Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.A...In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.展开更多
To clarify the connotations and extensions of urban resilience,this study focuses on the Chengdu-Chongqing Economic Circle with 16 cities as research subjects.A comprehensive evaluation index system was constructed to...To clarify the connotations and extensions of urban resilience,this study focuses on the Chengdu-Chongqing Economic Circle with 16 cities as research subjects.A comprehensive evaluation index system was constructed to measure the resilience of each city from 2003 to 2020.The spatial-temporal evolution characteristics were analyzed using Kernel density estimation,standard deviation ellipse,and spatial Markov chain analysis,and the spatial Tobit model was introduced to discover the influencing factors.The results indicate the following:①Urban resilience in the Chengdu-Chongqing Economic Circle displays an upward trend,with the center of gravity moving to the southwest,and the polarization phenomenon intensifying.②The urban resilience level in a region has certain spatial and geographical dependence,while the probability of urban resilience transfer differs in adjacent cities with different resilience levels.③Urban centrality,economic scale,openness level,and financial development promote urban resilience,whereas government scale significantly inhibits it.Finally,this paper proposes countermeasures and suggestions to improve the urban resilience of the Chengdu-Chongqing Economic Circle.展开更多
The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries an...The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.展开更多
The spatial and temporal variation of green economic efficiency and its driving factors are of great significance for the construction of high-efficiency and low-consumption green development model and sustainable soc...The spatial and temporal variation of green economic efficiency and its driving factors are of great significance for the construction of high-efficiency and low-consumption green development model and sustainable socio-economic development.The research focused on the Yangtze River Economic Belt(YREB)and employed the miniumum distance to strong efficient frontier DEA(MinDs)model to measure the green economic efficiency of the municipalities in the region between 2008 and 2020.Then,the spatial autocorrelation model was used to analyze the evolution characteristics of its spatial pattern.Finally,Geodetector was applied to reveal the drivers and their interactions on green economic efficiency.It is found that:1)the overall green economic efficiency of the YREB from 2008 to 2020 shows a W-shaped fluctuating upward trend,green economic efficiency is greater in the downstream and smallest in the upstream;2)the spatial distribution of green economic efficiency shows clustering characteristics,with multi-core clustering based on‘city clusters-central cities'becoming more obvious over time;the High-High agglomeration type is mainly clustered in Jiangsu and Zheji-ang,while the Low-Low agglomeration type is clustered in the western Sichuan Plateau area and southwestern Yunnan;3)from input-output factors,whether it is the YREB as a whole or the upper,middle and lower reaches regions,the economic development level,labor input,and capital investment are the leading factors in the spatial-temporal evolution of green economic efficiency,with the com-prehensive influence of economic development level and pollution index being the most important interactive driving factor;4)from so-cio-economic factors,information technology drivers such as government intervention,transportation accessibility,information infra-structure,and Internet penetration are always high impact influencers and dominant interaction factors for green economic efficiency in the YREB and the three major regions in the upper,middle and lower reaches.Accordingly,the article puts forward relevant policy re-commendations in terms of formulating differentiated green transformation strategies,strengthening network leadership and informa-tion technology construction and coordinating multi-factor integrated development,which could provide useful reference for promoting synergistic green economic efficiency in the YREB.展开更多
Highly evolved granite is an important sign of the mature continent crust and closely associated with deposits of rare metals.In this work,the authors undertake systematically zircon U-Pb ages and whole rock elemental...Highly evolved granite is an important sign of the mature continent crust and closely associated with deposits of rare metals.In this work,the authors undertake systematically zircon U-Pb ages and whole rock elemental data for highly evolved granitic intrusions from the Great Xing’an Range(GXR),NE China,to elucidate their discriminant criteria,spatial-temporal distribution,differentiation and geodynamic mecha-nism.Geochemical data of these highly evolved granites suggest that high w(SiO_(2))(>70%)and differentiation index(DI>88)could be quantified indicators,while strong Eu depletion,high TE_(1,3),lowΣREE and low Zr/Hf,Nb/Ta,K/Rb could only be qualitative indicators.Zircon U-Pb ages suggest that the highly evolved gran-ites in the GXR were mainly formed in Late Mesozoic,which can be divided into two major stages:Late Ju-rassic-early Early Cretaceous(162-136 Ma,peak at 138 Ma),and late Early Cretaceous(136-106 Ma,peak at 126 Ma).The highly evolved granites are mainly distributed in the central-southern GXR,and display a weakly trend of getting younger from northwest to southeast,meanwhile indicating the metallogenic potential of rare metals within the central GXR.The spatial-temporal distribution,combined with regional geological data,indicates the highly evolved Mesozoic granites in the GXR were emplaced in an extensional environ-ment,of which the Late Jurassic-early Early Cretaceous extension was related to the closure of the Mongol-Okhotsk Ocean and roll-back of the Paleo-Pacific Plate,while the late Early Cretaceous extension was mainly related to the roll-back of the Paleo-Pacific Plate.展开更多
Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic...Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.展开更多
As an important river in the western part of Jilin Province,the lower reach of the Nenjiang River is an important wetland water source conservation area in Jilin Province.Within the watershed,it governs the Momoge Wet...As an important river in the western part of Jilin Province,the lower reach of the Nenjiang River is an important wetland water source conservation area in Jilin Province.Within the watershed,it governs the Momoge Wetland,the Xianghai Wetland,and the Danjiang Wetland in Jilin Province.The main problem in the lower reaches of the Nenjiang River is the uneven distribution of water resources in time and space,and the intensification of land salinization.Zhenlai County and Da an City in the Nenjiang River Basin have sufficient surface water resources,with surface water as the drinking water source.Baicheng City and Tongyu County have scarce surface water resources,and both use groundwater as their domestic water source.The main polluted section in the basin is the Xianghai Reservoir,and the annual water quality evaluation is Class V.However,the water quality of the Tao er River,the main stream of the Nenjiang River,is significantly better than that of the Xianghai Reservoir.In order to better study the water environmental pollution situation in the Nenjiang River basin,monitoring data from five sections of non seasonal rivers in the basin from 2012 to 2021 were selected for studying water quality.This in-depth exploration of the water pollution status and river water quality change trends in the Nenjiang River basin is of great significance for future rural development,agricultural pattern transformation,and the promotion of water ecological civilization construction.展开更多
In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Ela...In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Elatty E.Abd Elgawad Computers,Materials&Continua,2022,Vol.70,No.1,pp.1617–1630.DOI:10.32604/cmc.2022.018621,URL:https://www.techscience.com/cmc/v70n1/44361,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.展开更多
Solar flare prediction is an important subject in the field of space weather.Deep learning technology has greatly promoted the development of this subject.In this study,we propose a novel solar flare forecasting model...Solar flare prediction is an important subject in the field of space weather.Deep learning technology has greatly promoted the development of this subject.In this study,we propose a novel solar flare forecasting model integrating Deep Residual Network(ResNet)and Support Vector Machine(SVM)for both≥C-class(C,M,and X classes)and≥M-class(M and X classes)flares.We collected samples of magnetograms from May 1,2010 to September 13,2018 from Space-weather Helioseismic and Magnetic Imager(HMI)Active Region Patches and then used a cross-validation method to obtain seven independent data sets.We then utilized five metrics to evaluate our fusion model,based on intermediate-output extracted by ResNet and SVM using the Gaussian kernel function.Our results show that the primary metric true skill statistics(TSS)achieves a value of 0.708±0.027 for≥C-class prediction,and of 0.758±0.042 for≥M-class prediction;these values indicate that our approach performs significantly better than those of previous studies.The metrics of our fusion model’s performance on the seven datasets indicate that the model is quite stable and robust,suggesting that fusion models that integrate an excellent baseline network with SVM can achieve improved performance in solar flare prediction.Besides,we also discuss the performance impact of architectural innovation in our fusion model.展开更多
Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it cha...Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.展开更多
BACKGROUND Ependymoma with lipomatous differentiation is a rare type of ependymoma.The ZFTA fusion-positive supratentorial ependymoma is a novel tumor type in the 2021 World Health Organization classification of centr...BACKGROUND Ependymoma with lipomatous differentiation is a rare type of ependymoma.The ZFTA fusion-positive supratentorial ependymoma is a novel tumor type in the 2021 World Health Organization classification of central nervous system tumors.ZFTA fusion-positive lipomatous ependymoma has not been reported to date.CASE SUMMARY We reported a case of a 15-year-old Chinese male who had a sudden convulsion lasting approximately six minutes.Magnetic resonance imaging showed a round cystic shadow of approximately 1.9 cm×1.5 cm×1.9 cm under the right parieto-occipital cortex.Microscopic examination showed characteristic perivascular pseudorosettes and adipose differentiation in the cytoplasm.Immunohisto-chemical staining showed that the tumor cells were negative for cytokeratin,NeuN,Syn and p53,but positive for GFAP,vimentin and S-100 protein.Signi-ficant punctate intracytoplasmic EMA immunoreactivity was observed.The level of Ki-67 was about 5%.Genetic analysis revealed ZFTA:RELA fusion.A cranio-tomy with total excision of the tumor was performed.The follow-up time was 36 months,no evidence of disease recurrence was found in magnetic resonance imaging.CONCLUSION Based on these findings,the patient was diagnosed as a ependymoma with ZFTA fusion and lipomatous differentiation.This case report provides information on the microscopic morphological features of ependymoma with ZFTA fusion and lipomatous differentiation,which can help pathologists to make a definitive diagnosis of this tumor.展开更多
BACKGROUND The classification of uterine sarcomas is based on distinctive morphological and immunophenotypic characteristics,increasingly supported by molecular genetic diagnostics.Data on neurotrophic tyrosine recept...BACKGROUND The classification of uterine sarcomas is based on distinctive morphological and immunophenotypic characteristics,increasingly supported by molecular genetic diagnostics.Data on neurotrophic tyrosine receptor kinase(NTRK)gene fusionpositive uterine sarcoma,potentially aggressive and morphologically similar to fibrosarcoma,are limited due to its recent recognition.Pan-TRK immunohistochemistry(IHC)analysis serves as an effective screening tool with high sensitivity and specificity for NTRK-fusion malignancies.CASE SUMMARY We report a case of a malignant mesenchymal tumor originating from the uterine cervix,which was pan-TRK IHC-positive but lacked NTRK gene fusions,accompanied by a brief literature review.A 55-year-old woman presented to the emergency department with abdominal pain and distension,exhibiting significant ascites and multiple solid pelvic masses.Pelvic examination revealed a tumor encompassing the uterine cervix,extending to the vagina and uterine corpus.A punch biopsy of the cervix indicated NTRK sarcoma with positive immunochemical pan-TRK stain.However,subsequent next generation sequencing revealed no NTRK gene fusion,leading to a diagnosis of poorly differentiated,advanced-stage sarcoma.CONCLUSION The clinical significance of NTRK gene fusion lies in potential treatment with TRK inhibitors for positive sarcomas.Identifying such rare tumors is crucial due to the potential applicability of tropomyosin receptor kinase inhibitor treatment.展开更多
Successful polyethylene glycol fusion(PEG-fusion)of severed axons following peripheral nerve injuries for PEG-fused axons has been reported to:(1)rapidly restore electrophysiological continuity;(2)prevent distal Walle...Successful polyethylene glycol fusion(PEG-fusion)of severed axons following peripheral nerve injuries for PEG-fused axons has been reported to:(1)rapidly restore electrophysiological continuity;(2)prevent distal Wallerian Degeneration and maintain their myelin sheaths;(3)promote primarily motor,voluntary behavioral recoveries as assessed by the Sciatic Functional Index;and,(4)rapidly produce correct and incorrect connections in many possible combinations that produce rapid and extensive recovery of functional peripheral nervous system/central nervous system connections and reflex(e.g.,toe twitch)or voluntary behaviors.The preceding companion paper describes sensory terminal field reo rganization following PEG-fusion repair of sciatic nerve transections or ablations;howeve r,sensory behavioral recovery has not been explicitly explored following PEG-fusion repair.In the current study,we confirmed the success of PEG-fusion surgeries according to criteria(1-3)above and more extensively investigated whether PEG-fusion enhanced mechanical nociceptive recovery following sciatic transection in male and female outbred Sprague-Dawley and inbred Lewis rats.Mechanical nociceptive responses were assessed by measuring withdrawal thresholds using von Frey filaments on the dorsal and midplantar regions of the hindpaws.Dorsal von Frey filament tests were a more reliable method than plantar von Frey filament tests to assess mechanical nociceptive sensitivity following sciatic nerve transections.Baseline withdrawal thresholds of the sciatic-mediated lateral dorsal region differed significantly across strain but not sex.Withdrawal thresholds did not change significantly from baseline in chronic Unoperated and Sham-operated rats.Following sciatic transection,all rats exhibited severe hyposensitivity to stimuli at the lateral dorsal region of the hindpaw ipsilateral to the injury.However,PEG-fused rats exhibited significantly earlier return to baseline withdrawal thresholds than Negative Control rats.Furthermore,PEG-fused rats with significantly improved Sciatic Functional Index scores at or after 4 weeks postoperatively exhibited yet-earlier von Frey filament recove ry compared with those without Sciatic Functional Index recovery,suggesting a correlation between successful PEG-fusion and both motor-dominant and sensory-dominant behavioral recoveries.This correlation was independent of the sex or strain of the rat.Furthermore,our data showed that the acceleration of von Frey filament sensory recovery to baseline was solely due to the PEG-fused sciatic nerve and not saphenous nerve collateral outgrowths.No chronic hypersensitivity developed in any rat up to 12 weeks.All these data suggest that PEG-fusion repair of transection peripheral nerve injuries co uld have important clinical benefits.展开更多
Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and t...Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and the modality fusion approach tends to be too simple,often neglecting modality alignment before fusion.This research introduces a novel dual stream multimodal alignment and fusion network named DMAFNet for classifying short videos.The network uses two unimodal encoder modules to extract features within modalities and exploits a multimodal encoder module to learn interaction between modalities.To solve the modality alignment problem,contrastive learning is introduced between two unimodal encoder modules.Additionally,masked language modeling(MLM)and video text matching(VTM)auxiliary tasks are introduced to improve the interaction between video frames and text modalities through backpropagation of loss functions.Diverse experiments prove the efficiency of DMAFNet in multimodal video classification tasks.Compared with other two mainstream baselines,DMAFNet achieves the best results on the 2022 WeChat Big Data Challenge dataset.展开更多
Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feat...Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.展开更多
In this editorial,the authors of this paper comment on the article by Bokov et al published in the recent issue of World Journal of Orthopedics.We reviewed a general overview of oblique lumbar interbody fusions(OLIF)a...In this editorial,the authors of this paper comment on the article by Bokov et al published in the recent issue of World Journal of Orthopedics.We reviewed a general overview of oblique lumbar interbody fusions(OLIF)and lateral lumbar interbody fusions(LLIF),their indications and complications as an increasingly popular minimally invasive technique to address several lumbar pathologies.This editorial thoroughly discusses and reviews the literature regarding factors affecting outcomes of indirect decompression utilized through OLIF and LLIF procedures.Several parameters play a critical role in patient outcomes including restoration of disc height,foraminal height,central canal squared,and foraminal area.The indirect decompression allows for unbuckling of the ligamentum flavum which can significantly decompress the neural elements as well as aid in reduction of spondylolisthesis.However,the authors further highlight the limitations of indirect decompression and factors that may predict unsuccessful outcomes including bony foraminal stenosis,severe central canal stenosis,and osteoporosis.As a result,failure of indirect decompression can lead to persistent pain,radiculopathy and unsatisfied patients.Spinal surgeons may be left to reimage patients and consider additional procedures with direct decompression.展开更多
With the rise of encrypted traffic,traditional network analysis methods have become less effective,leading to a shift towards deep learning-based approaches.Among these,multimodal learning-based classification methods...With the rise of encrypted traffic,traditional network analysis methods have become less effective,leading to a shift towards deep learning-based approaches.Among these,multimodal learning-based classification methods have gained attention due to their ability to leverage diverse feature sets from encrypted traffic,improving classification accuracy.However,existing research predominantly relies on late fusion techniques,which hinder the full utilization of deep features within the data.To address this limitation,we propose a novel multimodal encrypted traffic classification model that synchronizes modality fusion with multiscale feature extraction.Specifically,our approach performs real-time fusion of modalities at each stage of feature extraction,enhancing feature representation at each level and preserving inter-level correlations for more effective learning.This continuous fusion strategy improves the model’s ability to detect subtle variations in encrypted traffic,while boosting its robustness and adaptability to evolving network conditions.Experimental results on two real-world encrypted traffic datasets demonstrate that our method achieves a classification accuracy of 98.23% and 97.63%,outperforming existing multimodal learning-based methods.展开更多
Based on the Skyrme energy density functional and reaction Q-value,this study proposed an effective nucleus-nucleus poten-tial for describing the capture barrier in heavy-ion fusion processes.The 443 extracted barrier...Based on the Skyrme energy density functional and reaction Q-value,this study proposed an effective nucleus-nucleus poten-tial for describing the capture barrier in heavy-ion fusion processes.The 443 extracted barrier heights were well reproduced with a root-mean-square(RMS)error of 1.53 MeV,and the RMS deviations with respect to 144 time-dependent Hartree-Fock capture barrier heights were only 1.05 MeV.Coupled with the Siwek-Wilczyński formula,wherein three parameters were determined by the proposed effective potentials,the measured capture cross sections at energies around the barriers were reasonably well reproduced for several fusion reactions induced by nearly spherical nuclei as well as by nuclei with large deformations,such as^(154)Sm and^(238)U.The shallow capture pockets and small values of the average barrier radii resulted in the reduction of the capture cross sections for 52,54Cr-and 64 Ni-induced reactions,which were related to the synthesis of new super-heavy nuclei.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金This work is partly supported by the National Key Research and Development Program of China(Grant No.2020YFB1805403)the National Natural Science Foundation of China(Grant No.62032002)the 111 Project(Grant No.B21049).
文摘In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.
基金supported by the Graduate Research and Innovation Project of Chongqing Normal University[Grant No.YKC23035],comprehensive evaluation,and driving factors of urban resilience in the Chengdu-Chongqing Economic Circle.
文摘To clarify the connotations and extensions of urban resilience,this study focuses on the Chengdu-Chongqing Economic Circle with 16 cities as research subjects.A comprehensive evaluation index system was constructed to measure the resilience of each city from 2003 to 2020.The spatial-temporal evolution characteristics were analyzed using Kernel density estimation,standard deviation ellipse,and spatial Markov chain analysis,and the spatial Tobit model was introduced to discover the influencing factors.The results indicate the following:①Urban resilience in the Chengdu-Chongqing Economic Circle displays an upward trend,with the center of gravity moving to the southwest,and the polarization phenomenon intensifying.②The urban resilience level in a region has certain spatial and geographical dependence,while the probability of urban resilience transfer differs in adjacent cities with different resilience levels.③Urban centrality,economic scale,openness level,and financial development promote urban resilience,whereas government scale significantly inhibits it.Finally,this paper proposes countermeasures and suggestions to improve the urban resilience of the Chengdu-Chongqing Economic Circle.
基金supported by the China Scholarship Council and the CERNET Innovation Project under grant No.20170111.
文摘The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.
基金Under the auspices of the National Natural Science Foundation of China(No.71974070)‘CUG Scholar'Scientific Research Funds at China University of Geosciences(Wuhan)(No.2022005)。
文摘The spatial and temporal variation of green economic efficiency and its driving factors are of great significance for the construction of high-efficiency and low-consumption green development model and sustainable socio-economic development.The research focused on the Yangtze River Economic Belt(YREB)and employed the miniumum distance to strong efficient frontier DEA(MinDs)model to measure the green economic efficiency of the municipalities in the region between 2008 and 2020.Then,the spatial autocorrelation model was used to analyze the evolution characteristics of its spatial pattern.Finally,Geodetector was applied to reveal the drivers and their interactions on green economic efficiency.It is found that:1)the overall green economic efficiency of the YREB from 2008 to 2020 shows a W-shaped fluctuating upward trend,green economic efficiency is greater in the downstream and smallest in the upstream;2)the spatial distribution of green economic efficiency shows clustering characteristics,with multi-core clustering based on‘city clusters-central cities'becoming more obvious over time;the High-High agglomeration type is mainly clustered in Jiangsu and Zheji-ang,while the Low-Low agglomeration type is clustered in the western Sichuan Plateau area and southwestern Yunnan;3)from input-output factors,whether it is the YREB as a whole or the upper,middle and lower reaches regions,the economic development level,labor input,and capital investment are the leading factors in the spatial-temporal evolution of green economic efficiency,with the com-prehensive influence of economic development level and pollution index being the most important interactive driving factor;4)from so-cio-economic factors,information technology drivers such as government intervention,transportation accessibility,information infra-structure,and Internet penetration are always high impact influencers and dominant interaction factors for green economic efficiency in the YREB and the three major regions in the upper,middle and lower reaches.Accordingly,the article puts forward relevant policy re-commendations in terms of formulating differentiated green transformation strategies,strengthening network leadership and informa-tion technology construction and coordinating multi-factor integrated development,which could provide useful reference for promoting synergistic green economic efficiency in the YREB.
基金Supported by projects of the National Natural Science Foundation of China(Nos.92062216,41888101).
文摘Highly evolved granite is an important sign of the mature continent crust and closely associated with deposits of rare metals.In this work,the authors undertake systematically zircon U-Pb ages and whole rock elemental data for highly evolved granitic intrusions from the Great Xing’an Range(GXR),NE China,to elucidate their discriminant criteria,spatial-temporal distribution,differentiation and geodynamic mecha-nism.Geochemical data of these highly evolved granites suggest that high w(SiO_(2))(>70%)and differentiation index(DI>88)could be quantified indicators,while strong Eu depletion,high TE_(1,3),lowΣREE and low Zr/Hf,Nb/Ta,K/Rb could only be qualitative indicators.Zircon U-Pb ages suggest that the highly evolved gran-ites in the GXR were mainly formed in Late Mesozoic,which can be divided into two major stages:Late Ju-rassic-early Early Cretaceous(162-136 Ma,peak at 138 Ma),and late Early Cretaceous(136-106 Ma,peak at 126 Ma).The highly evolved granites are mainly distributed in the central-southern GXR,and display a weakly trend of getting younger from northwest to southeast,meanwhile indicating the metallogenic potential of rare metals within the central GXR.The spatial-temporal distribution,combined with regional geological data,indicates the highly evolved Mesozoic granites in the GXR were emplaced in an extensional environ-ment,of which the Late Jurassic-early Early Cretaceous extension was related to the closure of the Mongol-Okhotsk Ocean and roll-back of the Paleo-Pacific Plate,while the late Early Cretaceous extension was mainly related to the roll-back of the Paleo-Pacific Plate.
基金the National Natural Science Foundation of China(No.61461027,61762059)the Provincial Science and Technology Program supported the Key Project of Natural Science Foundation of Gansu Province(No.22JR5RA226)。
文摘Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.
文摘As an important river in the western part of Jilin Province,the lower reach of the Nenjiang River is an important wetland water source conservation area in Jilin Province.Within the watershed,it governs the Momoge Wetland,the Xianghai Wetland,and the Danjiang Wetland in Jilin Province.The main problem in the lower reaches of the Nenjiang River is the uneven distribution of water resources in time and space,and the intensification of land salinization.Zhenlai County and Da an City in the Nenjiang River Basin have sufficient surface water resources,with surface water as the drinking water source.Baicheng City and Tongyu County have scarce surface water resources,and both use groundwater as their domestic water source.The main polluted section in the basin is the Xianghai Reservoir,and the annual water quality evaluation is Class V.However,the water quality of the Tao er River,the main stream of the Nenjiang River,is significantly better than that of the Xianghai Reservoir.In order to better study the water environmental pollution situation in the Nenjiang River basin,monitoring data from five sections of non seasonal rivers in the basin from 2012 to 2021 were selected for studying water quality.This in-depth exploration of the water pollution status and river water quality change trends in the Nenjiang River basin is of great significance for future rural development,agricultural pattern transformation,and the promotion of water ecological civilization construction.
文摘In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed A.El-Meligy,Mohamed Sharaf,Abd Elatty E.Abd Elgawad Computers,Materials&Continua,2022,Vol.70,No.1,pp.1617–1630.DOI:10.32604/cmc.2022.018621,URL:https://www.techscience.com/cmc/v70n1/44361,there was an error regarding the affiliation for the author Hafiz Tayyab Rauf.Instead of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.
基金supported by the National Key R&D Program of China (Grant No.2022YFF0503700)the National Natural Science Foundation of China (42074196, 41925018)
文摘Solar flare prediction is an important subject in the field of space weather.Deep learning technology has greatly promoted the development of this subject.In this study,we propose a novel solar flare forecasting model integrating Deep Residual Network(ResNet)and Support Vector Machine(SVM)for both≥C-class(C,M,and X classes)and≥M-class(M and X classes)flares.We collected samples of magnetograms from May 1,2010 to September 13,2018 from Space-weather Helioseismic and Magnetic Imager(HMI)Active Region Patches and then used a cross-validation method to obtain seven independent data sets.We then utilized five metrics to evaluate our fusion model,based on intermediate-output extracted by ResNet and SVM using the Gaussian kernel function.Our results show that the primary metric true skill statistics(TSS)achieves a value of 0.708±0.027 for≥C-class prediction,and of 0.758±0.042 for≥M-class prediction;these values indicate that our approach performs significantly better than those of previous studies.The metrics of our fusion model’s performance on the seven datasets indicate that the model is quite stable and robust,suggesting that fusion models that integrate an excellent baseline network with SVM can achieve improved performance in solar flare prediction.Besides,we also discuss the performance impact of architectural innovation in our fusion model.
基金supported in part by the National Natural Science Foundation of China under Grants 62463002,62062021 and 62473033in part by the Guiyang Scientific Plan Project[2023]48–11,in part by QKHZYD[2023]010 Guizhou Province Science and Technology Innovation Base Construction Project“Key Laboratory Construction of Intelligent Mountain Agricultural Equipment”.
文摘Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.
文摘BACKGROUND Ependymoma with lipomatous differentiation is a rare type of ependymoma.The ZFTA fusion-positive supratentorial ependymoma is a novel tumor type in the 2021 World Health Organization classification of central nervous system tumors.ZFTA fusion-positive lipomatous ependymoma has not been reported to date.CASE SUMMARY We reported a case of a 15-year-old Chinese male who had a sudden convulsion lasting approximately six minutes.Magnetic resonance imaging showed a round cystic shadow of approximately 1.9 cm×1.5 cm×1.9 cm under the right parieto-occipital cortex.Microscopic examination showed characteristic perivascular pseudorosettes and adipose differentiation in the cytoplasm.Immunohisto-chemical staining showed that the tumor cells were negative for cytokeratin,NeuN,Syn and p53,but positive for GFAP,vimentin and S-100 protein.Signi-ficant punctate intracytoplasmic EMA immunoreactivity was observed.The level of Ki-67 was about 5%.Genetic analysis revealed ZFTA:RELA fusion.A cranio-tomy with total excision of the tumor was performed.The follow-up time was 36 months,no evidence of disease recurrence was found in magnetic resonance imaging.CONCLUSION Based on these findings,the patient was diagnosed as a ependymoma with ZFTA fusion and lipomatous differentiation.This case report provides information on the microscopic morphological features of ependymoma with ZFTA fusion and lipomatous differentiation,which can help pathologists to make a definitive diagnosis of this tumor.
基金Supported by Grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute,funded by the Ministry of Health&Welfare,Republic of Korea,No.RS-2022-KH129889.
文摘BACKGROUND The classification of uterine sarcomas is based on distinctive morphological and immunophenotypic characteristics,increasingly supported by molecular genetic diagnostics.Data on neurotrophic tyrosine receptor kinase(NTRK)gene fusionpositive uterine sarcoma,potentially aggressive and morphologically similar to fibrosarcoma,are limited due to its recent recognition.Pan-TRK immunohistochemistry(IHC)analysis serves as an effective screening tool with high sensitivity and specificity for NTRK-fusion malignancies.CASE SUMMARY We report a case of a malignant mesenchymal tumor originating from the uterine cervix,which was pan-TRK IHC-positive but lacked NTRK gene fusions,accompanied by a brief literature review.A 55-year-old woman presented to the emergency department with abdominal pain and distension,exhibiting significant ascites and multiple solid pelvic masses.Pelvic examination revealed a tumor encompassing the uterine cervix,extending to the vagina and uterine corpus.A punch biopsy of the cervix indicated NTRK sarcoma with positive immunochemical pan-TRK stain.However,subsequent next generation sequencing revealed no NTRK gene fusion,leading to a diagnosis of poorly differentiated,advanced-stage sarcoma.CONCLUSION The clinical significance of NTRK gene fusion lies in potential treatment with TRK inhibitors for positive sarcomas.Identifying such rare tumors is crucial due to the potential applicability of tropomyosin receptor kinase inhibitor treatment.
基金supported by DOD AFIRMⅢW81XWH-20-2-0029 subcontract,UT POC19-1774-13Neuraptive Therapeutics Inc.26-7724-56+1 种基金NIH R01-NS128086 grantsLone Star Paralysis gift(to GDB)。
文摘Successful polyethylene glycol fusion(PEG-fusion)of severed axons following peripheral nerve injuries for PEG-fused axons has been reported to:(1)rapidly restore electrophysiological continuity;(2)prevent distal Wallerian Degeneration and maintain their myelin sheaths;(3)promote primarily motor,voluntary behavioral recoveries as assessed by the Sciatic Functional Index;and,(4)rapidly produce correct and incorrect connections in many possible combinations that produce rapid and extensive recovery of functional peripheral nervous system/central nervous system connections and reflex(e.g.,toe twitch)or voluntary behaviors.The preceding companion paper describes sensory terminal field reo rganization following PEG-fusion repair of sciatic nerve transections or ablations;howeve r,sensory behavioral recovery has not been explicitly explored following PEG-fusion repair.In the current study,we confirmed the success of PEG-fusion surgeries according to criteria(1-3)above and more extensively investigated whether PEG-fusion enhanced mechanical nociceptive recovery following sciatic transection in male and female outbred Sprague-Dawley and inbred Lewis rats.Mechanical nociceptive responses were assessed by measuring withdrawal thresholds using von Frey filaments on the dorsal and midplantar regions of the hindpaws.Dorsal von Frey filament tests were a more reliable method than plantar von Frey filament tests to assess mechanical nociceptive sensitivity following sciatic nerve transections.Baseline withdrawal thresholds of the sciatic-mediated lateral dorsal region differed significantly across strain but not sex.Withdrawal thresholds did not change significantly from baseline in chronic Unoperated and Sham-operated rats.Following sciatic transection,all rats exhibited severe hyposensitivity to stimuli at the lateral dorsal region of the hindpaw ipsilateral to the injury.However,PEG-fused rats exhibited significantly earlier return to baseline withdrawal thresholds than Negative Control rats.Furthermore,PEG-fused rats with significantly improved Sciatic Functional Index scores at or after 4 weeks postoperatively exhibited yet-earlier von Frey filament recove ry compared with those without Sciatic Functional Index recovery,suggesting a correlation between successful PEG-fusion and both motor-dominant and sensory-dominant behavioral recoveries.This correlation was independent of the sex or strain of the rat.Furthermore,our data showed that the acceleration of von Frey filament sensory recovery to baseline was solely due to the PEG-fused sciatic nerve and not saphenous nerve collateral outgrowths.No chronic hypersensitivity developed in any rat up to 12 weeks.All these data suggest that PEG-fusion repair of transection peripheral nerve injuries co uld have important clinical benefits.
基金Fundamental Research Funds for the Central Universities,China(No.2232021A-10)National Natural Science Foundation of China(No.61903078)+1 种基金Shanghai Sailing Program,China(No.22YF1401300)Natural Science Foundation of Shanghai,China(No.20ZR1400400)。
文摘Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and the modality fusion approach tends to be too simple,often neglecting modality alignment before fusion.This research introduces a novel dual stream multimodal alignment and fusion network named DMAFNet for classifying short videos.The network uses two unimodal encoder modules to extract features within modalities and exploits a multimodal encoder module to learn interaction between modalities.To solve the modality alignment problem,contrastive learning is introduced between two unimodal encoder modules.Additionally,masked language modeling(MLM)and video text matching(VTM)auxiliary tasks are introduced to improve the interaction between video frames and text modalities through backpropagation of loss functions.Diverse experiments prove the efficiency of DMAFNet in multimodal video classification tasks.Compared with other two mainstream baselines,DMAFNet achieves the best results on the 2022 WeChat Big Data Challenge dataset.
基金supported by the National Natural Science Foundation of China(62302167,62477013)Natural Science Foundation of Shanghai(No.24ZR1456100)+1 种基金Science and Technology Commission of Shanghai Municipality(No.24DZ2305900)the Shanghai Municipal Special Fund for Promoting High-Quality Development of Industries(2211106).
文摘Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.
文摘In this editorial,the authors of this paper comment on the article by Bokov et al published in the recent issue of World Journal of Orthopedics.We reviewed a general overview of oblique lumbar interbody fusions(OLIF)and lateral lumbar interbody fusions(LLIF),their indications and complications as an increasingly popular minimally invasive technique to address several lumbar pathologies.This editorial thoroughly discusses and reviews the literature regarding factors affecting outcomes of indirect decompression utilized through OLIF and LLIF procedures.Several parameters play a critical role in patient outcomes including restoration of disc height,foraminal height,central canal squared,and foraminal area.The indirect decompression allows for unbuckling of the ligamentum flavum which can significantly decompress the neural elements as well as aid in reduction of spondylolisthesis.However,the authors further highlight the limitations of indirect decompression and factors that may predict unsuccessful outcomes including bony foraminal stenosis,severe central canal stenosis,and osteoporosis.As a result,failure of indirect decompression can lead to persistent pain,radiculopathy and unsatisfied patients.Spinal surgeons may be left to reimage patients and consider additional procedures with direct decompression.
基金supported by the National Key Research and Development Program of China No.2023YFB2705000.
文摘With the rise of encrypted traffic,traditional network analysis methods have become less effective,leading to a shift towards deep learning-based approaches.Among these,multimodal learning-based classification methods have gained attention due to their ability to leverage diverse feature sets from encrypted traffic,improving classification accuracy.However,existing research predominantly relies on late fusion techniques,which hinder the full utilization of deep features within the data.To address this limitation,we propose a novel multimodal encrypted traffic classification model that synchronizes modality fusion with multiscale feature extraction.Specifically,our approach performs real-time fusion of modalities at each stage of feature extraction,enhancing feature representation at each level and preserving inter-level correlations for more effective learning.This continuous fusion strategy improves the model’s ability to detect subtle variations in encrypted traffic,while boosting its robustness and adaptability to evolving network conditions.Experimental results on two real-world encrypted traffic datasets demonstrate that our method achieves a classification accuracy of 98.23% and 97.63%,outperforming existing multimodal learning-based methods.
基金supported by the National Natural Science Foundation of China(Nos.12265006,12375129,U1867212)the Innovation Project of Guangxi Graduate Education(No.YCSWYCSW2022176)the Guangxi Natural Science Foundation(2017GXNSFGA198001).
文摘Based on the Skyrme energy density functional and reaction Q-value,this study proposed an effective nucleus-nucleus poten-tial for describing the capture barrier in heavy-ion fusion processes.The 443 extracted barrier heights were well reproduced with a root-mean-square(RMS)error of 1.53 MeV,and the RMS deviations with respect to 144 time-dependent Hartree-Fock capture barrier heights were only 1.05 MeV.Coupled with the Siwek-Wilczyński formula,wherein three parameters were determined by the proposed effective potentials,the measured capture cross sections at energies around the barriers were reasonably well reproduced for several fusion reactions induced by nearly spherical nuclei as well as by nuclei with large deformations,such as^(154)Sm and^(238)U.The shallow capture pockets and small values of the average barrier radii resulted in the reduction of the capture cross sections for 52,54Cr-and 64 Ni-induced reactions,which were related to the synthesis of new super-heavy nuclei.
