In this paper,we established a class of parallel algorithm for solving low-rank tensor completion problem.The main idea is that N singular value decompositions are implemented in N different processors for each slice ...In this paper,we established a class of parallel algorithm for solving low-rank tensor completion problem.The main idea is that N singular value decompositions are implemented in N different processors for each slice matrix under unfold operator,and then the fold operator is used to form the next iteration tensor such that the computing time can be decreased.In theory,we analyze the global convergence of the algorithm.In numerical experiment,the simulation data and real image inpainting are carried out.Experiment results show the parallel algorithm outperform its original algorithm in CPU times under the same precision.展开更多
In order to rapidly and accurately detect infrared small and dim targets in the infrared image of complex scene collected by virtual prototyping of space-based downward-looking multiband detection,an improved detectio...In order to rapidly and accurately detect infrared small and dim targets in the infrared image of complex scene collected by virtual prototyping of space-based downward-looking multiband detection,an improved detection algorithm of infrared small and dim target is proposed in this paper.Firstly,the original infrared images are changed into a new infrared patch tensor mode through data reconstruction.Then,the infrared small and dim target detection problems are converted to low-rank tensor recovery problems based on tensor nuclear norm in accordance with patch tensor characteristics,and inverse variance weighted entropy is defined for self-adaptive adjustment of sparseness.Finally,the low-rank tensor recovery problem with noise is solved by alternating the direction method to obtain the sparse target image,and the final small target is worked out by a simple partitioning algorithm.The test results in various spacebased downward-looking complex scenes show that such method can restrain complex background well by virtue of rapid arithmetic speed with high detection probability and low false alarm rate.It is a kind of infrared small and dim target detection method with good performance.展开更多
This paper studies the problem of recovering low-rank tensors, and the tensors are corrupted by both impulse and Gaussian noise. The problem is well accomplished by integrating the tensor nuclear norm and the l1-norm ...This paper studies the problem of recovering low-rank tensors, and the tensors are corrupted by both impulse and Gaussian noise. The problem is well accomplished by integrating the tensor nuclear norm and the l1-norm in a unified convex relaxation framework. The nuclear norm is adopted to explore the low-rank components and the l1-norm is used to exploit the impulse noise. Then, this optimization problem is solved by some augmented-Lagrangian-based algorithms. Some preliminary numerical experiments verify that the proposed method can well recover the corrupted low-rank tensors.展开更多
Hyperspectral image(HSI) restoration has been widely used to improve the quality of HSI.HSIs are often impacted by various degradations,such as noise and deadlines,which have a bad visual effect and influence the subs...Hyperspectral image(HSI) restoration has been widely used to improve the quality of HSI.HSIs are often impacted by various degradations,such as noise and deadlines,which have a bad visual effect and influence the subsequent applications.For HSIs with missing data,most tensor regularized methods cannot complete missing data and restore it.We propose a spatial-spectral consistency regularized low-rank tensor completion(SSC-LRTC) model for removing noise and recovering HSI data,in which an SSC regularization is proposed considering the images of different bands are different from each other.Then,the proposed method is solved by a convergent multi-block alternating direction method of multipliers(ADMM) algorithm,and convergence of the solution is proved.The superiority of the proposed model on HSI restoration is demonstrated by experiments on removing various noises and deadlines.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
Compressed ultrafast photography(CUP)is a computational imaging technique that can simultaneously achieve an imaging speed of 10^(13)frames per second and a sequence depth of hundreds of frames.It is a powerful tool f...Compressed ultrafast photography(CUP)is a computational imaging technique that can simultaneously achieve an imaging speed of 10^(13)frames per second and a sequence depth of hundreds of frames.It is a powerful tool for observing unrepeatable ultrafast physical processes.However,since the forward model of CUP is a data compression process,the reconstruction process is an ill-posed problem.This causes inconvenience in the practical application of CUP,especially in those scenes with complex temporal behavior,high noise level and compression ratio.In this paper,the CUP system model based on spatial-intensity-temporal constraints is proposed by adding an additional charge-coupled device(CCD)camera to constrain the spatial and intensity behaviors of the dynamic scene and an additional narrow-slit streak camera to constrain the temporal behavior of the dynamic scene.Additionally,the unsupervised deep learning CUP reconstruction algorithm with low-rank tensor embedding is also proposed.The algorithm enhances the low-rankness of the reconstructed image by maintaining the low-rank structure of the dynamic scene and effectively utilizes the implicit prior information of the neural network and the hardware physical model.The proposed joint learning model enables high-quality reconstruction of complex dynamic scenes without training datasets.The simulation and experimental results demonstrate the application prospect of the proposed joint learning model in complex ultrafast physical phenomena imaging.展开更多
End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods th...End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.展开更多
The Wilczek–Zee connection(WZC)is a key concept in the study of topology of quantum systems.Here,we introduce the double Wilczek–Zee connection(DWZC)which naturally appears in the pure-state quantum geometric tensor...The Wilczek–Zee connection(WZC)is a key concept in the study of topology of quantum systems.Here,we introduce the double Wilczek–Zee connection(DWZC)which naturally appears in the pure-state quantum geometric tensor(QGT),another important concept in the field of quantum geometry.The DWZC is Hermitian with respect to the two integer indices,just like the original Hermitian WZC.Based on the symmetric logarithmic derivative operator,we propose a mixed-state quantum geometric tensor.Using the symmetric properties of the DWZC,we find that the real part of the QGT is connected to the real part of the DWZC and the square of eigenvalue differences of the density matrix,whereas the imaginary part can be given in terms of the imaginary part of the DWZC and the cube of the eigenvalue differences.For density matrices with full rank or no full rank,the QGT can be given in terms of real and imaginary parts of the DWZC.展开更多
We study the separability properties of solutions to elliptic equations with piecewise constant coefficients in Rd, d ≥ 2. The separation rank of the solution to diffusion equation with variable coefficients is prese...We study the separability properties of solutions to elliptic equations with piecewise constant coefficients in Rd, d ≥ 2. The separation rank of the solution to diffusion equation with variable coefficients is presented.展开更多
Dear Editor,This letter proposes the graph tensor alliance attention network(GT-A^(2)T)to represent a dynamic graph(DG)precisely.Its main idea includes 1)Establishing a unified spatio-temporal message propagation fram...Dear Editor,This letter proposes the graph tensor alliance attention network(GT-A^(2)T)to represent a dynamic graph(DG)precisely.Its main idea includes 1)Establishing a unified spatio-temporal message propagation framework on a DG via the tensor product for capturing the complex cohesive spatio-temporal interdependencies precisely and 2)Acquiring the alliance attention scores by node features and favorable high-order structural correlations.展开更多
As geological exploration conditions become increasingly complex, meeting the requirements of precise geological exploration necessitates the development of a controlled-source audio magnetotelluric (CSAMT) inversion ...As geological exploration conditions become increasingly complex, meeting the requirements of precise geological exploration necessitates the development of a controlled-source audio magnetotelluric (CSAMT) inversion method that considers anisotropy to improve the effectiveness of inversion accuracy and interpretation accuracy of data. This study is based on the 3D fi nite-diff erence forward modeling of axis anisotropy using the reciprocity theorem to calculate the Jacobian matrix by applying the search method to automatically search for the Lagrange operator. The aim is to establish inversion iteration equations to achieve the axis anisotropic Occam's 3D inversion of tensor CSAMT in data space. Further, we obtain an underground axis anisotropic 3D geoelectric model by inverting the impedance data of tensor CSAMT. Two synthetic data examples show that using the isotropic tensor CSAMT algorithm to directly invert data in anisotropic media can generate false anomalies, leading to incorrect geological interpretations. Meanwhile, the proposed anisotropic inversion algorithm can eff ectively improve the accuracy of data inversion in anisotropic media. Further, the inversion examples verify the eff ectiveness and stability of the algorithm.展开更多
Aiming at the problem that infrared small target detection faces low contrast between the background and the target and insufficient noise suppression ability under the complex cloud background,an infrared small targe...Aiming at the problem that infrared small target detection faces low contrast between the background and the target and insufficient noise suppression ability under the complex cloud background,an infrared small target detection method based on the tensor nuclear norm and direction residual weighting was proposed.Based on converting the infrared image into an infrared patch tensor model,from the perspective of the low-rank nature of the background tensor,and taking advantage of the difference in contrast between the background and the target in different directions,we designed a double-neighborhood local contrast based on direction residual weighting method(DNLCDRW)combined with the partial sum of tensor nuclear norm(PSTNN)to achieve effective background suppression and recovery of infrared small targets.Experiments show that the algorithm is effective in suppressing the background and improving the detection ability of the target.展开更多
The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelli...The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.展开更多
The composition and isotopic characteristics of coalbed methane(CBM), as well as the genesis of CH_(4)and CO_(2), associated geological process and migration-accumulation model of CBM in typical mid-to low-rank coal-b...The composition and isotopic characteristics of coalbed methane(CBM), as well as the genesis of CH_(4)and CO_(2), associated geological process and migration-accumulation model of CBM in typical mid-to low-rank coal-bearing basins were studied. The genesis of CBM is jointly influenced by the degree of coalification and biochemical processes, which in turn determine the composition and isotopic characteristics of CBM.Biogenic gas is extensively developed in mid-to low-rank coal-bearing basins, but its genesis varies. In the Baode area, China, and the San Juan Basin, USA, CBM is mainly secondary biogenic gas and thermogenic gas. In the Miquan area, China, CBM is characterized by primary biogenic gas. However, CBM in the Jiergalangtu area, China, Surat Basin, Australia, and Power River Basin, USA, are characterized by secondary biogenic gas. Microbial CO_(2)reduction occurs in these coal-bearing basins, but with significant gas generation by acetate fermentation in some areas of these basins. Moreover, CO_(2)in the Power River Basin, Surat Basin, and Jiergalangtu area mainly originates from microbial degradation of organic matter.However, in other basins studied, CO_(2)initially derives from coal pyrolysis and is subsequently supplemented by CO_(2)from microbial methanogenesis. The generation and isotope fractionation of CBM are affected and controlled by associated geological processes. Additionally, under the control of tectonic morphology and hydrogeological conditions, the genesis and migration-accumulation models of CBM in mid-to low-rank coal-bearing basins can be summarized into two models-the hydrodynamic active monoclinic model and the hydrodynamic differential syncline model-or a combination of the two.展开更多
Absorption compensation is a process involving the exponential amplification of reflection amplitudes.This process amplifies the seismic signal and noise,thereby substantially reducing the signal-tonoise ratio of seis...Absorption compensation is a process involving the exponential amplification of reflection amplitudes.This process amplifies the seismic signal and noise,thereby substantially reducing the signal-tonoise ratio of seismic data.Therefore,this paper proposes a multichannel inversion absorption compensation method based on structure tensor regularization.First,the structure tensor is utilized to extract the spatial inclination of seismic signals,and the spatial prediction filter is designed along the inclination direction.The spatial prediction filter is then introduced into the regularization condition of multichannel inversion absorption compensation,and the absorption compensation is realized under the framework of multichannel inversion theory.The spatial predictability of seismic signals is also introduced into the objective function of absorption compensation inversion.Thus,the inversion system can effectively suppress the noise amplification effect during absorption compensation and improve the recovery accuracy of high-frequency signals.Synthetic and field data tests are conducted to demonstrate the accuracy and effectiveness of the proposed method.展开更多
Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either dire...Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either directly or by reducing it to other problems.This paper introduces the Julia ecosystem for solving and analyzing CSPs with a focus on the programming practices.We introduce some important CSPs and show how these problems are reduced to each other.We also show how to transform CSPs into tensor networks,how to optimize the tensor network contraction orders,and how to extract the solution space properties by contracting the tensor networks with generic element types.Examples are given,which include computing the entropy constant,analyzing the overlap gap property,and the reduction between CSPs.展开更多
Computing free energy is a fundamental problem in statistical physics.Recently,two distinct methods have been developed and have demonstrated remarkable success:the tensor-network-based contraction method and the neur...Computing free energy is a fundamental problem in statistical physics.Recently,two distinct methods have been developed and have demonstrated remarkable success:the tensor-network-based contraction method and the neural-network-based variational method.Tensor networks are accurate,but their application is often limited to low-dimensional systems due to the high computational complexity in high-dimensional systems.The neural network method applies to systems with general topology.However,as a variational method,it is not as accurate as tensor networks.In this work,we propose an integrated approach,tensor-network-based variational autoregressive networks(TNVAN),that leverages the strengths of both tensor networks and neural networks:combining the variational autoregressive neural network’s ability to compute an upper bound on free energy and perform unbiased sampling from the variational distribution with the tensor network’s power to accurately compute the partition function for small sub-systems,resulting in a robust method for precisely estimating free energy.To evaluate the proposed approach,we conducted numerical experiments on spin glass systems with various topologies,including two-dimensional lattices,fully connected graphs,and random graphs.Our numerical results demonstrate the superior accuracy of our method compared to existing approaches.In particular,it effectively handles systems with longrange interactions and leverages GPU efficiency without requiring singular value decomposition,indicating great potential in tackling statistical mechanics problems and simulating high-dimensional complex systems through both tensor networks and neural networks.展开更多
When plants respond to drought stress,dynamic cellular changes occur,accompanied by alterations in gene expression,which often act through trans-regulation.However,the detection of trans-acting genetic variants and ne...When plants respond to drought stress,dynamic cellular changes occur,accompanied by alterations in gene expression,which often act through trans-regulation.However,the detection of trans-acting genetic variants and networks of genes is challenged by the large number of genes and markers.Using a tensor decomposition method,we identify trans-acting expression quantitative trait loci(trans-eQTLs)linked to gene modules,rather than individual genes,which were associated with maize drought response.Module-to-trait association analysis demonstrates that half of the modules are relevant to drought-related traits.Genome-wide association studies of the expression patterns of each module identify 286 trans-eQTLs linked to drought-responsive modules,the majority of which cannot be detected based on individual gene expression.Notably,the trans-eQTLs located in the regions selected during maize improvement tend towards relatively strong selection.We further prioritize the genes that affect the transcriptional regulation of multiple genes in trans,as exemplified by two transcription factor genes.Our analyses highlight that multidimensional reduction could facilitate the identification of trans-acting variations in gene expression in response to dynamic environments and serve as a promising technique for high-order data processing in future crop breeding.展开更多
基金Supported by National Nature Science Foundation(12371381)Nature Science Foundation of Shanxi(202403021222270)。
文摘In this paper,we established a class of parallel algorithm for solving low-rank tensor completion problem.The main idea is that N singular value decompositions are implemented in N different processors for each slice matrix under unfold operator,and then the fold operator is used to form the next iteration tensor such that the computing time can be decreased.In theory,we analyze the global convergence of the algorithm.In numerical experiment,the simulation data and real image inpainting are carried out.Experiment results show the parallel algorithm outperform its original algorithm in CPU times under the same precision.
文摘In order to rapidly and accurately detect infrared small and dim targets in the infrared image of complex scene collected by virtual prototyping of space-based downward-looking multiband detection,an improved detection algorithm of infrared small and dim target is proposed in this paper.Firstly,the original infrared images are changed into a new infrared patch tensor mode through data reconstruction.Then,the infrared small and dim target detection problems are converted to low-rank tensor recovery problems based on tensor nuclear norm in accordance with patch tensor characteristics,and inverse variance weighted entropy is defined for self-adaptive adjustment of sparseness.Finally,the low-rank tensor recovery problem with noise is solved by alternating the direction method to obtain the sparse target image,and the final small target is worked out by a simple partitioning algorithm.The test results in various spacebased downward-looking complex scenes show that such method can restrain complex background well by virtue of rapid arithmetic speed with high detection probability and low false alarm rate.It is a kind of infrared small and dim target detection method with good performance.
文摘This paper studies the problem of recovering low-rank tensors, and the tensors are corrupted by both impulse and Gaussian noise. The problem is well accomplished by integrating the tensor nuclear norm and the l1-norm in a unified convex relaxation framework. The nuclear norm is adopted to explore the low-rank components and the l1-norm is used to exploit the impulse noise. Then, this optimization problem is solved by some augmented-Lagrangian-based algorithms. Some preliminary numerical experiments verify that the proposed method can well recover the corrupted low-rank tensors.
文摘Hyperspectral image(HSI) restoration has been widely used to improve the quality of HSI.HSIs are often impacted by various degradations,such as noise and deadlines,which have a bad visual effect and influence the subsequent applications.For HSIs with missing data,most tensor regularized methods cannot complete missing data and restore it.We propose a spatial-spectral consistency regularized low-rank tensor completion(SSC-LRTC) model for removing noise and recovering HSI data,in which an SSC regularization is proposed considering the images of different bands are different from each other.Then,the proposed method is solved by a convergent multi-block alternating direction method of multipliers(ADMM) algorithm,and convergence of the solution is proved.The superiority of the proposed model on HSI restoration is demonstrated by experiments on removing various noises and deadlines.
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.
基金National Natural Science Foundation of China(11975184)。
文摘Compressed ultrafast photography(CUP)is a computational imaging technique that can simultaneously achieve an imaging speed of 10^(13)frames per second and a sequence depth of hundreds of frames.It is a powerful tool for observing unrepeatable ultrafast physical processes.However,since the forward model of CUP is a data compression process,the reconstruction process is an ill-posed problem.This causes inconvenience in the practical application of CUP,especially in those scenes with complex temporal behavior,high noise level and compression ratio.In this paper,the CUP system model based on spatial-intensity-temporal constraints is proposed by adding an additional charge-coupled device(CCD)camera to constrain the spatial and intensity behaviors of the dynamic scene and an additional narrow-slit streak camera to constrain the temporal behavior of the dynamic scene.Additionally,the unsupervised deep learning CUP reconstruction algorithm with low-rank tensor embedding is also proposed.The algorithm enhances the low-rankness of the reconstructed image by maintaining the low-rank structure of the dynamic scene and effectively utilizes the implicit prior information of the neural network and the hardware physical model.The proposed joint learning model enables high-quality reconstruction of complex dynamic scenes without training datasets.The simulation and experimental results demonstrate the application prospect of the proposed joint learning model in complex ultrafast physical phenomena imaging.
基金supported by the National Natural Science Foundation of China(Grant No.62266054)the Major Science and Technology Project of Yunnan Province(Grant No.202402AD080002)the Scientific Research Fund of the Yunnan Provincial Department of Education(Grant No.2025Y0302).
文摘End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.
基金Project supported by Quantum Science and Technology–National Science and Technology Major Project(Grant No.2024ZD0301000)the National Natural Science Foundation of China(Grant No.12305031)+1 种基金the Hangzhou Joint Fund of the Natural Science Foundation of Zhejiang Province,China(Grant No.LHZSD24A050001)the Science Foundation of Zhejiang Sci-Tech University(Grant Nos.23062088Y and 23062153-Y)。
文摘The Wilczek–Zee connection(WZC)is a key concept in the study of topology of quantum systems.Here,we introduce the double Wilczek–Zee connection(DWZC)which naturally appears in the pure-state quantum geometric tensor(QGT),another important concept in the field of quantum geometry.The DWZC is Hermitian with respect to the two integer indices,just like the original Hermitian WZC.Based on the symmetric logarithmic derivative operator,we propose a mixed-state quantum geometric tensor.Using the symmetric properties of the DWZC,we find that the real part of the QGT is connected to the real part of the DWZC and the square of eigenvalue differences of the density matrix,whereas the imaginary part can be given in terms of the imaginary part of the DWZC and the cube of the eigenvalue differences.For density matrices with full rank or no full rank,the QGT can be given in terms of real and imaginary parts of the DWZC.
文摘We study the separability properties of solutions to elliptic equations with piecewise constant coefficients in Rd, d ≥ 2. The separation rank of the solution to diffusion equation with variable coefficients is presented.
基金supported in part by the National Natural Science Foundation of China(62372385).
文摘Dear Editor,This letter proposes the graph tensor alliance attention network(GT-A^(2)T)to represent a dynamic graph(DG)precisely.Its main idea includes 1)Establishing a unified spatio-temporal message propagation framework on a DG via the tensor product for capturing the complex cohesive spatio-temporal interdependencies precisely and 2)Acquiring the alliance attention scores by node features and favorable high-order structural correlations.
基金supported by Heilongjiang Province Basic Research Business Expenses for Universities Heilongjiang University Special Fund Project (Grant No. 2023-KYYWF-1494)the Natural Science Foundation of Jiangxi Province (Grant No. 20212BAB213023)。
文摘As geological exploration conditions become increasingly complex, meeting the requirements of precise geological exploration necessitates the development of a controlled-source audio magnetotelluric (CSAMT) inversion method that considers anisotropy to improve the effectiveness of inversion accuracy and interpretation accuracy of data. This study is based on the 3D fi nite-diff erence forward modeling of axis anisotropy using the reciprocity theorem to calculate the Jacobian matrix by applying the search method to automatically search for the Lagrange operator. The aim is to establish inversion iteration equations to achieve the axis anisotropic Occam's 3D inversion of tensor CSAMT in data space. Further, we obtain an underground axis anisotropic 3D geoelectric model by inverting the impedance data of tensor CSAMT. Two synthetic data examples show that using the isotropic tensor CSAMT algorithm to directly invert data in anisotropic media can generate false anomalies, leading to incorrect geological interpretations. Meanwhile, the proposed anisotropic inversion algorithm can eff ectively improve the accuracy of data inversion in anisotropic media. Further, the inversion examples verify the eff ectiveness and stability of the algorithm.
基金Supported by the Key Laboratory Fund for Equipment Pre-Research(6142207210202)。
文摘Aiming at the problem that infrared small target detection faces low contrast between the background and the target and insufficient noise suppression ability under the complex cloud background,an infrared small target detection method based on the tensor nuclear norm and direction residual weighting was proposed.Based on converting the infrared image into an infrared patch tensor model,from the perspective of the low-rank nature of the background tensor,and taking advantage of the difference in contrast between the background and the target in different directions,we designed a double-neighborhood local contrast based on direction residual weighting method(DNLCDRW)combined with the partial sum of tensor nuclear norm(PSTNN)to achieve effective background suppression and recovery of infrared small targets.Experiments show that the algorithm is effective in suppressing the background and improving the detection ability of the target.
基金supported by the National Natural Science Foundation of China(No.52275104)the Science and Technology Innovation Program of Hunan Province(No.2023RC3097).
文摘The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.
基金supported by the National Natural Science Foundation of China(No.42272200)The Science and Technology Major Project of China National Petroleum Corporation(No.2023ZZ18-03)+1 种基金The Science and Technology Major Project of Changqing Oilfield(No.2023DZZ01)The Technology project of Huaneng Group Headquarters(Medium-deep Low-Rank Coalbed Methane Resource Potential Evaluation and Key Development Technologies of Zhalainuoer Coalfield,No.HNKJ23-H51).
文摘The composition and isotopic characteristics of coalbed methane(CBM), as well as the genesis of CH_(4)and CO_(2), associated geological process and migration-accumulation model of CBM in typical mid-to low-rank coal-bearing basins were studied. The genesis of CBM is jointly influenced by the degree of coalification and biochemical processes, which in turn determine the composition and isotopic characteristics of CBM.Biogenic gas is extensively developed in mid-to low-rank coal-bearing basins, but its genesis varies. In the Baode area, China, and the San Juan Basin, USA, CBM is mainly secondary biogenic gas and thermogenic gas. In the Miquan area, China, CBM is characterized by primary biogenic gas. However, CBM in the Jiergalangtu area, China, Surat Basin, Australia, and Power River Basin, USA, are characterized by secondary biogenic gas. Microbial CO_(2)reduction occurs in these coal-bearing basins, but with significant gas generation by acetate fermentation in some areas of these basins. Moreover, CO_(2)in the Power River Basin, Surat Basin, and Jiergalangtu area mainly originates from microbial degradation of organic matter.However, in other basins studied, CO_(2)initially derives from coal pyrolysis and is subsequently supplemented by CO_(2)from microbial methanogenesis. The generation and isotope fractionation of CBM are affected and controlled by associated geological processes. Additionally, under the control of tectonic morphology and hydrogeological conditions, the genesis and migration-accumulation models of CBM in mid-to low-rank coal-bearing basins can be summarized into two models-the hydrodynamic active monoclinic model and the hydrodynamic differential syncline model-or a combination of the two.
基金funded by the National Key R&D Program of China(Grant no.2018YFA0702504)the Sinopec research project(P22162).
文摘Absorption compensation is a process involving the exponential amplification of reflection amplitudes.This process amplifies the seismic signal and noise,thereby substantially reducing the signal-tonoise ratio of seismic data.Therefore,this paper proposes a multichannel inversion absorption compensation method based on structure tensor regularization.First,the structure tensor is utilized to extract the spatial inclination of seismic signals,and the spatial prediction filter is designed along the inclination direction.The spatial prediction filter is then introduced into the regularization condition of multichannel inversion absorption compensation,and the absorption compensation is realized under the framework of multichannel inversion theory.The spatial predictability of seismic signals is also introduced into the objective function of absorption compensation inversion.Thus,the inversion system can effectively suppress the noise amplification effect during absorption compensation and improve the recovery accuracy of high-frequency signals.Synthetic and field data tests are conducted to demonstrate the accuracy and effectiveness of the proposed method.
基金funded by the National Key R&D Program of China(Grant No.2024YFE0102500)the National Natural Science Foundation of China(Grant No.12404568)+1 种基金the Guangzhou Municipal Science and Technology Project(Grant No.2023A03J00904)the Quantum Science Center of Guangdong-Hong Kong-Macao Greater Bay Area,China and the Undergraduate Research Project from HKUST(Guangzhou).
文摘Constraint satisfaction problems(CSPs)are a class of problems that are ubiquitous in science and engineering.They feature a collection of constraints specified over subsets of variables.A CSP can be solved either directly or by reducing it to other problems.This paper introduces the Julia ecosystem for solving and analyzing CSPs with a focus on the programming practices.We introduce some important CSPs and show how these problems are reduced to each other.We also show how to transform CSPs into tensor networks,how to optimize the tensor network contraction orders,and how to extract the solution space properties by contracting the tensor networks with generic element types.Examples are given,which include computing the entropy constant,analyzing the overlap gap property,and the reduction between CSPs.
基金supported by Projects 12325501,12047503,and 12247104 of the National Natural Science Foundation of ChinaProject ZDRW-XX-2022-3-02 of the Chinese Academy of Sciencessupported by the Innovation Program for Quantum Science and Technology project 2021ZD0301900。
文摘Computing free energy is a fundamental problem in statistical physics.Recently,two distinct methods have been developed and have demonstrated remarkable success:the tensor-network-based contraction method and the neural-network-based variational method.Tensor networks are accurate,but their application is often limited to low-dimensional systems due to the high computational complexity in high-dimensional systems.The neural network method applies to systems with general topology.However,as a variational method,it is not as accurate as tensor networks.In this work,we propose an integrated approach,tensor-network-based variational autoregressive networks(TNVAN),that leverages the strengths of both tensor networks and neural networks:combining the variational autoregressive neural network’s ability to compute an upper bound on free energy and perform unbiased sampling from the variational distribution with the tensor network’s power to accurately compute the partition function for small sub-systems,resulting in a robust method for precisely estimating free energy.To evaluate the proposed approach,we conducted numerical experiments on spin glass systems with various topologies,including two-dimensional lattices,fully connected graphs,and random graphs.Our numerical results demonstrate the superior accuracy of our method compared to existing approaches.In particular,it effectively handles systems with longrange interactions and leverages GPU efficiency without requiring singular value decomposition,indicating great potential in tackling statistical mechanics problems and simulating high-dimensional complex systems through both tensor networks and neural networks.
基金supported by the Biological Breeding-National Science and Technology Major Project(2023ZD04076)the Guangxi Key Research and Development Projects of China(GuikeAB21238004)the Agricultural Science and Technology Innovation Program.
文摘When plants respond to drought stress,dynamic cellular changes occur,accompanied by alterations in gene expression,which often act through trans-regulation.However,the detection of trans-acting genetic variants and networks of genes is challenged by the large number of genes and markers.Using a tensor decomposition method,we identify trans-acting expression quantitative trait loci(trans-eQTLs)linked to gene modules,rather than individual genes,which were associated with maize drought response.Module-to-trait association analysis demonstrates that half of the modules are relevant to drought-related traits.Genome-wide association studies of the expression patterns of each module identify 286 trans-eQTLs linked to drought-responsive modules,the majority of which cannot be detected based on individual gene expression.Notably,the trans-eQTLs located in the regions selected during maize improvement tend towards relatively strong selection.We further prioritize the genes that affect the transcriptional regulation of multiple genes in trans,as exemplified by two transcription factor genes.Our analyses highlight that multidimensional reduction could facilitate the identification of trans-acting variations in gene expression in response to dynamic environments and serve as a promising technique for high-order data processing in future crop breeding.
