

Objective. Motor imagery electroencephalography (MI-EEG) produces one of the most commonly used biosignals in intelligent rehabilitation systems. The newly developed 3D convolutional neural network (3DCNN) is gaining increasing attention for its ability to recognize MI tasks. The key to successful identification of movement intention is dependent on whether the data representation can faithfully reflect the cortical activity induced by MI. However, the present data representation, which is often generated from partial source signals with time-frequency analysis, contains incomplete information. Therefore, it would be beneficial to explore a new type of data representation using raw spatiotemporal dipole information as well as the possible development of a matching 3DCNN.Approach.Based on EEG source imaging and 3DCNN, a novel decoding method for identifying MI tasks is proposed, called ESICNND. MI-EEG is mapped to the cerebral cortex by the standardized low resolution electromagnetic tomography algorithm, and the optimal sampling points of the dipoles are selected as the time of interest to best reveal the difference between any two MI tasks. Then, the initial subject coordinate system is converted to a magnetic resonance imaging coordinate system, followed by dipole interpolation and volume down-sampling; the resulting 3D dipole amplitude matrices are merged at the selected sampling points to obtain 4D dipole feature matrices (4DDFMs). These matrices are augmented by sliding window technology and input into a 3DCNN with a cascading architecture of three modules (3M3DCNN) to perform the extraction and classification of comprehensive features.Main results.Experiments are carried out on two public datasets; the average ten-fold CV classification accuracies reach 88.73% and 96.25%, respectively, and the statistical analysis demonstrates outstanding consistency and stability.Significance.The 4DDFMs reveals the variation of cortical activation in a 3D spatial cube with a temporal dimension and matches the 3M3DCNN well, making full use of the high-resolution spatiotemporal information from all dipoles.

Evolution of isoprene emission in Arecaceae (palms).

Isoprene synthase (IspS) is the sole enzyme in plants responsible for the yearly emission in the atmosphere of thousands of tonnes of the natural hydrocarbon isoprene worldwide. Species of the monocotyledonous family Arecaceae (palms) are among the highest plant emitters, but to date no IspS gene from this family has been identified. Here, we screened with PTR-ToF-MS 18 genera of the Arecaceae for isoprene emission and found that the majority of the sampled species emits isoprene. Putative IspS genes from six different genera were sequenced and three of them were functionally characterized by heterologous overexpression in Arabidopsis thaliana, demonstrating that they encode functional IspS genes. Site-directed mutagenesis and expression in Arabidopsis demonstrated the functional relevance of a novel IspS diagnostic tetrad from Arecaceae, whose most variable amino acids could not preserve catalytic function when substituted by a putatively dicotyledonous-specific tetrad. In particular, mutation of threonine 479 likely impairs the open-closed transition of the enzyme by altering the network of hydrogen bonds between helices H1α, H, and I. These results shed new light on the evolution of IspS in monocots, suggesting that isoprene emission is an ancestral trait within the Arecaceae family. The identification of IspS from Arecaceae provides promising novel enzymes for the production of isoprene in heterologous systems and allows the screening and selection of commercially relevant palm varieties with lower environmental impact.

Interspecific and intraspecific phenotypic diversity for drought adaptation in bioenergy Arundo species.

Biomass crops are commonly grown in low-grade land and selection of drought-tolerant accessions is of major importance to sustain productivity. In this work, we assess phenotypic variation under different environmental scenarios in a series of accessions of Arundo donax, and contrast it with two closely related species, Arundo donaciformis and Arundo plinii. Gas-exchange and stomatal anatomy analysis showed an elevated photosynthetic capacity in A. plinii compared to A. donax and A. donaciformis with a significant intraspecific variation in A. donax. The three species showed significantly contrasting behaviour of transpiration under developing water stress and increasing vapour pressure deficit (VPD), with A. donax being the most conservative while A. plinii showed an elevated degree of insensitivity to environmental cues. Under optimal conditions, A. donax had the highest estimated leaf area (projected leaf area) and plant dry weight although a significant reduction under water stress was observed for A. donax and A. donaciformis accessions while no differences were recorded for A. plinii between optimal growing conditions (well-watered [WW]) and reduced soil water availability (water-stressed [WS]). A. donax displayed a markedly conservative water use behaviour but elevated sensitivity of biomass accumulation under stress conditions. By contrast, in A. plinii, biomass and transpiration were largely insensitive to WS and increasing VPD, though biomass dry weight under optimal conditions was significantly lower than A. donax. We provide evidence of interspecific phenotypic variation within the Arundo genus while the intraspecific phenotypic plasticity may be exploited for further selection of superior clones under disadvantageous environmental conditions. The extensive trade-off between water use and biomass accumulation present in the three species under stress conditions provides a series of novel traits to be exploited in the selection of superior clones adapted to different environmental scenarios. Non-destructive approaches are provided to screen large populations for water-stress-tolerant A. donax clones.

Fuzzy support vector machine with joint optimization of genetic algorithm and fuzzy c-means.

BACKGROUND: Motor imagery electroencephalogram (MI-EEG) play an important role in the field of neurorehabilitation, and a fuzzy support vector machine (FSVM) is one of the most used classifiers. Specifically, a fuzzy c-means (FCM) algorithm was used to membership calculation to deal with the classification problems with outliers or noises. However, FCM is sensitive to its initial value and easily falls into local optima. OBJECTIVE: The joint optimization of genetic algorithm (GA) and FCM is proposed to enhance robustness of fuzzy memberships to initial cluster centers, yielding an improved FSVM (GF-FSVM). METHOD: The features of each channel of MI-EEG are extracted by the improved refined composite multivariate multiscale fuzzy entropy and fused to form a feature vector for a trial. Then, GA is employed to optimize the initial cluster center of FCM, and the fuzzy membership degrees are calculated through an iterative process and further applied to classify two-class MI-EEGs. RESULTS: Extensive experiments are conducted on two publicly available datasets, the average recognition accuracies achieve 99.89% and 98.81% and the corresponding kappa values are 0.9978 and 0.9762, respectively. CONCLUSION: The optimized cluster centers of FCM via GA are almost overlapping, showing great stability, and GF-FSVM obtains higher classification accuracies and higher consistency as well.

An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG.

Motor Imagery Electroencephalography (MI-EEG) has shown good prospects in neurorehabilitation, and the entropy-based nonlinear dynamic methods have been successfully applied to feature extraction of MI-EEG. Especially based on Multiscale Fuzzy Entropy (MFE), the fuzzy entropies of the τ coarse-grained sequences in τ scale are calculated and averaged to develop the Composite MFE (CMFE) with more feature information. However, the coarse-grained process fails to match the nonstationary characteristic of MI-EEG by a mean filtering algorithm. In this paper, CMFE is improved by assigning the different weight factors to the different sample points in the coarse-grained process, i.e., using the weighted mean filters instead of the original mean filters, which is conductive to signal filtering and feature extraction, and the resulting personalized Weighted CMFE (WCMFE) is more suitable to represent the nonstationary MI-EEG for different subjects. All the WCMFEs of multi-channel MI-EEG are fused in serial to construct the feature vector, which is evaluated by a back-propagation neural network. Based on a public dataset, extensive experiments are conducted, yielding a relatively higher classification accuracy by WCMFE, and the statistical significance is examined by two-sample t-test. The results suggest that WCMFE is superior to the other entropy-based and traditional feature extraction methods.