This study examines the effectiveness of artificial intelligence techniques in generating high-quality environmental data for species introductory site selection systems.Combining Strengths,Weaknesses,Opportunities,Th...This study examines the effectiveness of artificial intelligence techniques in generating high-quality environmental data for species introductory site selection systems.Combining Strengths,Weaknesses,Opportunities,Threats(SWOT)analysis data with Variation Autoencoder(VAE)and Generative AdversarialNetwork(GAN)the network framework model(SAE-GAN),is proposed for environmental data reconstruction.The model combines two popular generative models,GAN and VAE,to generate features conditional on categorical data embedding after SWOT Analysis.The model is capable of generating features that resemble real feature distributions and adding sample factors to more accurately track individual sample data.Reconstructed data is used to retain more semantic information to generate features.The model was applied to species in Southern California,USA,citing SWOT analysis data to train the model.Experiments show that the model is capable of integrating data from more comprehensive analyses than traditional methods and generating high-quality reconstructed data from them,effectively solving the problem of insufficient data collection in development environments.The model is further validated by the Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS)classification assessment commonly used in the environmental data domain.This study provides a reliable and rich source of training data for species introduction site selection systems and makes a significant contribution to ecological and sustainable development.展开更多
A Bayesian network reconstruction method based on norm minimization is proposed to address the sparsity and iterative divergence issues in network reconstruction caused by noise and missing values.This method achieves...A Bayesian network reconstruction method based on norm minimization is proposed to address the sparsity and iterative divergence issues in network reconstruction caused by noise and missing values.This method achieves precise adjustment of the network structure by constructing a preliminary random network model and introducing small-world network characteristics and combines L1 norm minimization regularization techniques to control model complexity and optimize the inference process of variable dependencies.In the experiment of game network reconstruction,when the success rate of the L1 norm minimization model’s existence connection reconstruction reaches 100%,the minimum data required is about 40%,while the minimum data required for a sparse Bayesian learning network is about 45%.In terms of operational efficiency,the running time for minimizing the L1 normis basically maintained at 1.0 s,while the success rate of connection reconstruction increases significantly with an increase in data volume,reaching a maximum of 13.2 s.Meanwhile,in the case of a signal-to-noise ratio of 10 dB,the L1 model achieves a 100% success rate in the reconstruction of existing connections,while the sparse Bayesian network had the highest success rate of 90% in the reconstruction of non-existent connections.In the analysis of actual cases,the maximum lift and drop track of the research method is 0.08 m.The mean square error is 5.74 cm^(2).The results indicate that this norm minimization-based method has good performance in data efficiency and model stability,effectively reducing the impact of outliers on the reconstruction results to more accurately reflect the actual situation.展开更多
In the concurrent extraction of coal and gas,the quantitative assessment of evolving characteristics in mining-induced fracture networks and mining-enhanced permeability within coal seams serves as the cornerstone for...In the concurrent extraction of coal and gas,the quantitative assessment of evolving characteristics in mining-induced fracture networks and mining-enhanced permeability within coal seams serves as the cornerstone for effective gas extraction.However,representing mining-induced fracture networks from a three-dimensional(3D)sight and developing a comprehensive model to evaluate the anisotropic mining-enhanced permeability characteristics still pose significant challenges.In this investigation,a field experiment was undertaken to systematically monitor the evolution of borehole fractures in the coal mass ahead of the mining face at the Pingdingshan Coal Mining Group in China.Using the testing data of borehole fracture,the mining-induced fracture network at varying distances from the mining face was reconstructed through a statistical reconstruction method.Additionally,utilizing fractal theory,a model for the permeability enhancement rate(PER)induced by mining was established.This model was employed to quantitatively depict the anisotropic evolution patterns of PER as the mining face advanced.The research conclusions are as follows:(1)The progression of the mining-induced fracture network can be classified into the stage of rapid growth,the stage of stable growth,and the stage of weak impact;(2)The PER of mining-induced fracture network exhibited a typical progression that can be characterized with slow growth,rapid growth and significant decline;(3)The anisotropic mining-enhanced permeability of the reconstructed mining-induced fracture networks were significant.The peak PER in the vertical direction of the coal seam is 6.86 times and 4446.38 times greater than the direction perpendicular to the vertical thickness and the direction parallel to the advancement of the mining face,respectively.This investigatione provides a viable approach and methodology for quantitatively assessing the anisotropic PER of fracture networks induced during mining,in the concurrent exploitation of coal and gas.展开更多
For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high com...For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high computational complexity,and long reconstruction time.An image compressed sensing reconstruction network based on self-attention mechanism(SAMNet)was proposed.For the compressed sampling,self-attention convolution was designed,which was conducive to capturing richer features,so that the compressed sensing measurement value retained more image structure information.For the reconstruction,a self-attention mechanism was introduced in the convolutional neural network.A reconstruction network including residual blocks,bottleneck transformer(BoTNet),and dense blocks was proposed,which strengthened the transfer of image features and reduced the amount of parameters dramatically.Under the Set5 dataset,when the measurement rates are 0.01,0.04,0.10,and 0.25,the average peak signal-to-noise ratio(PSNR)of SAMNet is improved by 1.27,1.23,0.50,and 0.15 dB,respectively,compared to the CSNet+.The running time of reconstructing a 256×256 image is reduced by 0.1473,0.1789,0.2310,and 0.2524 s compared to ReconNet.Experimental results showed that SAMNet improved the quality of reconstructed images and reduced the reconstruction time.展开更多
3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safe...3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.展开更多
Lost acceleration response reconstruction is crucial for assessing structural conditions in structural health monitoring(SHM).However,traditional methods struggle to address the reconstruction of acceleration response...Lost acceleration response reconstruction is crucial for assessing structural conditions in structural health monitoring(SHM).However,traditional methods struggle to address the reconstruction of acceleration responses with complex features,resulting in a lower reconstruction accuracy.This paper addresses this challenge by leveraging the advanced feature extraction and learning capabilities of fully convolutional networks(FCN)to achieve precise reconstruction of acceleration responses.In the designed network architecture,the incorporation of skip connections preserves low-level details of the network,greatly facilitating the flow of information and improving training efficiency and accuracy.Dropout techniques are employed to reduce computational load and enhance feature extraction.The proposed FCN model automatically extracts high-level features from the input data and establishes a nonlinearmapping relationship between the input and output responses.Finally,the accuracy of the FCN for structural response reconstructionwas evaluated using acceleration data from an experimental arch rib and comparedwith several traditional methods.Additionally,this approach was applied to reconstruct actual acceleration responses measured by an SHM system on a long-span bridge.Through parameter analysis,the feasibility and accuracy of aspects such as available response positions,the number of available channels,and multi-channel response reconstruction were explored.The results indicate that this method exhibits high-precision response reconstruction capability in both time and frequency domains.,with performance surpassing that of other networks,confirming its effectiveness in reconstructing responses under various sensor data loss scenarios.展开更多
Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic...Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic,showing great potential.However,this method faces many challenges in practical applications,including uneven distribution of underground sources and complex survey environments.These situations seriously affect the reconstruction quality of virtual shot records,resulting in unguaranteed imaging results and greatly limiting passive source seismic exploration applications.In addition,the quality of the reconstructed records is directly related to the time length of the noise records,but in practice it is often difficult to obtain long-term,high-quality noise segments containing body wave events.To solve the above problems,we propose a deep learning method for reconstructing passive source virtual shot records and apply it to passive source time-lapse monitoring.This method combines the UNet network and the BiLSTM(Bidirectional Long Short-Term Memory)network for extracting spatial features and temporal features respectively.It introduces the spatial attention mechanism to establish a hybrid SUNet-BiLSTM-Attention(SBA)network for supervised training.Through pre-training and fine-tuning training,the network can accurately reconstruct passive source virtual shot records directly from short-time noisy segments containing body wave events.The experimental results of theoretical data show that the virtual shot records reconstructed by the network have high resolution and signal to noise ratio(SNR),providing high-quality data for subsequent monitoring and imaging.Finally,to further validate the effectiveness of proposed method,we applied it to field data collected from gas storage in northwest China.The reconstruction results of field data effectively improve the quality of virtual records and obtain more reliable time-lapse imaging monitoring results,which have significant practical value.展开更多
The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to case...The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.展开更多
There are millimeter, micron and nanometer scales of pores and fractures in coal to describe different scales of coal pores and fissures communicating path and to quantitatively characterize their permeability. Such i...There are millimeter, micron and nanometer scales of pores and fractures in coal to describe different scales of coal pores and fissures communicating path and to quantitatively characterize their permeability. Such information provides an important basis for studying coalbed methane output mechanism. The pores and fissures in a large number of coal samples were observed and counted by scanning electron microscopy and optical microscopy. The probability distribution models of pore-fissure network were then established. Different scales of pore-fissures 2D network models were reconstructed by Monte Carlo method. The 2D seepage models were obtained through assignment zero method and using Matlab software. The effect of permeability on different scale pore-fractures network was obtained by two-dimensional seepage equation. Predicted permeability is compared with the measured ones. The results showed that the dominant order of different scale pore-fractures connected path from high to low is millimeter-sized fractures, seepage pores and micron-size fractures. The contribution of coal reservoir permeability from large to small is millimeter-size fractures, micron-size fractures and seepage pores. Different parameters in different scale pore-fractures are of different influence permeability.Reconstruction of different scale pore-fractures network can clearly display the connectivity of porefractures, which can provide a basis for selecting migration path and studying gas flow pattern.展开更多
Phase space reconstruction is the first step of recognizing the chaotic time series.On the basis of differential entropy ratio method,the embedding dimension opt m and time delay t are optimal for the state space reco...Phase space reconstruction is the first step of recognizing the chaotic time series.On the basis of differential entropy ratio method,the embedding dimension opt m and time delay t are optimal for the state space reconstruction could be determined.But they are not the optimal parameters accepted for prediction.This study proposes an improved method based on the differential entropy ratio and Radial Basis Function(RBF)neural network to estimate the embedding dimension m and the time delay t,which have both optimal characteristics of the state space reconstruction and the prediction.Simulating experiments of Lorenz system and Doffing system show that the original phase space could be reconstructed from the time series effectively,and both the prediction accuracy and prediction length are improved greatly.展开更多
Proposed a new method to disclose the complicated non-linearity structure of the water-resource system, introducing chaos theory into the hydrology and water resources field, and combined with the chaos theory and art...Proposed a new method to disclose the complicated non-linearity structure of the water-resource system, introducing chaos theory into the hydrology and water resources field, and combined with the chaos theory and artificial neural networks. Training data construction and networks structure were determined by the phase space reconstruction, and establishing nonlinear relationship of phase points with neural networks, the forecasting model of the resource quantity of the surface water was brought forward. The keystone of the way and the detailed arithmetic of the network training were given. The example shows that the model has highly forecasting precision.展开更多
In LEO satellite communication networks,the number of satellites has increased sharply, the relative velocity of satellites is very fast, then electronic signal aliasing occurs from time to time. Those aliasing signal...In LEO satellite communication networks,the number of satellites has increased sharply, the relative velocity of satellites is very fast, then electronic signal aliasing occurs from time to time. Those aliasing signals make the receiving ability of the signal receiver worse, the signal processing ability weaker,and the anti-interference ability of the communication system lower. Aiming at the above problems, to save communication resources and improve communication efficiency, and considering the irregularity of interference signals, the underdetermined blind separation technology can effectively deal with the problem of interference sensing and signal reconstruction in this scenario. In order to improve the stability of source signal separation and the security of information transmission, a greedy optimization algorithm can be executed. At the same time, to improve network information transmission efficiency and prevent algorithms from getting trapped in local optima, delete low-energy points during each iteration process. Ultimately, simulation experiments validate that the algorithm presented in this paper enhances both the transmission efficiency of the network transmission system and the security of the communication system, achieving the process of interference sensing and signal reconstruction in the LEO satellite communication system.展开更多
The state reconstruction problem is addressed for complex dynamical networks coupled with states and outputs respectively, in a noisy transmission channel. By using Lyapunov stability theory and H∞ performance, two s...The state reconstruction problem is addressed for complex dynamical networks coupled with states and outputs respectively, in a noisy transmission channel. By using Lyapunov stability theory and H∞ performance, two schemes of state reconstruction are proposed for the complex dynamical networks with the nodes coupled by states and outputs respectively, and the estimation errors are convergent to zeros with H∞ performance index. A numerical simulation demonstrates the effectiveness of the proposed observers.展开更多
Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual...Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual perception,significantly increasing the utility of low-resolution images.In this study,an improved image superresolution reconstruction model based on Generative Adversarial Networks(SRGAN)was proposed.This model introduced a channel and spatial attention mechanism(CSAB)in the generator,allowing it to effectively leverage the information from the input image to enhance feature representations and capture important details.The discriminator was designed with an improved PatchGAN architecture,which more accurately captured local details and texture information of the image.With these enhanced generator and discriminator architectures and an optimized loss function design,this method demonstrated superior performance in image quality assessment metrics.Experimental results showed that this model outperforms traditional methods,presenting more detailed and realistic image details in the visual effects.展开更多
At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achievi...At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.展开更多
In current research, a series of triaxial tests, which were employed to simulate three typical mining lay-outs (i.e., top-coal caving, non-pillar mining and protected coal seam mining), were conducted on coal by using...In current research, a series of triaxial tests, which were employed to simulate three typical mining lay-outs (i.e., top-coal caving, non-pillar mining and protected coal seam mining), were conducted on coal by using MTS815 Flex Test GT rock mechanics test system, and the fracture networks in the broken coal samples were qualitatively and quantitatively investigated by employing CT scanning and 3D reconstruc-tion techniques. This work aimed at providing a detail description on the micro-structure and fracture-connectivity characteristics of rupture coal samples under different mining layouts. The results show that: (i) for protected coal seam mining layout, the coal specimens failure is in a compression-shear manner and oppositely, (ii) the tension-shear failure phenomenon is observed for top-coal caving and non-pillar mining layouts. By investigating the connectivity features of the generated fractures in the direction of r1 under different mining layouts, it is found that the connectivity level of the fractures of the samples corresponding to non-pillar mining layout was the highest.展开更多
In this paper, we improve traditional generative adversarial networks (GAN) with reference to residual networks and convolutional neural networks to facilitate the reconstruction of complex objects that cannot be reco...In this paper, we improve traditional generative adversarial networks (GAN) with reference to residual networks and convolutional neural networks to facilitate the reconstruction of complex objects that cannot be reconstructed by traditional associative imaging methods. Unlike traditional ghost imaging to reconstruct objects from bucket signals, our proposed method can use simple objects (such as EMNIST) as a training set for GAN, and then recognize objects (such as faces) of completely different complexity than the training set. We use traditional ghost imaging and neural network to reconstruct target objects respectively. According to the research results in this paper, the method based on neural network can reconstruct complex objects very well, but the method based on traditional ghost imaging cannot reconstruct complex objects. The research scheme in this paper is of great significance for the reconstruction of complex object-related imaging under low sampling conditions.展开更多
The 3D reconstruction of digital rocks assumes a paramount role within various engineering applications,necessitating careful consideration of the methods employed.The available approaches are divided into two groups,...The 3D reconstruction of digital rocks assumes a paramount role within various engineering applications,necessitating careful consideration of the methods employed.The available approaches are divided into two groups,i.e.,the physical experimental method and the numerical simulation method.Although the former is reliable,it incurs high costs and is limited by sample size constraints.The latter is cost-effective but suffers from prolonged processing times and sometimes suboptimal performance.However,the advent of deep learning has paved the way for integrating these techniques into 3D digital rock reconstruction.A standout amongst the method of deep learning techniques is the generative adversarial network(GAN).Nonetheless,existing models of GAN lack complete integration of multi-scale information.To address this issue,this study proposed style-transformer GAN(STGAN),a novel GAN model founded upon style-based GAN(StyleGAN)and Transformer.By utilizing the attention mechanisms of Transformer,STGAN ameliorates its ability to extract features from multi-scale training images.Additionally,the incorporation of style transfer further enhances the quality of the generated images.By comparing it with other deep learning algorithms,the efficiency and applicability of the proposed method are demonstrated.展开更多
β-ray-induced X-ray spectroscopy(BIXS)is a promising method for tritium detection in solid materials because of its unique advantages,such as large detection depth,nondestructive testing capabilities,and low requirem...β-ray-induced X-ray spectroscopy(BIXS)is a promising method for tritium detection in solid materials because of its unique advantages,such as large detection depth,nondestructive testing capabilities,and low requirements for sample preparation.However,high-accuracy reconstruction of the tritium depth profile remains a significant challenge for this technique.In this study,a novel reconstruction method based on a backpropagation(BP)neural network algorithm that demonstrates high accuracy,broad applicability,and robust noise resistance is proposed.The average reconstruction error calculated using the BP network(8.0%)was much lower than that obtained using traditional numerical methods(26.5%).In addition,the BP method can accurately reconstruct BIX spectra of samples with an unknown range of tritium and exhibits wide applicability to spectra with various tritium distributions.Furthermore,the BP network demonstrates superior accuracy and stability compared to numerical methods when reconstructing the spectra,with a relative uncertainty ranging from 0 to 10%.This study highlights the advantages of BP networks in accurately reconstructing the tritium depth profile from BIXS and promotes their further application in tritium detection.展开更多
Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrat...Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrates the utilization of sparse confocal microscopy layers to interpolate continuous axial resolution.With an embedded system focused on neural network pruning,image scaling,and post-processing,PLayer achieves high-performance metrics with an average structural similarity index of 0.9217 and a peak signal-to-noise ratio of 27.75 dB,all within 20 s.This represents a significant time saving of 85.71%with simplified image processing.By harnessing statistical map estimation in interpolation and incorporating the Vision Transformer–based Restorer,PLayer ensures 2D layer consistency while mitigating heavy computational dependence.As such,PLayer can reconstruct 3D neural organoid confocal data continuously under limited computational power for the wide acceptance of fundamental connectomics and pattern-related research with embedded devices.展开更多
基金supported by the Fundamental Research Funds for the Liaoning Universities(LJ212410146025).
文摘This study examines the effectiveness of artificial intelligence techniques in generating high-quality environmental data for species introductory site selection systems.Combining Strengths,Weaknesses,Opportunities,Threats(SWOT)analysis data with Variation Autoencoder(VAE)and Generative AdversarialNetwork(GAN)the network framework model(SAE-GAN),is proposed for environmental data reconstruction.The model combines two popular generative models,GAN and VAE,to generate features conditional on categorical data embedding after SWOT Analysis.The model is capable of generating features that resemble real feature distributions and adding sample factors to more accurately track individual sample data.Reconstructed data is used to retain more semantic information to generate features.The model was applied to species in Southern California,USA,citing SWOT analysis data to train the model.Experiments show that the model is capable of integrating data from more comprehensive analyses than traditional methods and generating high-quality reconstructed data from them,effectively solving the problem of insufficient data collection in development environments.The model is further validated by the Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS)classification assessment commonly used in the environmental data domain.This study provides a reliable and rich source of training data for species introduction site selection systems and makes a significant contribution to ecological and sustainable development.
基金supported by the Scientific and Technological Developing Scheme of Jilin Province,China(No.20240101371JC)the National Natural Science Foundation of China(No.62107008).
文摘A Bayesian network reconstruction method based on norm minimization is proposed to address the sparsity and iterative divergence issues in network reconstruction caused by noise and missing values.This method achieves precise adjustment of the network structure by constructing a preliminary random network model and introducing small-world network characteristics and combines L1 norm minimization regularization techniques to control model complexity and optimize the inference process of variable dependencies.In the experiment of game network reconstruction,when the success rate of the L1 norm minimization model’s existence connection reconstruction reaches 100%,the minimum data required is about 40%,while the minimum data required for a sparse Bayesian learning network is about 45%.In terms of operational efficiency,the running time for minimizing the L1 normis basically maintained at 1.0 s,while the success rate of connection reconstruction increases significantly with an increase in data volume,reaching a maximum of 13.2 s.Meanwhile,in the case of a signal-to-noise ratio of 10 dB,the L1 model achieves a 100% success rate in the reconstruction of existing connections,while the sparse Bayesian network had the highest success rate of 90% in the reconstruction of non-existent connections.In the analysis of actual cases,the maximum lift and drop track of the research method is 0.08 m.The mean square error is 5.74 cm^(2).The results indicate that this norm minimization-based method has good performance in data efficiency and model stability,effectively reducing the impact of outliers on the reconstruction results to more accurately reflect the actual situation.
基金supported by the National Natural Science Foundation of China (Grant No.42377143)Sichuan Natural Science Foundation (Grant No.2024NSFSC0097)the Open Fund of State Key Laboratory of Coal Mining and Clean Utilization,China (Grant No.2021-CMCU-KFZD001).
文摘In the concurrent extraction of coal and gas,the quantitative assessment of evolving characteristics in mining-induced fracture networks and mining-enhanced permeability within coal seams serves as the cornerstone for effective gas extraction.However,representing mining-induced fracture networks from a three-dimensional(3D)sight and developing a comprehensive model to evaluate the anisotropic mining-enhanced permeability characteristics still pose significant challenges.In this investigation,a field experiment was undertaken to systematically monitor the evolution of borehole fractures in the coal mass ahead of the mining face at the Pingdingshan Coal Mining Group in China.Using the testing data of borehole fracture,the mining-induced fracture network at varying distances from the mining face was reconstructed through a statistical reconstruction method.Additionally,utilizing fractal theory,a model for the permeability enhancement rate(PER)induced by mining was established.This model was employed to quantitatively depict the anisotropic evolution patterns of PER as the mining face advanced.The research conclusions are as follows:(1)The progression of the mining-induced fracture network can be classified into the stage of rapid growth,the stage of stable growth,and the stage of weak impact;(2)The PER of mining-induced fracture network exhibited a typical progression that can be characterized with slow growth,rapid growth and significant decline;(3)The anisotropic mining-enhanced permeability of the reconstructed mining-induced fracture networks were significant.The peak PER in the vertical direction of the coal seam is 6.86 times and 4446.38 times greater than the direction perpendicular to the vertical thickness and the direction parallel to the advancement of the mining face,respectively.This investigatione provides a viable approach and methodology for quantitatively assessing the anisotropic PER of fracture networks induced during mining,in the concurrent exploitation of coal and gas.
基金supported by National Natural Science Foundation of China(Nos.61261016,61661025)Science and Technology Plan of Gansu Province(No.20JR10RA273).
文摘For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high computational complexity,and long reconstruction time.An image compressed sensing reconstruction network based on self-attention mechanism(SAMNet)was proposed.For the compressed sampling,self-attention convolution was designed,which was conducive to capturing richer features,so that the compressed sensing measurement value retained more image structure information.For the reconstruction,a self-attention mechanism was introduced in the convolutional neural network.A reconstruction network including residual blocks,bottleneck transformer(BoTNet),and dense blocks was proposed,which strengthened the transfer of image features and reduced the amount of parameters dramatically.Under the Set5 dataset,when the measurement rates are 0.01,0.04,0.10,and 0.25,the average peak signal-to-noise ratio(PSNR)of SAMNet is improved by 1.27,1.23,0.50,and 0.15 dB,respectively,compared to the CSNet+.The running time of reconstructing a 256×256 image is reduced by 0.1473,0.1789,0.2310,and 0.2524 s compared to ReconNet.Experimental results showed that SAMNet improved the quality of reconstructed images and reduced the reconstruction time.
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004).
文摘3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.
基金National Natural Science Foundation of China(Grant Nos.52408314,52278292)Chongqing Outstanding Youth Science Foundation(Grant No.CSTB2023NSCQ-JQX0029)+1 种基金Science and Technology Project of Sichuan Provincial Transportation Department(Grant No.2023-ZL-03)Science and Technology Project of Guizhou Provincial Transportation Department(Grant No.2024-122-018).
文摘Lost acceleration response reconstruction is crucial for assessing structural conditions in structural health monitoring(SHM).However,traditional methods struggle to address the reconstruction of acceleration responses with complex features,resulting in a lower reconstruction accuracy.This paper addresses this challenge by leveraging the advanced feature extraction and learning capabilities of fully convolutional networks(FCN)to achieve precise reconstruction of acceleration responses.In the designed network architecture,the incorporation of skip connections preserves low-level details of the network,greatly facilitating the flow of information and improving training efficiency and accuracy.Dropout techniques are employed to reduce computational load and enhance feature extraction.The proposed FCN model automatically extracts high-level features from the input data and establishes a nonlinearmapping relationship between the input and output responses.Finally,the accuracy of the FCN for structural response reconstructionwas evaluated using acceleration data from an experimental arch rib and comparedwith several traditional methods.Additionally,this approach was applied to reconstruct actual acceleration responses measured by an SHM system on a long-span bridge.Through parameter analysis,the feasibility and accuracy of aspects such as available response positions,the number of available channels,and multi-channel response reconstruction were explored.The results indicate that this method exhibits high-precision response reconstruction capability in both time and frequency domains.,with performance surpassing that of other networks,confirming its effectiveness in reconstructing responses under various sensor data loss scenarios.
基金supported by the CNPC-SWPU Innovation Alliance Technology Cooperation Project(2020CX020000)the Natural Science Foundation of Sichuan Province(24NSFSC0808)the China Scholarship Council(202306440144).
文摘Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic,showing great potential.However,this method faces many challenges in practical applications,including uneven distribution of underground sources and complex survey environments.These situations seriously affect the reconstruction quality of virtual shot records,resulting in unguaranteed imaging results and greatly limiting passive source seismic exploration applications.In addition,the quality of the reconstructed records is directly related to the time length of the noise records,but in practice it is often difficult to obtain long-term,high-quality noise segments containing body wave events.To solve the above problems,we propose a deep learning method for reconstructing passive source virtual shot records and apply it to passive source time-lapse monitoring.This method combines the UNet network and the BiLSTM(Bidirectional Long Short-Term Memory)network for extracting spatial features and temporal features respectively.It introduces the spatial attention mechanism to establish a hybrid SUNet-BiLSTM-Attention(SBA)network for supervised training.Through pre-training and fine-tuning training,the network can accurately reconstruct passive source virtual shot records directly from short-time noisy segments containing body wave events.The experimental results of theoretical data show that the virtual shot records reconstructed by the network have high resolution and signal to noise ratio(SNR),providing high-quality data for subsequent monitoring and imaging.Finally,to further validate the effectiveness of proposed method,we applied it to field data collected from gas storage in northwest China.The reconstruction results of field data effectively improve the quality of virtual records and obtain more reliable time-lapse imaging monitoring results,which have significant practical value.
基金supported by the National Natural Science Foundation of China(No.12305344)the 2023 Anhui university research project of China(No.2023AH052179).
文摘The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.
基金in major projects of Henan Province University Science and Technology Innovation Talent Support Program of China (No. 15HASTIT050)Funding Scheme for Henan Province the Young Key Teachers (No. 2013GGJS-049) of ChinaScience and Technology Department of Henan Province of China (No. 142102210050)
文摘There are millimeter, micron and nanometer scales of pores and fractures in coal to describe different scales of coal pores and fissures communicating path and to quantitatively characterize their permeability. Such information provides an important basis for studying coalbed methane output mechanism. The pores and fissures in a large number of coal samples were observed and counted by scanning electron microscopy and optical microscopy. The probability distribution models of pore-fissure network were then established. Different scales of pore-fissures 2D network models were reconstructed by Monte Carlo method. The 2D seepage models were obtained through assignment zero method and using Matlab software. The effect of permeability on different scale pore-fractures network was obtained by two-dimensional seepage equation. Predicted permeability is compared with the measured ones. The results showed that the dominant order of different scale pore-fractures connected path from high to low is millimeter-sized fractures, seepage pores and micron-size fractures. The contribution of coal reservoir permeability from large to small is millimeter-size fractures, micron-size fractures and seepage pores. Different parameters in different scale pore-fractures are of different influence permeability.Reconstruction of different scale pore-fractures network can clearly display the connectivity of porefractures, which can provide a basis for selecting migration path and studying gas flow pattern.
基金Supported by the Key Program of National Natural Science Foundation of China(Nos.61077071,51075349)Program of National Natural Science Foundation of Hebei Province(Nos.F2011203207,F2010001312)
文摘Phase space reconstruction is the first step of recognizing the chaotic time series.On the basis of differential entropy ratio method,the embedding dimension opt m and time delay t are optimal for the state space reconstruction could be determined.But they are not the optimal parameters accepted for prediction.This study proposes an improved method based on the differential entropy ratio and Radial Basis Function(RBF)neural network to estimate the embedding dimension m and the time delay t,which have both optimal characteristics of the state space reconstruction and the prediction.Simulating experiments of Lorenz system and Doffing system show that the original phase space could be reconstructed from the time series effectively,and both the prediction accuracy and prediction length are improved greatly.
基金Supported by 863 Program of China(2002AA2Z4291) Henan Innovation Project for University Prominent Research Talents(2005KYCX015)Henan Project for University Prominent Talents
文摘Proposed a new method to disclose the complicated non-linearity structure of the water-resource system, introducing chaos theory into the hydrology and water resources field, and combined with the chaos theory and artificial neural networks. Training data construction and networks structure were determined by the phase space reconstruction, and establishing nonlinear relationship of phase points with neural networks, the forecasting model of the resource quantity of the surface water was brought forward. The keystone of the way and the detailed arithmetic of the network training were given. The example shows that the model has highly forecasting precision.
基金supported by National Natural Science Foundation of China (62171390)Central Universities of Southwest Minzu University (ZYN2022032,2023NYXXS034)the State Scholarship Fund of the China Scholarship Council (NO.202008510081)。
文摘In LEO satellite communication networks,the number of satellites has increased sharply, the relative velocity of satellites is very fast, then electronic signal aliasing occurs from time to time. Those aliasing signals make the receiving ability of the signal receiver worse, the signal processing ability weaker,and the anti-interference ability of the communication system lower. Aiming at the above problems, to save communication resources and improve communication efficiency, and considering the irregularity of interference signals, the underdetermined blind separation technology can effectively deal with the problem of interference sensing and signal reconstruction in this scenario. In order to improve the stability of source signal separation and the security of information transmission, a greedy optimization algorithm can be executed. At the same time, to improve network information transmission efficiency and prevent algorithms from getting trapped in local optima, delete low-energy points during each iteration process. Ultimately, simulation experiments validate that the algorithm presented in this paper enhances both the transmission efficiency of the network transmission system and the security of the communication system, achieving the process of interference sensing and signal reconstruction in the LEO satellite communication system.
文摘The state reconstruction problem is addressed for complex dynamical networks coupled with states and outputs respectively, in a noisy transmission channel. By using Lyapunov stability theory and H∞ performance, two schemes of state reconstruction are proposed for the complex dynamical networks with the nodes coupled by states and outputs respectively, and the estimation errors are convergent to zeros with H∞ performance index. A numerical simulation demonstrates the effectiveness of the proposed observers.
文摘Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual perception,significantly increasing the utility of low-resolution images.In this study,an improved image superresolution reconstruction model based on Generative Adversarial Networks(SRGAN)was proposed.This model introduced a channel and spatial attention mechanism(CSAB)in the generator,allowing it to effectively leverage the information from the input image to enhance feature representations and capture important details.The discriminator was designed with an improved PatchGAN architecture,which more accurately captured local details and texture information of the image.With these enhanced generator and discriminator architectures and an optimized loss function design,this method demonstrated superior performance in image quality assessment metrics.Experimental results showed that this model outperforms traditional methods,presenting more detailed and realistic image details in the visual effects.
基金This study was supported by the National Natural Science Foundation of China under the project‘Research on the Dynamic Location of Receiver Points and Wave Field Separation Technology Based on Deep Learning in OBN Seismic Exploration’(No.42074140).
文摘At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.
基金financially supported by the Major State Fundamental Research Project of China(Nos.2011CB201201and2010CB226802)the National Natural Science Foundation of China(No.51204113)the Youth Science and Technology Fund of Sichuan Province(No.2012JQ0031)
文摘In current research, a series of triaxial tests, which were employed to simulate three typical mining lay-outs (i.e., top-coal caving, non-pillar mining and protected coal seam mining), were conducted on coal by using MTS815 Flex Test GT rock mechanics test system, and the fracture networks in the broken coal samples were qualitatively and quantitatively investigated by employing CT scanning and 3D reconstruc-tion techniques. This work aimed at providing a detail description on the micro-structure and fracture-connectivity characteristics of rupture coal samples under different mining layouts. The results show that: (i) for protected coal seam mining layout, the coal specimens failure is in a compression-shear manner and oppositely, (ii) the tension-shear failure phenomenon is observed for top-coal caving and non-pillar mining layouts. By investigating the connectivity features of the generated fractures in the direction of r1 under different mining layouts, it is found that the connectivity level of the fractures of the samples corresponding to non-pillar mining layout was the highest.
文摘In this paper, we improve traditional generative adversarial networks (GAN) with reference to residual networks and convolutional neural networks to facilitate the reconstruction of complex objects that cannot be reconstructed by traditional associative imaging methods. Unlike traditional ghost imaging to reconstruct objects from bucket signals, our proposed method can use simple objects (such as EMNIST) as a training set for GAN, and then recognize objects (such as faces) of completely different complexity than the training set. We use traditional ghost imaging and neural network to reconstruct target objects respectively. According to the research results in this paper, the method based on neural network can reconstruct complex objects very well, but the method based on traditional ghost imaging cannot reconstruct complex objects. The research scheme in this paper is of great significance for the reconstruction of complex object-related imaging under low sampling conditions.
基金supported by the National Natural Science Foundation of China(41702148,41672114,and 42202146)Support Program of China Postdoctoral Innovative Talents(BX2021373 and 2022M723495)+3 种基金Natural Science Foundation of Shandong Province(ZR2022QD029)Taishan Scholars Program(tsqn202408104)Fundamental Research Funds for the Central Universities(22CX06006A,24CX06015A and 24CX02001A)Postdoctoral Application Research Project of Qingdao City(qdyy20210088).
文摘The 3D reconstruction of digital rocks assumes a paramount role within various engineering applications,necessitating careful consideration of the methods employed.The available approaches are divided into two groups,i.e.,the physical experimental method and the numerical simulation method.Although the former is reliable,it incurs high costs and is limited by sample size constraints.The latter is cost-effective but suffers from prolonged processing times and sometimes suboptimal performance.However,the advent of deep learning has paved the way for integrating these techniques into 3D digital rock reconstruction.A standout amongst the method of deep learning techniques is the generative adversarial network(GAN).Nonetheless,existing models of GAN lack complete integration of multi-scale information.To address this issue,this study proposed style-transformer GAN(STGAN),a novel GAN model founded upon style-based GAN(StyleGAN)and Transformer.By utilizing the attention mechanisms of Transformer,STGAN ameliorates its ability to extract features from multi-scale training images.Additionally,the incorporation of style transfer further enhances the quality of the generated images.By comparing it with other deep learning algorithms,the efficiency and applicability of the proposed method are demonstrated.
基金supported by the National Key Research and Development Program of China(No.2022YFE03170003)the National Natural Science Foundation of China(Nos.12305403 and 12275243).
文摘β-ray-induced X-ray spectroscopy(BIXS)is a promising method for tritium detection in solid materials because of its unique advantages,such as large detection depth,nondestructive testing capabilities,and low requirements for sample preparation.However,high-accuracy reconstruction of the tritium depth profile remains a significant challenge for this technique.In this study,a novel reconstruction method based on a backpropagation(BP)neural network algorithm that demonstrates high accuracy,broad applicability,and robust noise resistance is proposed.The average reconstruction error calculated using the BP network(8.0%)was much lower than that obtained using traditional numerical methods(26.5%).In addition,the BP method can accurately reconstruct BIX spectra of samples with an unknown range of tritium and exhibits wide applicability to spectra with various tritium distributions.Furthermore,the BP network demonstrates superior accuracy and stability compared to numerical methods when reconstructing the spectra,with a relative uncertainty ranging from 0 to 10%.This study highlights the advantages of BP networks in accurately reconstructing the tritium depth profile from BIXS and promotes their further application in tritium detection.
基金supported by the National Key R&D Program of China(Grant No.2021YFA1001000)the National Natural Science Foundation of China(Grant Nos.82111530212,U23A20282,and 61971255)+2 种基金the Natural Science Founda-tion of Guangdong Province(Grant No.2021B1515020092)the Shenzhen Bay Laboratory Fund(Grant No.SZBL2020090501014)the Shenzhen Science,Technology and Innovation Commission(Grant Nos.KJZD20231023094659002,JCYJ20220530142809022,and WDZC20220811170401001).
文摘Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrates the utilization of sparse confocal microscopy layers to interpolate continuous axial resolution.With an embedded system focused on neural network pruning,image scaling,and post-processing,PLayer achieves high-performance metrics with an average structural similarity index of 0.9217 and a peak signal-to-noise ratio of 27.75 dB,all within 20 s.This represents a significant time saving of 85.71%with simplified image processing.By harnessing statistical map estimation in interpolation and incorporating the Vision Transformer–based Restorer,PLayer ensures 2D layer consistency while mitigating heavy computational dependence.As such,PLayer can reconstruct 3D neural organoid confocal data continuously under limited computational power for the wide acceptance of fundamental connectomics and pattern-related research with embedded devices.
