Long-termpetroleum production forecasting is essential for the effective development andmanagement of oilfields.Due to its ability to extract complex patterns,deep learning has gained popularity for production forecas...Long-termpetroleum production forecasting is essential for the effective development andmanagement of oilfields.Due to its ability to extract complex patterns,deep learning has gained popularity for production forecasting.However,existing deep learning models frequently overlook the selective utilization of information from other production wells,resulting in suboptimal performance in long-term production forecasting across multiple wells.To achieve accurate long-term petroleum production forecast,we propose a spatial-geological perception graph convolutional neural network(SGP-GCN)that accounts for the temporal,spatial,and geological dependencies inherent in petroleum production.Utilizing the attention mechanism,the SGP-GCN effectively captures intricate correlations within production and geological data,forming the representations of each production well.Based on the spatial distances and geological feature correlations,we construct a spatial-geological matrix as the weight matrix to enable differential utilization of information from other wells.Additionally,a matrix sparsification algorithm based on production clustering(SPC)is also proposed to optimize the weight distribution within the spatial-geological matrix,thereby enhancing long-term forecasting performance.Empirical evaluations have shown that the SGP-GCN outperforms existing deep learning models,such as CNN-LSTM-SA,in long-term petroleum production forecasting.This demonstrates the potential of the SGP-GCN as a valuable tool for long-term petroleum production forecasting across multiple wells.展开更多
Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim ...Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim to offer a platform for the rapid dissemination of signifi cant,novel,and high-impact research in the fi elds of agricultural product processing science,technology,engineering,and nutrition.Additionally,supplemental issues are curated and published to facilitate in-depth discussions on special topics.展开更多
We propose a novel fast numerical calculation method for the Rayleigh-Sommerfeld diffraction integral,which is developed based on the existing scaled convolution method.This approach enables fast cal-culations for gen...We propose a novel fast numerical calculation method for the Rayleigh-Sommerfeld diffraction integral,which is developed based on the existing scaled convolution method.This approach enables fast cal-culations for general cases of off-axis scenarios where the sampling intervals and numbers of the input and observation planes are unequal.Additionally,it allows for arbitrary adjustment of the sampling interval of the impulse response function,facilitating a manual trade-off between computational load and accuracy.The er-rors associated with this method,which is equivalent to interpolation,primarily arise from the discontinuities of the sampling matrix of the impulse response function on its boundaries of periodic extension.To address this issue,we propose the concept of the padding function and its construction method,and evaluate its ef-fectiveness in enhancing computational accuracy.The feasibility of the proposed method is verified by nu-merical simulation and compared with the direct integration DI-method in a simplified scenario.It shows that the proposed method has good computational accuracy for the general case where the sampling interval of the input and observation plane is not equal under non-near-field diffraction,and when the diffraction distance is large,although the computational accuracy of the proposed method cannot exceed that of the DI-method,the computational amount can be significantly reduced with almost no effect on the computational accuracy.This method provides a general numerical calculation scheme of diffraction in the non-near field case for areas such as computational holography.展开更多
The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adver...The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adversarial network(GAN)algorithm was proposed.Taking GAN as the basic framework,it combined a depthwise separable convolution module,attention mechanism,and reconstructed convolution module to realize the enhancement of underwater degraded images.Multi-scale features were captured by the depthwise separable convolution module,and the attention mechanism was utilized to enhance attention to important features.The reconstructed convolution module further extracts and fuses local and global features.Experimental results showed that the algorithm performs well in improving the color bias and blurring of underwater images,with PSNR reaching 27.835,SSIM reaching 0.883,UIQM reaching 3.205,and UCIQE reaching 0.713.The enhanced image outperforms the comparison algorithm in both subjective and objective metrics.展开更多
Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim ...Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim to offer a platform for the rapid dissemination of significant,novel,and high-impact research in the fields of agricultural product processing science,technology,engineering,and nutrition.Additionally,supplemental issues are curated and published to facilitate in-depth discussions on special topics.展开更多
This paper deals with the global boundedness of a two-competing-species chemotaxis model with indirect signal production in a three-dimensional bounded domain.The current work extends prior results by ZHENG et al.(202...This paper deals with the global boundedness of a two-competing-species chemotaxis model with indirect signal production in a three-dimensional bounded domain.The current work extends prior results by ZHENG et al.(2022)who established global existence and boundedness of classical solution under the parameter constraintsµ_(1)µ_(2)a_(2)≥χ1(4+µ_(2)^(2)a _(2)^(2)),µ_(1)µ_(2)a_(1)≥χ2(4+µ_(1)^(2)a_(1)^( 2)).Our main contribution demonstrates that these technical conditions can be significantly relaxed toµ1≥5χ_(1),µ2≥5χ_(2),thereby expanding the admissible parameter space for solution boundedness.展开更多
Two[FeFe]-hydrogenase compounds with 2-cyanobenzyl groups,{Fe_(2)[(SCH_(2)CH_(3))(SR)](CO)_(6)}(1 or 1′,which are the crystalline states from petroleum ether and dichloromethane solution,respectively)and{Fe_(2)[(SCH_...Two[FeFe]-hydrogenase compounds with 2-cyanobenzyl groups,{Fe_(2)[(SCH_(2)CH_(3))(SR)](CO)_(6)}(1 or 1′,which are the crystalline states from petroleum ether and dichloromethane solution,respectively)and{Fe_(2)[(SCH_(2)CH_(3))(SR)](CO)_(5)(PPh_(3))}(2)(R=2-cyanobenzyl),were synthesized and characterized by infrared spectroscopy,UV-Vis spectroscopy,single-crystal diffraction,powder X-ray diffraction,etc.Their performances as photocatalysts for H_(2)production through water splitting were evaluated.The results showed that 316.8μmol of H_(2)was produced on compound 1 after 3 h of illumination,with a catalytic efficiency of 25.1μmol·mg^(-1)·h^(-1)and a turnover number(TON)of 36.8.The replacement of carbonyl with PPh3 could significantly improve the catalytic performance of the complex,and 705.0μmol of H_(2)was produced on 2 after 3 h of illumination,with a catalytic efficiency of 37.9μmol·mg^(-1)·h^(-1)and a TON of 81.8.CCDC:2515700,1;2515702,1′;2515701,2.展开更多
A dynamic graph(DG)is adopted to portray the evolving interplay between nodes in real-world scenarios prevalently.A high-order graph convolutional network(HGCN)is equipped with the ability to represent a DG by the spa...A dynamic graph(DG)is adopted to portray the evolving interplay between nodes in real-world scenarios prevalently.A high-order graph convolutional network(HGCN)is equipped with the ability to represent a DG by the spatial-temporal message passing mechanism built on tensor product.Concretely,an HGCN utilizes the discrete Fourier transform(DFT)to implement temporal message passing and then employs face-wise product to realize spatial message passing.However,DFT is only a special case of assorted time-frequency transforms,which considers the complex temporal patterns partially,thereby resulting in an inaccurate temporal message passing possibly.To address this issue,this study proposes six advanced time-frequency transform-incorporated HGCNs(TF-HGCNs)with discrete Fourier,discrete Hartley,discrete cosine,Haar wavelet,Walsh Hadamard,and slant transforms.In addition,a potent ensemble is built regarding the proposed six TF-HGCNs as the bases.Finally,the corresponding theoretical proof is presented.Empirical studies on six DG datasets demonstrate that owing to diverse time-frequency transforms,the proposed six TF-HGCNs significantly outperform state-of-the-art models in addressing the task of link weight estimation.Moreover,their ensemble outstrips each base's performance.展开更多
In response to the global energy crisis and environmental challenges,photocatalytic hydrogen(H_(2))production has emerged as a sustainable alternative toward clean energy conversion.Among diverse photocatalysts invest...In response to the global energy crisis and environmental challenges,photocatalytic hydrogen(H_(2))production has emerged as a sustainable alternative toward clean energy conversion.Among diverse photocatalysts investigated,TiO_(2)-based nanomaterials have attracted significant attention due to their unique physicochemical properties,such as high chemical stability,strong redox capacity and tunable electronic structures,along with high cost-effectiveness.Extensive research on TiO_(2)-based photocatalysts proves their enormous potential in the field of H2 production.This timely and critical review explores the recent advances in TiO_(2)-based photocatalysts,discussing their distinctive advantages and synthesis methods in photocatalytic H2 production.Modification strategies,such as elemental doping(e.g.,precious metals,non-precious metals and non-metals),morphology engineering and composite formation,are summarised to improve photocatalytic efficiency.Advanced in/ex situ characterization techniques employed to probe photocatalytic mechanisms are also highlighted.Finally,major challenges,such as limited visible-light activity and charge recombination,are outlined,with perspectives on emerging TiO_(2)-based nanomaterials and design strategies to overcome current bottlenecks.And the research focus in the future is prospected,such as atomic interface engineering,machine learning auxiliary material design and large-scale preparation technology.This work aims to provide insights into the rational design of TiO_(2)-based photocatalysts for next-generation H2 production systems.展开更多
Fatigue impacts both mental and physical health,significantly reducing quality of life and daily productivity.Natural bioactive compounds have emerged as promising agents to combat fatigue due to their multifaceted bi...Fatigue impacts both mental and physical health,significantly reducing quality of life and daily productivity.Natural bioactive compounds have emerged as promising agents to combat fatigue due to their multifaceted biological activities and minimal side effects.Key mechanisms through which these compounds exert anti-fatigue effects include enhancing energy metabolism,reducing oxidative stress,supporting mitochondrial integrity,modulating the immune response,and regulating neurotransmitter balance.Plant-derived metabolites such as flavonoids,ginsenosides,saponins,and polysaccharides,as well as animal-based peptides and microbial-derived substances,have demonstrated significant potential in alleviating fatigue symptoms in both clinical and preclinical studies.Additionally,fermented products like kefir,fermented rice bran,and yogurt enhance endurance performance,reduce lactate buildup,and improve glycogen storage,further contributing to fatigue mitigation.As consumer interest in natural alternatives grows,future research should prioritize improving the bioavailability,stability,and targeted delivery of these compounds.This review consolidates recent advances in the understanding of anti-fatigue mechanisms of natural products and highlights emerging directions for their development as functional foods and therapeutic agents.展开更多
Dear Editor,D2This letter presents a node feature similarity preserving graph convolutional framework P G.Graph neural networks(GNNs)have garnered significant attention for their efficacy in learning graph representat...Dear Editor,D2This letter presents a node feature similarity preserving graph convolutional framework P G.Graph neural networks(GNNs)have garnered significant attention for their efficacy in learning graph representations across diverse real-world applications.展开更多
Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating In...Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.展开更多
Viral infections play a crucial role in marine biogeochemical cycles,by regulating bacterial mortality and mediating nutrient and carbon fluxes.However,despite of their ecological significance,existing climate change ...Viral infections play a crucial role in marine biogeochemical cycles,by regulating bacterial mortality and mediating nutrient and carbon fluxes.However,despite of their ecological significance,existing climate change models generally fail to incorporate virus-mediated ecological processes due to the current limited understanding of marine viral dynamics under global warming.While numerous studies have explored the effect of warming for viral decay and production,how temperature regulates the total abundance of marine viruses remains unclear.In this study,we conducted year-round measurements of viral production and decay rates in Qingdao's coastal waters,with additional experimental warming treatments.The result showed that under in-situ temperature,the viral decay and production rate displayed distinct seasonal variations.With the exception of summer,elevated temperature stimulated both viral decay rate and production rate,and further improved the net viral production rate.While in summer,the net viral production rate turned negative,implying divergent threshold viral decay and viral production rate on warming.Our study deepens the understanding of the effect of global warming on marine viruses and provides scientific data for climate change models.展开更多
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in...In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.展开更多
Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-...Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.展开更多
Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient im...Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient image captioning model named Mob-IMWTC,which integrates improved wavelet convolution(IMWTC)with an enhanced MobileNet V3 architecture.The enhanced MobileNet V3 integrates a transformer encoder as its encoding module and a transformer decoder as its decoding module.This innovative neural network significantly reduces the memory space required and model training time,while maintaining a high level of accuracy in generating image descriptions.IMWTC facilitates large receptive fields without significantly increasing the number of parameters or computational overhead.The improvedMobileNet V3 model has its classifier removed,and simultaneously,it employs IMWTC layers to replace the original convolutional layers.This makes Mob-IMWTC exceptionally well-suited for deployment on lowresource devices.Experimental results,based on objective evaluation metrics such as BLEU,ROUGE,CIDEr,METEOR,and SPICE,demonstrate that Mob-IMWTC outperforms state-of-the-art models,including three CNN architectures(CNN-LSTM,CNN-Att-LSTM,CNN-Tran),two mainstream methods(LCM-Captioner,ClipCap),and our previous work(Mob-Tran).Subjective evaluations further validate the model’s superiority in terms of grammaticality,adequacy,logic,readability,and humanness.Mob-IMWTC offers a lightweight yet effective solution for image captioning,making it suitable for deployment on resource-constrained devices.展开更多
Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural n...Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural network(CNN)based methods,in which class activation mapping(CAM)is proposed to obtain the pseudo labels,and only concentrates on the most discriminative parts.Recently,transformer-based methods utilize attention map from the multi-headed self-attention(MHSA)module to predict pseudo labels,which usually contain obvious background noise and incoherent object area.To solve the above problems,we use the Conformer as our backbone,which is a parallel network based on convolutional neural network(CNN)and Transformer.The two branches generate pseudo labels and refine them independently,and can effectively combine the advantages of CNN and Transformer.However,the parallel structure is not close enough in the information communication.Thus,parallel structure can result in poor details about pseudo labels,and the background noise still exists.To alleviate this problem,we propose enhancing convolution CAM(ECCAM)model,which have three improved modules based on enhancing convolution,including deeper stem(DStem),convolutional feed-forward network(CFFN)and feature coupling unit with convolution(FCUConv).The ECCAM could make Conformer have tighter interaction between CNN and Transformer branches.After experimental verification,the improved modules we propose can help the network perceive more local information from images,making the final segmentation results more refined.Compared with similar architecture,our modules greatly improve the semantic segmentation performance and achieve70.2%mean intersection over union(mIoU)on the PASCAL VOC 2012 dataset.展开更多
Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empir...Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.展开更多
The development of brain-computer interfaces(BCI)based on motor imagery(MI)has greatly improved patients’quality of life with movement disorders.The classification of upper limb MI has been widely studied and applied...The development of brain-computer interfaces(BCI)based on motor imagery(MI)has greatly improved patients’quality of life with movement disorders.The classification of upper limb MI has been widely studied and applied in many fields,including rehabilitation.However,the physiological representations of left and right lower limb movements are too close and activated deep in the cerebral cortex,making it difficult to distinguish their features.Therefore,classifying lower limbs motor imagery is more challenging.In this study,we propose a feature extraction method based on functional connectivity,which utilizes phase-locked values to construct a functional connectivity matrix as the features of the left and right legs,which can effectively avoid the problem of physiological representations of the left and right lower limbs being too close to each other during movement.In addition,considering the topology and the temporal characteristics of the electroencephalogram(EEG),we designed a temporal-spatial convolutional network(TSGCN)to capture the spatiotemporal information for classification.Experimental results show that the accuracy of the proposed method is higher than that of existing methods,achieving an average classification accuracy of 73.58%on the internal dataset.Finally,this study explains the network mechanism of left and right foot MI from the perspective of graph theoretic features and demonstrates the feasibility of decoding lower limb MI.展开更多
基金funded by National Natural Science Foundation of China,grant number 62071491.
文摘Long-termpetroleum production forecasting is essential for the effective development andmanagement of oilfields.Due to its ability to extract complex patterns,deep learning has gained popularity for production forecasting.However,existing deep learning models frequently overlook the selective utilization of information from other production wells,resulting in suboptimal performance in long-term production forecasting across multiple wells.To achieve accurate long-term petroleum production forecast,we propose a spatial-geological perception graph convolutional neural network(SGP-GCN)that accounts for the temporal,spatial,and geological dependencies inherent in petroleum production.Utilizing the attention mechanism,the SGP-GCN effectively captures intricate correlations within production and geological data,forming the representations of each production well.Based on the spatial distances and geological feature correlations,we construct a spatial-geological matrix as the weight matrix to enable differential utilization of information from other wells.Additionally,a matrix sparsification algorithm based on production clustering(SPC)is also proposed to optimize the weight distribution within the spatial-geological matrix,thereby enhancing long-term forecasting performance.Empirical evaluations have shown that the SGP-GCN outperforms existing deep learning models,such as CNN-LSTM-SA,in long-term petroleum production forecasting.This demonstrates the potential of the SGP-GCN as a valuable tool for long-term petroleum production forecasting across multiple wells.
文摘Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim to offer a platform for the rapid dissemination of signifi cant,novel,and high-impact research in the fi elds of agricultural product processing science,technology,engineering,and nutrition.Additionally,supplemental issues are curated and published to facilitate in-depth discussions on special topics.
文摘We propose a novel fast numerical calculation method for the Rayleigh-Sommerfeld diffraction integral,which is developed based on the existing scaled convolution method.This approach enables fast cal-culations for general cases of off-axis scenarios where the sampling intervals and numbers of the input and observation planes are unequal.Additionally,it allows for arbitrary adjustment of the sampling interval of the impulse response function,facilitating a manual trade-off between computational load and accuracy.The er-rors associated with this method,which is equivalent to interpolation,primarily arise from the discontinuities of the sampling matrix of the impulse response function on its boundaries of periodic extension.To address this issue,we propose the concept of the padding function and its construction method,and evaluate its ef-fectiveness in enhancing computational accuracy.The feasibility of the proposed method is verified by nu-merical simulation and compared with the direct integration DI-method in a simplified scenario.It shows that the proposed method has good computational accuracy for the general case where the sampling interval of the input and observation plane is not equal under non-near-field diffraction,and when the diffraction distance is large,although the computational accuracy of the proposed method cannot exceed that of the DI-method,the computational amount can be significantly reduced with almost no effect on the computational accuracy.This method provides a general numerical calculation scheme of diffraction in the non-near field case for areas such as computational holography.
文摘The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adversarial network(GAN)algorithm was proposed.Taking GAN as the basic framework,it combined a depthwise separable convolution module,attention mechanism,and reconstructed convolution module to realize the enhancement of underwater degraded images.Multi-scale features were captured by the depthwise separable convolution module,and the attention mechanism was utilized to enhance attention to important features.The reconstructed convolution module further extracts and fuses local and global features.Experimental results showed that the algorithm performs well in improving the color bias and blurring of underwater images,with PSNR reaching 27.835,SSIM reaching 0.883,UIQM reaching 3.205,and UCIQE reaching 0.713.The enhanced image outperforms the comparison algorithm in both subjective and objective metrics.
文摘Agricultural Products Processing and Storage(ISSN 3059-4510,Owner:Hunan Academy of Agricultural Sciences,China.Production and hosting:Springer Nature)is an international,peer-reviewed open access journal with the aim to offer a platform for the rapid dissemination of significant,novel,and high-impact research in the fields of agricultural product processing science,technology,engineering,and nutrition.Additionally,supplemental issues are curated and published to facilitate in-depth discussions on special topics.
基金Supported by the National Natural Science Foundation of China(12301631)the Natural Science Foundation of Qinghai Province(2023-ZJ-949Q)。
文摘This paper deals with the global boundedness of a two-competing-species chemotaxis model with indirect signal production in a three-dimensional bounded domain.The current work extends prior results by ZHENG et al.(2022)who established global existence and boundedness of classical solution under the parameter constraintsµ_(1)µ_(2)a_(2)≥χ1(4+µ_(2)^(2)a _(2)^(2)),µ_(1)µ_(2)a_(1)≥χ2(4+µ_(1)^(2)a_(1)^( 2)).Our main contribution demonstrates that these technical conditions can be significantly relaxed toµ1≥5χ_(1),µ2≥5χ_(2),thereby expanding the admissible parameter space for solution boundedness.
文摘Two[FeFe]-hydrogenase compounds with 2-cyanobenzyl groups,{Fe_(2)[(SCH_(2)CH_(3))(SR)](CO)_(6)}(1 or 1′,which are the crystalline states from petroleum ether and dichloromethane solution,respectively)and{Fe_(2)[(SCH_(2)CH_(3))(SR)](CO)_(5)(PPh_(3))}(2)(R=2-cyanobenzyl),were synthesized and characterized by infrared spectroscopy,UV-Vis spectroscopy,single-crystal diffraction,powder X-ray diffraction,etc.Their performances as photocatalysts for H_(2)production through water splitting were evaluated.The results showed that 316.8μmol of H_(2)was produced on compound 1 after 3 h of illumination,with a catalytic efficiency of 25.1μmol·mg^(-1)·h^(-1)and a turnover number(TON)of 36.8.The replacement of carbonyl with PPh3 could significantly improve the catalytic performance of the complex,and 705.0μmol of H_(2)was produced on 2 after 3 h of illumination,with a catalytic efficiency of 37.9μmol·mg^(-1)·h^(-1)and a TON of 81.8.CCDC:2515700,1;2515702,1′;2515701,2.
基金supported in part by the National Natural Science Foundation of China(62372385,62272078,62002337)Chongqing Natural Science Foundation(CSTB2022NSCQ-MSX1486,CSTB2023NSCQ-LZX0069)。
文摘A dynamic graph(DG)is adopted to portray the evolving interplay between nodes in real-world scenarios prevalently.A high-order graph convolutional network(HGCN)is equipped with the ability to represent a DG by the spatial-temporal message passing mechanism built on tensor product.Concretely,an HGCN utilizes the discrete Fourier transform(DFT)to implement temporal message passing and then employs face-wise product to realize spatial message passing.However,DFT is only a special case of assorted time-frequency transforms,which considers the complex temporal patterns partially,thereby resulting in an inaccurate temporal message passing possibly.To address this issue,this study proposes six advanced time-frequency transform-incorporated HGCNs(TF-HGCNs)with discrete Fourier,discrete Hartley,discrete cosine,Haar wavelet,Walsh Hadamard,and slant transforms.In addition,a potent ensemble is built regarding the proposed six TF-HGCNs as the bases.Finally,the corresponding theoretical proof is presented.Empirical studies on six DG datasets demonstrate that owing to diverse time-frequency transforms,the proposed six TF-HGCNs significantly outperform state-of-the-art models in addressing the task of link weight estimation.Moreover,their ensemble outstrips each base's performance.
文摘In response to the global energy crisis and environmental challenges,photocatalytic hydrogen(H_(2))production has emerged as a sustainable alternative toward clean energy conversion.Among diverse photocatalysts investigated,TiO_(2)-based nanomaterials have attracted significant attention due to their unique physicochemical properties,such as high chemical stability,strong redox capacity and tunable electronic structures,along with high cost-effectiveness.Extensive research on TiO_(2)-based photocatalysts proves their enormous potential in the field of H2 production.This timely and critical review explores the recent advances in TiO_(2)-based photocatalysts,discussing their distinctive advantages and synthesis methods in photocatalytic H2 production.Modification strategies,such as elemental doping(e.g.,precious metals,non-precious metals and non-metals),morphology engineering and composite formation,are summarised to improve photocatalytic efficiency.Advanced in/ex situ characterization techniques employed to probe photocatalytic mechanisms are also highlighted.Finally,major challenges,such as limited visible-light activity and charge recombination,are outlined,with perspectives on emerging TiO_(2)-based nanomaterials and design strategies to overcome current bottlenecks.And the research focus in the future is prospected,such as atomic interface engineering,machine learning auxiliary material design and large-scale preparation technology.This work aims to provide insights into the rational design of TiO_(2)-based photocatalysts for next-generation H2 production systems.
基金supported by Guangdong Higher Education Upgrading Plan(2021-2025)with No.of UICR0400015-24 and UICR0400016-24 at Beijing Normal-Hong Kong Baptist University,Zhuhai,China.
文摘Fatigue impacts both mental and physical health,significantly reducing quality of life and daily productivity.Natural bioactive compounds have emerged as promising agents to combat fatigue due to their multifaceted biological activities and minimal side effects.Key mechanisms through which these compounds exert anti-fatigue effects include enhancing energy metabolism,reducing oxidative stress,supporting mitochondrial integrity,modulating the immune response,and regulating neurotransmitter balance.Plant-derived metabolites such as flavonoids,ginsenosides,saponins,and polysaccharides,as well as animal-based peptides and microbial-derived substances,have demonstrated significant potential in alleviating fatigue symptoms in both clinical and preclinical studies.Additionally,fermented products like kefir,fermented rice bran,and yogurt enhance endurance performance,reduce lactate buildup,and improve glycogen storage,further contributing to fatigue mitigation.As consumer interest in natural alternatives grows,future research should prioritize improving the bioavailability,stability,and targeted delivery of these compounds.This review consolidates recent advances in the understanding of anti-fatigue mechanisms of natural products and highlights emerging directions for their development as functional foods and therapeutic agents.
基金supported by the National Natural Science Foundation of China(62402399)the New Chongqing Youth Innovation Talent Project(CSTB2024NSCQ-QCXMX0035)。
文摘Dear Editor,D2This letter presents a node feature similarity preserving graph convolutional framework P G.Graph neural networks(GNNs)have garnered significant attention for their efficacy in learning graph representations across diverse real-world applications.
文摘Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(No.42276108)the Young Scientists Fund of Shandong Provincial Natural Science Foundation(No.ZR2022QD052)。
文摘Viral infections play a crucial role in marine biogeochemical cycles,by regulating bacterial mortality and mediating nutrient and carbon fluxes.However,despite of their ecological significance,existing climate change models generally fail to incorporate virus-mediated ecological processes due to the current limited understanding of marine viral dynamics under global warming.While numerous studies have explored the effect of warming for viral decay and production,how temperature regulates the total abundance of marine viruses remains unclear.In this study,we conducted year-round measurements of viral production and decay rates in Qingdao's coastal waters,with additional experimental warming treatments.The result showed that under in-situ temperature,the viral decay and production rate displayed distinct seasonal variations.With the exception of summer,elevated temperature stimulated both viral decay rate and production rate,and further improved the net viral production rate.While in summer,the net viral production rate turned negative,implying divergent threshold viral decay and viral production rate on warming.Our study deepens the understanding of the effect of global warming on marine viruses and provides scientific data for climate change models.
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
文摘In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.
基金supported,in part,by the National Nature Science Foundation of China under Grant 62272236,62376128in part,by the Natural Science Foundation of Jiangsu Province under Grant BK20201136,BK20191401.
文摘Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.
基金funded by National Social Science Fund of China,grant number 23BYY197.
文摘Image captioning,a pivotal research area at the intersection of image understanding,artificial intelligence,and linguistics,aims to generate natural language descriptions for images.This paper proposes an efficient image captioning model named Mob-IMWTC,which integrates improved wavelet convolution(IMWTC)with an enhanced MobileNet V3 architecture.The enhanced MobileNet V3 integrates a transformer encoder as its encoding module and a transformer decoder as its decoding module.This innovative neural network significantly reduces the memory space required and model training time,while maintaining a high level of accuracy in generating image descriptions.IMWTC facilitates large receptive fields without significantly increasing the number of parameters or computational overhead.The improvedMobileNet V3 model has its classifier removed,and simultaneously,it employs IMWTC layers to replace the original convolutional layers.This makes Mob-IMWTC exceptionally well-suited for deployment on lowresource devices.Experimental results,based on objective evaluation metrics such as BLEU,ROUGE,CIDEr,METEOR,and SPICE,demonstrate that Mob-IMWTC outperforms state-of-the-art models,including three CNN architectures(CNN-LSTM,CNN-Att-LSTM,CNN-Tran),two mainstream methods(LCM-Captioner,ClipCap),and our previous work(Mob-Tran).Subjective evaluations further validate the model’s superiority in terms of grammaticality,adequacy,logic,readability,and humanness.Mob-IMWTC offers a lightweight yet effective solution for image captioning,making it suitable for deployment on resource-constrained devices.
文摘Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural network(CNN)based methods,in which class activation mapping(CAM)is proposed to obtain the pseudo labels,and only concentrates on the most discriminative parts.Recently,transformer-based methods utilize attention map from the multi-headed self-attention(MHSA)module to predict pseudo labels,which usually contain obvious background noise and incoherent object area.To solve the above problems,we use the Conformer as our backbone,which is a parallel network based on convolutional neural network(CNN)and Transformer.The two branches generate pseudo labels and refine them independently,and can effectively combine the advantages of CNN and Transformer.However,the parallel structure is not close enough in the information communication.Thus,parallel structure can result in poor details about pseudo labels,and the background noise still exists.To alleviate this problem,we propose enhancing convolution CAM(ECCAM)model,which have three improved modules based on enhancing convolution,including deeper stem(DStem),convolutional feed-forward network(CFFN)and feature coupling unit with convolution(FCUConv).The ECCAM could make Conformer have tighter interaction between CNN and Transformer branches.After experimental verification,the improved modules we propose can help the network perceive more local information from images,making the final segmentation results more refined.Compared with similar architecture,our modules greatly improve the semantic segmentation performance and achieve70.2%mean intersection over union(mIoU)on the PASCAL VOC 2012 dataset.
基金supported by the Ministry of Education(MOE)Singapore,Academic Research Fund(AcRF)Tier 1(RG65/22)。
文摘Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.
基金supported in part by the National Natural Science Foundation of China under Grant 62172368the Natural Science Foundation of Zhejiang Province under Grant LR22F020003.
文摘The development of brain-computer interfaces(BCI)based on motor imagery(MI)has greatly improved patients’quality of life with movement disorders.The classification of upper limb MI has been widely studied and applied in many fields,including rehabilitation.However,the physiological representations of left and right lower limb movements are too close and activated deep in the cerebral cortex,making it difficult to distinguish their features.Therefore,classifying lower limbs motor imagery is more challenging.In this study,we propose a feature extraction method based on functional connectivity,which utilizes phase-locked values to construct a functional connectivity matrix as the features of the left and right legs,which can effectively avoid the problem of physiological representations of the left and right lower limbs being too close to each other during movement.In addition,considering the topology and the temporal characteristics of the electroencephalogram(EEG),we designed a temporal-spatial convolutional network(TSGCN)to capture the spatiotemporal information for classification.Experimental results show that the accuracy of the proposed method is higher than that of existing methods,achieving an average classification accuracy of 73.58%on the internal dataset.Finally,this study explains the network mechanism of left and right foot MI from the perspective of graph theoretic features and demonstrates the feasibility of decoding lower limb MI.
