With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object si...With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object significant challenges have been presented in accurately segmenting melanomas in dermoscopic images due to the objects that could interfere human observations,such as bubbles and scales.To address these challenges,we propose a dual U-Net network framework for skin melanoma segmentation.In our proposed architecture,we introduce several innovative components that aim to enhance the performance and capabilities of the traditional U-Net.First,we establish a novel framework that links two simplified U-Nets,enabling more comprehensive information exchange and feature integration throughout the network.Second,after cascading the second U-Net,we introduce a skip connection between the decoder and encoder networks,and incorporate a modified receptive field block(MRFB),which is designed to capture multi-scale spatial information.Third,to further enhance the feature representation capabilities,we add a multi-path convolution block attention module(MCBAM)to the first two layers of the first U-Net encoding,and integrate a new squeeze-and-excitation(SE)mechanism with residual connections in the second U-Net.To illustrate the performance of our proposed model,we conducted comprehensive experiments on widely recognized skin datasets.On the ISIC-2017 dataset,the IoU value of our proposed model increased from 0.6406 to 0.6819 and the Dice coefficient increased from 0.7625 to 0.8023.On the ISIC-2018 dataset,the IoU value of proposed model also improved from 0.7138 to 0.7709,while the Dice coefficient increased from 0.8285 to 0.8665.Furthermore,the generalization experiments conducted on the jaw cyst dataset from Quzhou People’s Hospital further verified the outstanding segmentation performance of the proposed model.These findings collectively affirm the potential of our approach as a valuable tool in supporting clinical decision-making in the field of skin cancer detection,as well as advancing research in medical image analysis.展开更多
In recent years,there has been a growing interest in graph convolutional networks(GCN).However,existing GCN and variants are predominantly based on simple graph or hypergraph structures,which restricts their ability t...In recent years,there has been a growing interest in graph convolutional networks(GCN).However,existing GCN and variants are predominantly based on simple graph or hypergraph structures,which restricts their ability to handle complex data correlations in practical applications.These limitations stem from the difficulty in establishing multiple hierarchies and acquiring adaptive weights for each of them.To address this issue,this paper introduces the latest concept of complex hypergraphs and constructs a versatile high-order multi-level data correlation model.This model is realized by establishing a three-tier structure of complexes-hypergraphs-vertices.Specifically,we start by establishing hyperedge clusters on a foundational network,utilizing a second-order hypergraph structure to depict potential correlations.For this second-order structure,truncation methods are used to assess and generate a three-layer composite structure.During the construction of the composite structure,an adaptive learning strategy is implemented to merge correlations across different levels.We evaluate this model on several popular datasets and compare it with recent state-of-the-art methods.The comprehensive assessment results demonstrate that the proposed model surpasses the existing methods,particularly in modeling implicit data correlations(the classification accuracy of nodes on five public datasets Cora,Citeseer,Pubmed,Github Web ML,and Facebook are 86.1±0.33,79.2±0.35,83.1±0.46,83.8±0.23,and 80.1±0.37,respectively).This indicates that our approach possesses advantages in handling datasets with implicit multi-level structures.展开更多
Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Ou...Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.展开更多
Digital rock physics(DRP)is a paramount technology to improve the economic benefits of oil and gas fields,devise more scientific oil and gas field development plans,and create digital oil and gas fields.Currently,a si...Digital rock physics(DRP)is a paramount technology to improve the economic benefits of oil and gas fields,devise more scientific oil and gas field development plans,and create digital oil and gas fields.Currently,a significant gap is present between DRP theory and practical applications.Conventional digital-core construction focuses only on simple cores,and the recognition and segmentation effect of fractures and pores of complex cores is poor.The identification of rock minerals is inaccurate,which leads to the difference between the digital and actual cores.To promote the application of DRP in developing oil and gas fields,based on the high-precision X-ray computed tomography scanning technology,the U-Net deep learning model of the full convolution neural network is used to segment the pores,fractures,and matrix from the complex rock core with natural fractures innovatively.Simultaneously,the distribution of rock minerals is divided,and the distribution of rock conditions is corrected by X-ray diffraction.A pore—fracture network model is established based on the equivalent radius,which lays the foundation for fluid seepage simulation.Finally,the accuracy of the established a digital core is verified by the porosity measured via nuclear magnetic resonance technology,which is of great significance to the development and application of DRP in oil and gas fields.展开更多
Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of...Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.展开更多
A discrete algorithm suitable for the computation of complex frequency-domain convolution on computers was derived. The Durbin's numerical inversion of Laplace transforms can be used to figure out the time-domain ...A discrete algorithm suitable for the computation of complex frequency-domain convolution on computers was derived. The Durbin's numerical inversion of Laplace transforms can be used to figure out the time-domain digital solution of the result of complex frequency-domain convolutions. Compared with the digital solutions and corresponding analytical solutions, it is shown that the digital solutions have high precision.展开更多
Orbital angular momentum(OAM),emerging as an inherently high-dimensional property of photons,has boosted information capacity in optical communications.However,the potential of OAM in optical computing remains almost ...Orbital angular momentum(OAM),emerging as an inherently high-dimensional property of photons,has boosted information capacity in optical communications.However,the potential of OAM in optical computing remains almost unexplored.Here,we present a highly efficient optical computing protocol for complex vector convolution with the superposition of high-dimensional OAM eigenmodes.We used two cascaded spatial light modulators to prepare suitable OAM superpositions to encode two complex vectors.Then,a deep-learning strategy is devised to decode the complex OAM spectrum,thus accomplishing the optical convolution task.In our experiment,we succeed in demonstrating 7-,9-,and 11-dimensional complex vector convolutions,in which an average proximity better than 95%and a mean relative error<6%are achieved.Our present scheme can be extended to incorporate other degrees of freedom for a more versatile optical computing in the high-dimensional Hilbert space.展开更多
In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addi...In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addition,during feature fusion,the use of fixed sampling kernels makes it difficult to focus on local changes in features,leading to limited localization accuracy.This paper proposes an image manipulation localization method based on dual-branch hybrid convolution.First,a dual-branch hybrid convolution module is designed to expand the receptive field of the model to enhance the feature extraction ability of contextual semantic information,while also enabling the model to focus more on the high-frequency detail features of manipulation traces while localizing the manipulated area.Second,a multiscale content-aware feature fusion module is used to dynamically generate adaptive sampling kernels for each position in the feature map,enabling the model to focus more on the details of local features while locating the manipulated area.Experimental results on multiple datasets show that this method not only effectively improves the accuracy of image manipulation localization but also enhances the robustness of the model.展开更多
为确立船舶营运过程中的风险涌现特征,需要考虑复杂系统组成因子的不确定结构问题。以复杂性系统为视角,提出了一种复杂网络不确定结构的风险功能共振分析模型。首先,利用Apriori算法对船舶系统组分进行风险分析,计算组成因子间的非线...为确立船舶营运过程中的风险涌现特征,需要考虑复杂系统组成因子的不确定结构问题。以复杂性系统为视角,提出了一种复杂网络不确定结构的风险功能共振分析模型。首先,利用Apriori算法对船舶系统组分进行风险分析,计算组成因子间的非线性交互效用,生成交互强度矩阵,从而确立船舶营运安全风险的功能共振分析模型(Functional Resonance Analysis Model,FRAM)。随后,采用图卷积网络(Graph Convolutional Network,GCN)构建系统组分网络,识别关键节点,并对因子交互关系网络结构进行重塑。最后,引入深度优先搜索(Depth First Search,DFS)算法,识别关键风险路径,计算出船舶系统组分因子的影响度。结合港口国监督(Port State Control,PSC)缺陷数据,运用前述模型对船舶营运风险进行仿真应用。应用结果表明,船舶的不安全状态受到内外部组成因子的属性影响,并存在关键共振路径关系,其中消防系统、船舶结构状态等是影响船舶不安全状态的核心节点。构建的风险功能共振分析模型能够基于不同的数据输入,自适应生成相应的风险路径依赖。基于复杂网络结构的风险功能共振模型有助于分析不确定结构复杂系统的风险涌现。展开更多
Level set method has been extensively used for image segmentation,which is a key technology of water extraction.However,one of the problems of the level-set method is how to find the appropriate initial surface parame...Level set method has been extensively used for image segmentation,which is a key technology of water extraction.However,one of the problems of the level-set method is how to find the appropriate initial surface parameters,which will affect the accuracy and speed of level set evolution.Recently,the semantic segmentation based on deep learning has opened the exciting research possibilities.In addition,the Convolutional Neural Network(CNN)has shown a strong feature representation capability.Therefore,in this paper,the CNN method is used to obtain the initial SAR image segmentation map to provide deep a priori information for the zero-level set curve,which only needs to describe the general outline of the water body,rather than the accurate edges.Compared with the traditional circular and rectangular zero-level set initialization method,this method can converge to the edge of the water body faster and more precisely;it will not fall into the local minimum value and be able to obtain accurate segmentation results.The effectiveness of the proposed method is demonstrated by the experimental results of flood disaster monitoring in South China in 2020.展开更多
Deep neural networks are now widely used in the medical image segmentation field for their performance superiority and no need of manual feature extraction.U-Net has been the baseline model since the very beginning du...Deep neural networks are now widely used in the medical image segmentation field for their performance superiority and no need of manual feature extraction.U-Net has been the baseline model since the very beginning due to a symmetricalU-structure for better feature extraction and fusing and suitable for small datasets.To enhance the segmentation performance of U-Net,cascaded U-Net proposes to put two U-Nets successively to segment targets from coarse to fine.However,the plain cascaded U-Net faces the problem of too less between connections so the contextual information learned by the former U-Net cannot be fully used by the latter one.In this article,we devise novel Inner Cascaded U-Net and Inner Cascaded U^(2)-Net as improvements to plain cascaded U-Net for medical image segmentation.The proposed Inner Cascaded U-Net adds inner nested connections between two U-Nets to share more contextual information.To further boost segmentation performance,we propose Inner Cascaded U^(2)-Net,which applies residual U-block to capture more global contextual information from different scales.The proposed models can be trained from scratch in an end-to-end fashion and have been evaluated on Multimodal Brain Tumor Segmentation Challenge(BraTS)2013 and ISBI Liver Tumor Segmentation Challenge(LiTS)dataset in comparison to related U-Net,cascaded U-Net,U-Net++,U^(2)-Net and state-of-the-art methods.Our experiments demonstrate that our proposed Inner Cascaded U-Net and Inner Cascaded U^(2)-Net achieve better segmentation performance in terms of dice similarity coefficient and hausdorff distance as well as get finer outline segmentation.展开更多
Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder ar...Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.展开更多
In order to solve the problems of shallow features loss and high computation cost of U-Net,we propose a lightweight with shallow features combination(IU-Net).IU-Net adds several convolution layers and short links to t...In order to solve the problems of shallow features loss and high computation cost of U-Net,we propose a lightweight with shallow features combination(IU-Net).IU-Net adds several convolution layers and short links to the skip path to extract more shallow features.At the same time,the original convolution is replaced by the depth-wise separable convolution to reduce the calculation cost and the number of parameters.IU-Net is applied to detecting small metal industrial products defects.It is evaluated on our own SUES-Washer dataset to verify the effectiveness.Experimental results demonstrate that our proposed method outperforms the original U-Net,and it has 1.73%,2.08%and 11.2%improvement in the intersection over union,accuracy,and detection time,respectively,which satisfies the requirements of industrial detection.展开更多
Human brain consists of millions of cells to control the overall structure of the human body.When these cells start behaving abnormally,then brain tumors occurred.Precise and initial stage brain tumor detection has al...Human brain consists of millions of cells to control the overall structure of the human body.When these cells start behaving abnormally,then brain tumors occurred.Precise and initial stage brain tumor detection has always been an issue in the field of medicines for medical experts.To handle this issue,various deep learning techniques for brain tumor detection and segmentation techniques have been developed,which worked on different datasets to obtain fruitful results,but the problem still exists for the initial stage of detection of brain tumors to save human lives.For this purpose,we proposed a novel U-Net-based Convolutional Neural Network(CNN)technique to detect and segmentizes the brain tumor for Magnetic Resonance Imaging(MRI).Moreover,a 2-dimensional publicly available Multimodal Brain Tumor Image Segmentation(BRATS2020)dataset with 1840 MRI images of brain tumors has been used having an image size of 240×240 pixels.After initial dataset preprocessing the proposed model is trained by dividing the dataset into three parts i.e.,testing,training,and validation process.Our model attained an accuracy value of 0.98%on the BRATS2020 dataset,which is the highest one as compared to the already existing techniques.展开更多
基金funded by Zhejiang Basic Public Welfare Research Project,grant number LZY24E060001supported by Guangzhou Development Zone Science and Technology(2021GH10,2020GH10,2023GH02)+1 种基金the University of Macao(MYRG2022-00271-FST)the Science and Technology Development Fund(FDCT)of Macao(0032/2022/A).
文摘With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object significant challenges have been presented in accurately segmenting melanomas in dermoscopic images due to the objects that could interfere human observations,such as bubbles and scales.To address these challenges,we propose a dual U-Net network framework for skin melanoma segmentation.In our proposed architecture,we introduce several innovative components that aim to enhance the performance and capabilities of the traditional U-Net.First,we establish a novel framework that links two simplified U-Nets,enabling more comprehensive information exchange and feature integration throughout the network.Second,after cascading the second U-Net,we introduce a skip connection between the decoder and encoder networks,and incorporate a modified receptive field block(MRFB),which is designed to capture multi-scale spatial information.Third,to further enhance the feature representation capabilities,we add a multi-path convolution block attention module(MCBAM)to the first two layers of the first U-Net encoding,and integrate a new squeeze-and-excitation(SE)mechanism with residual connections in the second U-Net.To illustrate the performance of our proposed model,we conducted comprehensive experiments on widely recognized skin datasets.On the ISIC-2017 dataset,the IoU value of our proposed model increased from 0.6406 to 0.6819 and the Dice coefficient increased from 0.7625 to 0.8023.On the ISIC-2018 dataset,the IoU value of proposed model also improved from 0.7138 to 0.7709,while the Dice coefficient increased from 0.8285 to 0.8665.Furthermore,the generalization experiments conducted on the jaw cyst dataset from Quzhou People’s Hospital further verified the outstanding segmentation performance of the proposed model.These findings collectively affirm the potential of our approach as a valuable tool in supporting clinical decision-making in the field of skin cancer detection,as well as advancing research in medical image analysis.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12275179 and 11875042)the Natural Science Foundation of Shanghai Municipality,China(Grant No.21ZR1443900)。
文摘In recent years,there has been a growing interest in graph convolutional networks(GCN).However,existing GCN and variants are predominantly based on simple graph or hypergraph structures,which restricts their ability to handle complex data correlations in practical applications.These limitations stem from the difficulty in establishing multiple hierarchies and acquiring adaptive weights for each of them.To address this issue,this paper introduces the latest concept of complex hypergraphs and constructs a versatile high-order multi-level data correlation model.This model is realized by establishing a three-tier structure of complexes-hypergraphs-vertices.Specifically,we start by establishing hyperedge clusters on a foundational network,utilizing a second-order hypergraph structure to depict potential correlations.For this second-order structure,truncation methods are used to assess and generate a three-layer composite structure.During the construction of the composite structure,an adaptive learning strategy is implemented to merge correlations across different levels.We evaluate this model on several popular datasets and compare it with recent state-of-the-art methods.The comprehensive assessment results demonstrate that the proposed model surpasses the existing methods,particularly in modeling implicit data correlations(the classification accuracy of nodes on five public datasets Cora,Citeseer,Pubmed,Github Web ML,and Facebook are 86.1±0.33,79.2±0.35,83.1±0.46,83.8±0.23,and 80.1±0.37,respectively).This indicates that our approach possesses advantages in handling datasets with implicit multi-level structures.
文摘Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.
基金Science and Technology Cooperation Project of the CNPC-SWPU Innovation Alliance(No.2020CX010501)National Science and Technology Major ProjectNational Natural Science Foundation of China Petrochemical Joint Fund Project(U1762107)
文摘Digital rock physics(DRP)is a paramount technology to improve the economic benefits of oil and gas fields,devise more scientific oil and gas field development plans,and create digital oil and gas fields.Currently,a significant gap is present between DRP theory and practical applications.Conventional digital-core construction focuses only on simple cores,and the recognition and segmentation effect of fractures and pores of complex cores is poor.The identification of rock minerals is inaccurate,which leads to the difference between the digital and actual cores.To promote the application of DRP in developing oil and gas fields,based on the high-precision X-ray computed tomography scanning technology,the U-Net deep learning model of the full convolution neural network is used to segment the pores,fractures,and matrix from the complex rock core with natural fractures innovatively.Simultaneously,the distribution of rock minerals is divided,and the distribution of rock conditions is corrected by X-ray diffraction.A pore—fracture network model is established based on the equivalent radius,which lays the foundation for fluid seepage simulation.Finally,the accuracy of the established a digital core is verified by the porosity measured via nuclear magnetic resonance technology,which is of great significance to the development and application of DRP in oil and gas fields.
基金The authors received Sichuan Science and Technology Program(No.18YYJC1917)funding for this study.
文摘Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.
文摘A discrete algorithm suitable for the computation of complex frequency-domain convolution on computers was derived. The Durbin's numerical inversion of Laplace transforms can be used to figure out the time-domain digital solution of the result of complex frequency-domain convolutions. Compared with the digital solutions and corresponding analytical solutions, it is shown that the digital solutions have high precision.
基金supported by the National Natural Science Foundation of China(Grant Nos.12034016,61975169,and 11904303)the Youth Innovation Fund of Xiamen(Grant No.3502Z20206045)+2 种基金the Fundamental Research Funds for the Central Universities at Xiamen University(Grant Nos.20720200074 and 20720220030)the Natural Science Foundation of Fujian Province of China(Grant No.2021J02002)and for Distinguished Young Scientists(Grant No.2015J06002)the Program for New Century Excellent Talents in University of China(Grant No.NCET-13-0495).
文摘Orbital angular momentum(OAM),emerging as an inherently high-dimensional property of photons,has boosted information capacity in optical communications.However,the potential of OAM in optical computing remains almost unexplored.Here,we present a highly efficient optical computing protocol for complex vector convolution with the superposition of high-dimensional OAM eigenmodes.We used two cascaded spatial light modulators to prepare suitable OAM superpositions to encode two complex vectors.Then,a deep-learning strategy is devised to decode the complex OAM spectrum,thus accomplishing the optical convolution task.In our experiment,we succeed in demonstrating 7-,9-,and 11-dimensional complex vector convolutions,in which an average proximity better than 95%and a mean relative error<6%are achieved.Our present scheme can be extended to incorporate other degrees of freedom for a more versatile optical computing in the high-dimensional Hilbert space.
基金National Natural Science Foundation of China(61703363)Shanxi Provincial Basic Research Program(202403021221206)+2 种基金Key Project of Shanxi Provincial Strategic Research on Science and Technology(202304031401011)Funding Project for Scientific Research Innovation Team on Data Mining and Industrial Intelligence Applications(YCXYTD-202402)Yuncheng University Research Project(YQ-2020021)。
文摘In existing image manipulation localization methods,the receptive field of standard convolution is limited,and during feature transfer,it is easy to lose high-frequency information about traces of manipulation.In addition,during feature fusion,the use of fixed sampling kernels makes it difficult to focus on local changes in features,leading to limited localization accuracy.This paper proposes an image manipulation localization method based on dual-branch hybrid convolution.First,a dual-branch hybrid convolution module is designed to expand the receptive field of the model to enhance the feature extraction ability of contextual semantic information,while also enabling the model to focus more on the high-frequency detail features of manipulation traces while localizing the manipulated area.Second,a multiscale content-aware feature fusion module is used to dynamically generate adaptive sampling kernels for each position in the feature map,enabling the model to focus more on the details of local features while locating the manipulated area.Experimental results on multiple datasets show that this method not only effectively improves the accuracy of image manipulation localization but also enhances the robustness of the model.
文摘为确立船舶营运过程中的风险涌现特征,需要考虑复杂系统组成因子的不确定结构问题。以复杂性系统为视角,提出了一种复杂网络不确定结构的风险功能共振分析模型。首先,利用Apriori算法对船舶系统组分进行风险分析,计算组成因子间的非线性交互效用,生成交互强度矩阵,从而确立船舶营运安全风险的功能共振分析模型(Functional Resonance Analysis Model,FRAM)。随后,采用图卷积网络(Graph Convolutional Network,GCN)构建系统组分网络,识别关键节点,并对因子交互关系网络结构进行重塑。最后,引入深度优先搜索(Depth First Search,DFS)算法,识别关键风险路径,计算出船舶系统组分因子的影响度。结合港口国监督(Port State Control,PSC)缺陷数据,运用前述模型对船舶营运风险进行仿真应用。应用结果表明,船舶的不安全状态受到内外部组成因子的属性影响,并存在关键共振路径关系,其中消防系统、船舶结构状态等是影响船舶不安全状态的核心节点。构建的风险功能共振分析模型能够基于不同的数据输入,自适应生成相应的风险路径依赖。基于复杂网络结构的风险功能共振模型有助于分析不确定结构复杂系统的风险涌现。
基金supported by the National Natural Science Foundation of China[grant numbers 41771457 and 41601443]the Research Program of the Department of Natural Resources of Hubei Province of China[grant number ZRZY2020KJ03].
文摘Level set method has been extensively used for image segmentation,which is a key technology of water extraction.However,one of the problems of the level-set method is how to find the appropriate initial surface parameters,which will affect the accuracy and speed of level set evolution.Recently,the semantic segmentation based on deep learning has opened the exciting research possibilities.In addition,the Convolutional Neural Network(CNN)has shown a strong feature representation capability.Therefore,in this paper,the CNN method is used to obtain the initial SAR image segmentation map to provide deep a priori information for the zero-level set curve,which only needs to describe the general outline of the water body,rather than the accurate edges.Compared with the traditional circular and rectangular zero-level set initialization method,this method can converge to the edge of the water body faster and more precisely;it will not fall into the local minimum value and be able to obtain accurate segmentation results.The effectiveness of the proposed method is demonstrated by the experimental results of flood disaster monitoring in South China in 2020.
基金supported in part by the National Nature Science Foundation of China(No.62172299)in part by the Shanghai Municipal Science and Technology Major Project(No.2021SHZDZX0100)in part by the Fundamental Research Funds for the Central Universi-ties of China.
文摘Deep neural networks are now widely used in the medical image segmentation field for their performance superiority and no need of manual feature extraction.U-Net has been the baseline model since the very beginning due to a symmetricalU-structure for better feature extraction and fusing and suitable for small datasets.To enhance the segmentation performance of U-Net,cascaded U-Net proposes to put two U-Nets successively to segment targets from coarse to fine.However,the plain cascaded U-Net faces the problem of too less between connections so the contextual information learned by the former U-Net cannot be fully used by the latter one.In this article,we devise novel Inner Cascaded U-Net and Inner Cascaded U^(2)-Net as improvements to plain cascaded U-Net for medical image segmentation.The proposed Inner Cascaded U-Net adds inner nested connections between two U-Nets to share more contextual information.To further boost segmentation performance,we propose Inner Cascaded U^(2)-Net,which applies residual U-block to capture more global contextual information from different scales.The proposed models can be trained from scratch in an end-to-end fashion and have been evaluated on Multimodal Brain Tumor Segmentation Challenge(BraTS)2013 and ISBI Liver Tumor Segmentation Challenge(LiTS)dataset in comparison to related U-Net,cascaded U-Net,U-Net++,U^(2)-Net and state-of-the-art methods.Our experiments demonstrate that our proposed Inner Cascaded U-Net and Inner Cascaded U^(2)-Net achieve better segmentation performance in terms of dice similarity coefficient and hausdorff distance as well as get finer outline segmentation.
文摘Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.
基金the Youth Fund of National Natural Science Foundation of China(61801286,62006150)Shanghai Young Science and Technology Talents Sailing Program(19YF1418400)Fund Project of Shanghai Science and Technology Commission(16dz1206002)。
文摘In order to solve the problems of shallow features loss and high computation cost of U-Net,we propose a lightweight with shallow features combination(IU-Net).IU-Net adds several convolution layers and short links to the skip path to extract more shallow features.At the same time,the original convolution is replaced by the depth-wise separable convolution to reduce the calculation cost and the number of parameters.IU-Net is applied to detecting small metal industrial products defects.It is evaluated on our own SUES-Washer dataset to verify the effectiveness.Experimental results demonstrate that our proposed method outperforms the original U-Net,and it has 1.73%,2.08%and 11.2%improvement in the intersection over union,accuracy,and detection time,respectively,which satisfies the requirements of industrial detection.
基金the support of the Deputy for Research and Innovation-Ministry of Education,Kingdom of Saudi Arabia for funding this research through a project(NU/IFC/ENT/01/014)under the institutional funding committee at Najran University,Kingdom of Saudi Arabia.
文摘Human brain consists of millions of cells to control the overall structure of the human body.When these cells start behaving abnormally,then brain tumors occurred.Precise and initial stage brain tumor detection has always been an issue in the field of medicines for medical experts.To handle this issue,various deep learning techniques for brain tumor detection and segmentation techniques have been developed,which worked on different datasets to obtain fruitful results,but the problem still exists for the initial stage of detection of brain tumors to save human lives.For this purpose,we proposed a novel U-Net-based Convolutional Neural Network(CNN)technique to detect and segmentizes the brain tumor for Magnetic Resonance Imaging(MRI).Moreover,a 2-dimensional publicly available Multimodal Brain Tumor Image Segmentation(BRATS2020)dataset with 1840 MRI images of brain tumors has been used having an image size of 240×240 pixels.After initial dataset preprocessing the proposed model is trained by dividing the dataset into three parts i.e.,testing,training,and validation process.Our model attained an accuracy value of 0.98%on the BRATS2020 dataset,which is the highest one as compared to the already existing techniques.
