Tree allometry responses to competition and complementarity in mixed-species plantations of Betula alnoides

Tree allometry plays a crucial role in tree survival,stability,and timber quantity and quality of mixed-species plantations.However,the responses of tree allometry to resource utilisation within the framework of interspecific competition and complementarity remain poorly understood.Taking into consideration strong-and weakspace competition(SC and WC),as well as N_(2)-fixing and non-N_(2)-fixing tree species(FN and nFN),a mixedspecies planting trial was conducted for Betula alnoides,a pioneer tree species,which was separately mixed with Acacia melanoxylon(SC+FN),Erythrophleum fordii(WC+FN),Eucalyptus cloeziana(SC+nFN)and Pinus kesiya var.langbianensis(WC+nFN)in southern China.Six years after planting,tree growth,total nitrogen(N)and carbon(C)contents,and the natural abundances of^(15)N and^(13)C in the leaves were measured for each species,and the mycorrhizal colonisation rates of B.alnoides were investigated under each treatment.Allometric variations and their relationships with space competition and nutrient-related factors were analyzed.The results showed a consistent effect of space competition on the height-diameter relationship of B.alnoides in mixtures with FN or nFN.The tree height growth of B.alnoides was significantly promoted under high space competition,and growth in diameter at breast height(DBH),tree height and crown size were all expedited in mixtures with FN.The symbiotic relationship between ectomycorrhizal fungi and B.alnoides was significantly influenced by both space competition and N_(2) fixation by the accompanying tree species,whereas such significant effects were absent for arbuscular mycorrhizal fungi.Furthermore,high space competition significantly decreased the water use efficiency(WUE)of B.alnoides,and its N use efficiency(NUE)was much lower in the FN mixtures.Structural equation modeling further demonstrated that the stem allometry of B.alnoides was affected by its NUE and WUE via changes in its height growth,and crown allometry was influenced by the mycorrhizal symbiotic relationship.Our findings provide new insights into the mechanisms driving tree allometric responses to above-and belowground resource competition and complementarity in mixed-species plantations,which are instructive for the establishment of mixed-species plantations.

Algorithm of Helmet Wearing Detection Based on AT-YOLO Deep Mode

The existing safety helmet detection methods are mainly based on one-stage object detection algorithms with high detection speed to reach the real-time detection requirements,but they can’t accurately detect small objects and objects with obstructions.Therefore,we propose a helmet detection algorithm based on the attention mechanism(AT-YOLO).First of all,a channel attention module is added to the YOLOv3 backbone network,which can adaptively calibrate the channel features of the direction to improve the feature utilization,and a spatial attention module is added to the neck of the YOLOv3 network to capture the correlation between any positions in the feature map so that to increase the receptive field of the network.Secondly,we use DIoU(Distance Intersection over Union)bounding box regression loss function,it not only improving the measurement of bounding box regression loss but also increases the normalized distance loss between the prediction boxes and the target boxes,which makes the network more accurate in detecting small objects and faster in convergence.Finally,we explore the training strategy of the network model,which improves network performance without increasing the inference cost.Experiments show that the mAP of the proposed method reaches 96.5%,and the detection speed can reach 27 fps.Compared with other existing methods,it has better performance in detection accuracy and speed.

Automatic Detection of Aortic Dissection Based on Morphology and Deep Learning

Aortic dissection(AD)is a kind of acute and rapidly progressing cardiovascular disease.In this work,we build a CTA image library with 88 CT cases,43 cases of aortic dissection and 45 cases of health.An aortic dissection detection method based on CTA images is proposed.ROI is extracted based on binarization and morphology opening operation.The deep learning networks(InceptionV3,ResNet50,and DenseNet)are applied after the preprocessing of the datasets.Recall,F1-score,Matthews correlation coefficient(MCC)and other performance indexes are investigated.It is shown that the deep learning methods have much better performance than the traditional method.And among those deep learning methods,DenseNet121 can exceed other networks such as ResNet50 and InceptionV3.

Population and conservation status of a transboundary group of black snub-nosed monkeys(Rhinopithecus strykeri)between China and Myanmar

DEAR EDITOR,We examined the distribution,population,and conservation status of the critically endangered Myanmar or black snub-nosed monkey(Rhinopithecus strykeri)via field surveys over 26 months(2019-2021)in the Pianma region of the China-Myanmar border.Contrary to previous reports,we only identified one group in the region,which was a cross-border group occupying a multi-year home range of 51.50-57.02 km^(2).The current group size was much larger(155-160 individuals)than that in 2012-2014(ca 100 individuals),and the group appeared to be growing.However,confirmed poaching,mining,and transboundary forest fires on the Myanmar side of the border threaten their survival.

Progress on Molecular Mechanism of Aluminum Resistance in Rice

Aluminum(Al)toxicity in acid soils is a significant limitation to crop production worldwide,as 13%of the world's rice is produced in acid soil with high Al content.Rice is likely the most Al-resistant cereal and also the cereal,where Al resistance is the most genetically complex with external detoxification and internal tolerance.Many Al-resistance genes in rice have been cloned,including Al resistance transcription factor 1(ART1)and other transcription factors,organic acid transporter genes,and metal ion transporter gene.This review summarized the recent characterized genes affecting Al tolerance in rice and the interrelationships between Al and other plant nutrients.

Energetics and electronic structure of refractory elements in the dislocation of NiAl

Using DMol and the discrete variational method within the framework of the density functional theory, we study the alloying effects of Nb, Ti, and V in the [100] （010） edge dislocation core of NiAl. We find that when Nb （Ti, V） is substituted for Al in the center-Al, the binding energy of the system reduces 3.00 eV （2.98 eV, 2.66 eV）. When Nb （Ti, V） is substituted for Ni in the center-Ni, the binding energy of the system reduces only 0.47 eV （0.16 eV, 0.09 eV）. This shows that Nb （Ti, V） exhibits a strong Al site preference, which agrees with the experimental and other theoretical results. The analyses of the charge distribution, the interatomic energy and the partial density of states show that some charge accumulations appear between the impurity atom and Ni atoms, and the strong bonding states are formed between impurity atom and neighbouring host atoms due mainly to the hybridization of 4d5s（3d4s） orbitals of impurity atoms and 3d4s4p orbitals of host Ni atoms. The impurity induces a strong pinning effect on the [100] （010） edge dislocation motion in NiAl, which is related to the mechanical properties of the NiAl alloy.

Risk Prediction of Aortic Dissection Operation Based on Boosting Trees

During the COVID-19 pandemic,the treatment of aortic dissection has faced additional challenges.The necessary medical resources are in serious shortage,and the preoperative waiting time has been significantly prolonged due to the requirement to test for COVID-19 infection.In this work,we focus on the risk prediction of aortic dissection surgery under the influence of the COVID-19 pandemic.A general scheme of medical data processing is proposed,which includes five modules,namely problem definition,data preprocessing,data mining,result analysis,and knowledge application.Based on effective data preprocessing,feature analysis and boosting trees,our proposed fusion decision model can obtain 100%accuracy for early postoperative mortality prediction,which outperforms machine learning methods based on a single model such as LightGBM,XGBoost,and CatBoost.The results reveal the critical factors related to the postoperative mortality of aortic dissection,which can provide a theoretical basis for the formulation of clinical operation plans and help to effectively avoid risks in advance.

Four new species of the Cimbicidae(Hymenoptera:Tenthredinoidea)from China

Four new species of the Cimbicidae from China are described:Abia jimeii Yan&Wei sp.nov.,Zaraea zhui Yan&Wei sp.nov.,Leptocimbex nigrotegularis Yan&Wei sp.nov.,and Corynis zhengi Yan&Wei sp.nov.A key to all extant Holarctic genera of Cimbicidae is provided.

强化木地板的色差及其控制

分析了强化木地板在生产过程中因原纸色差、浸胶工艺匹配不稳定、表面模板的纹理及光泽度差异等造成的产品色差问题,并阐述了强化木地板色差的判定及控制方法。

News Text Topic Clustering Optimized Method Based on TF-IDF Algorithm on Spark

Due to the slow processing speed of text topic clustering in stand-alone architecture under the background of big data,this paper takes news text as the research object and proposes LDA text topic clustering algorithm based on Spark big data platform.Since the TF-IDF(term frequency-inverse document frequency)algorithm under Spark is irreversible to word mapping,the mapped words indexes cannot be traced back to the original words.In this paper,an optimized method is proposed that TF-IDF under Spark to ensure the text words can be restored.Firstly,the text feature is extracted by the TF-IDF algorithm combined CountVectorizer proposed in this paper,and then the features are inputted to the LDA(Latent Dirichlet Allocation)topic model for training.Finally,the text topic clustering is obtained.Experimental results show that for large data samples,the processing speed of LDA topic model clustering has been improved based Spark.At the same time,compared with the LDA topic model based on word frequency input,the model proposed in this paper has a reduction of perplexity.

An Improved Deep Fusion CNN for Image Recognition

With the development of Deep Convolutional Neural Networks(DCNNs),the extracted features for image recognition tasks have shifted from low-level features to the high-level semantic features of DCNNs.Previous studies have shown that the deeper the network is,the more abstract the features are.However,the recognition ability of deep features would be limited by insufficient training samples.To address this problem,this paper derives an improved Deep Fusion Convolutional Neural Network(DF-Net)which can make full use of the differences and complementarities during network learning and enhance feature expression under the condition of limited datasets.Specifically,DF-Net organizes two identical subnets to extract features from the input image in parallel,and then a well-designed fusion module is introduced to the deep layer of DF-Net to fuse the subnet’s features in multi-scale.Thus,the more complex mappings are created and the more abundant and accurate fusion features can be extracted to improve recognition accuracy.Furthermore,a corresponding training strategy is also proposed to speed up the convergence and reduce the computation overhead of network training.Finally,DF-Nets based on the well-known ResNet,DenseNet and MobileNetV2 are evaluated on CIFAR100,Stanford Dogs,and UECFOOD-100.Theoretical analysis and experimental results strongly demonstrate that DF-Net enhances the performance of DCNNs and increases the accuracy of image recognition.

A Novel Combinational Convolutional Neural Network for Automatic Food-Ingredient Classification

With the development of deep learning and Convolutional Neural Networks(CNNs),the accuracy of automatic food recognition based on visual data have significantly improved.Some research studies have shown that the deeper the model is,the higher the accuracy is.However,very deep neural networks would be affected by the overfitting problem and also consume huge computing resources.In this paper,a new classification scheme is proposed for automatic food-ingredient recognition based on deep learning.We construct an up-to-date combinational convolutional neural network(CBNet)with a subnet merging technique.Firstly,two different neural networks are utilized for learning interested features.Then,a well-designed feature fusion component aggregates the features from subnetworks,further extracting richer and more precise features for image classification.In order to learn more complementary features,the corresponding fusion strategies are also proposed,including auxiliary classifiers and hyperparameters setting.Finally,CBNet based on the well-known VGGNet,ResNet and DenseNet is evaluated on a dataset including 41 major categories of food ingredients and 100 images for each category.Theoretical analysis and experimental results demonstrate that CBNet achieves promising accuracy for multi-class classification and improves the performance of convolutional neural networks.

AF-Net:A Medical Image Segmentation Network Based on Attention Mechanism and Feature Fusion

Medical image segmentation is an important application field of computer vision in medical image processing.Due to the close location and high similarity of different organs in medical images,the current segmentation algorithms have problems with mis-segmentation and poor edge segmentation.To address these challenges,we propose a medical image segmentation network(AF-Net)based on attention mechanism and feature fusion,which can effectively capture global information while focusing the network on the object area.In this approach,we add dual attention blocks(DA-block)to the backbone network,which comprises parallel channels and spatial attention branches,to adaptively calibrate and weigh features.Secondly,the multi-scale feature fusion block(MFF-block)is proposed to obtain feature maps of different receptive domains and get multi-scale information with less computational consumption.Finally,to restore the locations and shapes of organs,we adopt the global feature fusion blocks(GFF-block)to fuse high-level and low-level information,which can obtain accurate pixel positioning.We evaluate our method on multiple datasets(the aorta and lungs dataset),and the experimental results achieve 94.0%in mIoU and 96.3%in DICE,showing that our approach performs better than U-Net and other state-of-art methods.

Coverless Image Steganography Based on Image Segmentation

To resist the risk of the stego-image being maliciously altered during transmission,we propose a coverless image steganography method based on image segmentation.Most existing coverless steganography methods are based on whole feature mapping,which has poor robustness when facing geometric attacks,because the contents in the image are easy to lost.To solve this problem,we use ResNet to extract semantic features,and segment the object areas from the image through Mask RCNN for information hiding.These selected object areas have ethical structural integrity and are not located in the visual center of the image,reducing the information loss of malicious attacks.Then,these object areas will be binarized to generate hash sequences for information mapping.In transmission,only a set of stego-images unrelated to the secret information are transmitted,so it can fundamentally resist steganalysis.At the same time,since both Mask RCNN and ResNet have excellent robustness,pre-training the model through supervised learning can achieve good performance.The robust hash algorithm can also resist attacks during transmission.Although image segmentation will reduce the capacity,multiple object areas can be extracted from an image to ensure the capacity to a certain extent.Experimental results show that compared with other coverless image steganography methods,our method is more robust when facing geometric attacks.

An Encrypted Image Retrieval Method Based on SimHash in Cloud Computing

With the massive growth of images data and the rise of cloud computing that can provide cheap storage space and convenient access,more and more users store data in cloud server.However,how to quickly query the expected data with privacy-preserving is still a challenging in the encryption image data retrieval.Towards this goal,this paper proposes a ciphertext image retrieval method based on SimHash in cloud computing.Firstly,we extract local feature of images,and then cluster the features by K-means.Based on it,the visual word codebook is introduced to represent feature information of images,which hashes the codebook to the corresponding fingerprint.Finally,the image feature vector is generated by SimHash searchable encryption feature algorithm for similarity retrieval.Extensive experiments on two public datasets validate the effectiveness of our method.Besides,the proposed method outperforms one popular searchable encryption,and the results are competitive to the state-of-the-art.

Feature Fusion Multi-View Hashing Based on Random Kernel Canonical Correlation Analysis

Hashing technology has the advantages of reducing data storage and improving the efficiency of the learning system,making it more and more widely used in image retrieval.Multi-view data describes image information more comprehensively than traditional methods using a single-view.How to use hashing to combine multi-view data for image retrieval is still a challenge.In this paper,a multi-view fusion hashing method based on RKCCA(Random Kernel Canonical Correlation Analysis)is proposed.In order to describe image content more accurately,we use deep learning dense convolutional network feature DenseNet to construct multi-view by combining GIST feature or BoW_SIFT(Bag-of-Words model+SIFT feature)feature.This algorithm uses RKCCA method to fuse multi-view features to construct association features and apply them to image retrieval.The algorithm generates binary hash code with minimal distortion error by designing quantization regularization terms.A large number of experiments on benchmark datasets show that this method is superior to other multi-view hashing methods.

Privacy Protection for Medical Images Based on DenseNet and Coverless Steganography

With the development of the internet of medical things(IoMT),the privacy protection problem has become more and more critical.In this paper,we propose a privacy protection scheme for medical images based on DenseNet and coverless steganography.For a given group of medical images of one patient,DenseNet is used to regroup the images based on feature similarity comparison.Then the mapping indexes can be constructed based on LBP feature and hash generation.After mapping the privacy information with the hash sequences,the corresponding mapped indexes of secret information will be packed together with the medical images group and released to the authorized user.The user can extract the privacy information successfully with a similar method of feature analysis and index construction.The simulation results show good performance of robustness.And the hiding success rate also shows good feasibility and practicability for application.Since the medical images are kept original without embedding and modification,the performance of crack resistance is outstanding and can keep better quality for diagnosis compared with traditional schemes with data embedding.

Adaptive Median Filtering Algorithm Based on Divide and Conquer and Its Application in CAPTCHA Recognition

As the first barrier to protect cyberspace,the CAPTCHA has made significant contributions to maintaining Internet security and preventing malicious attacks.By researching the CAPTCHA,we can find its vulnerability and improve the security of CAPTCHA.Recently,many studies have shown that improving the image preprocessing effect of the CAPTCHA,which can achieve a better recognition rate by the state-of-theart machine learning algorithms.There are many kinds of noise and distortion in the CAPTCHA images of this experiment.We propose an adaptive median filtering algorithm based on divide and conquer in this paper.Firstly,the filtering window data quickly sorted by the data correlation,which can greatly improve the filtering efficiency.Secondly,the size of the filtering window is adaptively adjusted according to the noise density.As demonstrated in the experimental results,the proposed scheme can achieve superior performance compared with the conventional median filter.The algorithm can not only effectively detect the noise and remove it,but also has a good effect in preservation details.Therefore,this algorithm can be one of the most strong tools for various CAPTCHA image recognition and related applications.

C:N:P stoichiometry of Ericaceae species in shrubland biomes across Southern China:influences of climate,soil and species identity

Aims Carbon(C),nitrogen(N)and phosphorus(P)stoichiometry strongly affect functions and nutrient cycling within ecosystems.However,the related researches in shrubs were very limited.In this study,we aimed to inves-tigate leaf stoichiometry and its driving factors in shrubs,and whether stoichiometry significantly differs among closely related species.Methods We analyzed leaf C,N and P concentrations and their ratios in 32 species of Ericaceae from 161 sites across southern China.We examined the relationships of leaf stoichiometry with environmen-tal variables using linear regressions,and quantified the interactive and independent effects of climate,soil and species on foliar stoi-chiometry using general linear models(GLM).Important Findings The foliar C,N and P contents of Ericaceae were 484.66,14.44 and 1.06 mg g−1,respectively.Leaf C,N and P concentrations and their ratios in Ericaceae were significantly related with latitude and altitude,except the N:P insignificantly correlated with latitude.Climate(mean annual temperature and precipitation)and soil properties(soil C,N and P and bulk density)were significantly influenced element stoichiom-etry.The GLM analysis showed that soil exerted a greater direct effect on leaf stoichiometry than climate did,and climate affected leaf traits mainly via indirect ways.Further,soil properties had stronger influ-ences on leaf P than on leaf C and N.Among all independent factors examined,we found species accounted for the largest proportion of the variation in foliar stoichiometry.These results suggest that species can largely influence foliar stoichiometry,even at a lower taxonomic level.

Ceratopteris chunii and Ceratopteris chingii(Pteridaceae),two new diploid species from China,based on morphological,cytological,and molecular data

Understanding how natural hybridization and polyploidizations originate in plants requires identifying potential diploid ancestors.However,cryptic plant species are widespread,particularly in Ceratopteris(Pteridaceae).Identifying Ceratopteris cryptic species with different polyploidy levels is a challenge because Ceratopteris spp.exhibit high degrees of phenotypic plasticity.Here,two new cryptic species of Ceratopteris,Ceratopteris chunii and Ceratopteris chingii,are described and illustrated.Phylogenetic analyses reveal that each of the new species form a well-supported clade.C.chunii and C.chingii are similar to Ceratopteris gaudichaudii var.vulgaris and C.pteridoides,respectively,but distinct from their relatives in the stipe,basal pinna of the sterile leaf or subelliptic shape of the fertile leaf,as well as the spore surface.In addition,chromosome studies indicate that C.chunii and C.chingii are both diploid.These findings will help us further understand the origin of Ceratopteris polyploids in Asia.