Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To ...Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.展开更多
Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insigh...Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.展开更多
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t...Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.展开更多
Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectra...Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.展开更多
Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstr...Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstruction algorithms usually used nonadaptive sparsifying transforms,resulting in a limited reconstruction accuracy.Therefore,we proposed a new model for accurate parallel MRI reconstruction by combining the L0 norm regularization term based on the efficient sum of outer products dictionary learning(SOUPDIL)with the SENSE model,called SOUPDIL-SENSE.The SOUPDIL-SENSE model is mainly solved by utilizing the variable splitting and alternating direction method of multipliers techniques.The experimental results on four human datasets show that the proposed algorithm effectively promotes the image sparsity,eliminates the noise and artifacts of the reconstructed images,and improves the reconstruction accuracy.展开更多
Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting fo...Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.展开更多
An accurate and comprehensive understanding of shale pore structure is fundamental and critical for accurate reserves evaluation and efficient hydrocarbon development.Thus,by taking the shale of Paleogene Eocene Shahe...An accurate and comprehensive understanding of shale pore structure is fundamental and critical for accurate reserves evaluation and efficient hydrocarbon development.Thus,by taking the shale of Paleogene Eocene Shahejie Formation in the Jiyang Depression,Bohai Bay Basin,as an example,the 2D and 3D multi-resolution images of the shale microstructure are obtained by multiple imaging technologies,including X-ray computed tomography,large-field scanning electron microscopy,scanning electron microscopy and focused ion beam scanning electron microscopy.By integrating image processing and machine learning algorithms,the shale pore structure is characterized at a single scale and multi scales.The results are obtained as follows.First,the shale pore space in the study area is mainly composed of microfractures,inorganic pores,organic matters and organic pores,and exclusively shows multi-scale characteristics.Second,there are various types of inorganic pores,and abundant dissolution pores;organic matters are distributed as strips and patches,and no organic pores are found in some organic matters.Third,pores with radius less than 20 nm account for 25%,those with radius between 20 and 50 nm account for 19%,those with radius between 50 and 100 nm account for 29%,those with radius between 100 and 500 nm account for 14%,those with radius between 500 nm and 20 mm account for 11%,and those with radius between 20 and 50 mm account for 2%.Fourth,the organic pores are less connected than the inorganic pores.The connectivity between organic pores and inorganic pores plays a crucial role in hydrocarbon migration,and microfractures control fluid flow channels.Fifth,pores with radius less than 50 nm are dominantly organic pores,those with radius between 50 and 500 nm are mainly organic and inorganic pores,and microfractures mainly contribute to the pores with radius more than 500 nm.It is concluded that a single imaging experiment cannot accurately and comprehensively reveal the multi-scale micro pore structure of a shale reservoir.Through integration of multiple imaging technologies and machine learning algorithms,the shale pore structure can be recognized and characterized at both single scale and multi scales.The proposed new method provides accurate and comprehensive information of multi-scale pore structures.展开更多
Impulse components in vibration signals are important fault features of complex machines. Sparse coding （SC） algorithm has been introduced as an impulse feature extraction method, but it could not guarantee a satisf...Impulse components in vibration signals are important fault features of complex machines. Sparse coding （SC） algorithm has been introduced as an impulse feature extraction method, but it could not guarantee a satisfactory performance in processing vibration signals with heavy background noises. In this paper, a method based on fusion sparse coding （FSC） and online dictionary learning is proposed to extract impulses efficiently. Firstly, fusion scheme of different sparse coding algorithms is presented to ensure higher reconstruction accuracy. Then, an improved online dictionary learning method using FSC scheme is established to obtain redundant dictionary and it can capture specific features of training samples and reconstruct the sparse approximation of vibration signals. Simulation shows that this method has a good performance in solving sparse coefficients and training redundant dictionary compared with other methods. Lastly, the proposed method is further applied to processing aircraft engine rotor vibration signals. Compared with other feature extraction approaches, our method can extract impulse features accurately and efficiently from heavy noisy vibration signal, which has significant supports for machinery fault detection and diagnosis.展开更多
Time-domain airborne electromagnetic(AEM)data are frequently subject to interference from various types of noise,which can reduce the data quality and affect data inversion and interpretation.Traditional denoising met...Time-domain airborne electromagnetic(AEM)data are frequently subject to interference from various types of noise,which can reduce the data quality and affect data inversion and interpretation.Traditional denoising methods primarily deal with data directly,without analyzing the data in detail;thus,the results are not always satisfactory.In this paper,we propose a method based on dictionary learning for EM data denoising.This method uses dictionary learning to perform feature analysis and to extract and reconstruct the true signal.In the process of dictionary learning,the random noise is fi ltered out as residuals.To verify the eff ectiveness of this dictionary learning approach for denoising,we use a fi xed overcomplete discrete cosine transform(ODCT)dictionary algorithm,the method-of-optimal-directions(MOD)dictionary learning algorithm,and the K-singular value decomposition(K-SVD)dictionary learning algorithm to denoise decay curves at single points and to denoise profi le data for diff erent time channels in time-domain AEM.The results show obvious diff erences among the three dictionaries for denoising AEM data,with the K-SVD dictionary achieving the best performance.展开更多
Human action recognition under complex environment is a challenging work.Recently,sparse representation has achieved excellent results of dealing with human action recognition problem under different conditions.The ma...Human action recognition under complex environment is a challenging work.Recently,sparse representation has achieved excellent results of dealing with human action recognition problem under different conditions.The main idea of sparse representation classification is to construct a general classification scheme where the training samples of each class can be considered as the dictionary to express the query class,and the minimal reconstruction error indicates its corresponding class.However,how to learn a discriminative dictionary is still a difficult work.In this work,we make two contributions.First,we build a new and robust human action recognition framework by combining one modified sparse classification model and deep convolutional neural network(CNN)features.Secondly,we construct a novel classification model which consists of the representation-constrained term and the coefficients incoherence term.Experimental results on benchmark datasets show that our modified model can obtain competitive results in comparison to other state-of-the-art models.展开更多
Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.展开更多
Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs ...Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.展开更多
Automatic Modulation Classification(AMC) is an important technology used to recognize the modulation type.A dictionary set was trained via signals with known modulation schemes in cooperative scenarios.Then we classif...Automatic Modulation Classification(AMC) is an important technology used to recognize the modulation type.A dictionary set was trained via signals with known modulation schemes in cooperative scenarios.Then we classify the modulation scheme of the signals received in the non-cooperative environment according to its sparse representation.Furthermore,we proposed a novel approach called Fast Block Coordinate descent Dictionary Learning(FBCDL).Moreover,the convergence of FBCDL was proved and we find that our proposed method achieves lower complexity.Experimental results indicate that our proposed FBCDL achieves better classification accuracy than traditional methods.展开更多
Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge.However,most data-dr...Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge.However,most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution.In fact,due to the harsh environment of industrial systems,the collected data from real industrial processes are always affected by many factors,such as the changeable operating environment,variation in the raw materials,and production indexes.These factors often cause the distributions of online monitoring data and historical training data to differ,which induces a model mismatch in the process-monitoring task.Thus,it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring.In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments,a robust transfer dictionary learning(RTDL)algorithm is proposed in this paper for industrial process monitoring.The RTDL is a synergy of representative learning and domain adaptive transfer learning.The proposed method regards historical training data and online testing data as the source domain and the target domain,respectively,in the transfer learning problem.Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework,which can reduce the distribution divergence between the source domain and target domain.In this way,a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment.Such a dictionary can effectively improve the performance of process monitoring and mode classification.Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.展开更多
To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of ...To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of Things,artificial intelligence,and big data,can build a smart environmental monitoring system.Remote sensing image classification is an important research content in ecological environmental monitoring.Remote sensing images contain rich spatial information andmulti-temporal information,but also bring challenges such as difficulty in obtaining classification labels and low classification accuracy.To solve this problem,this study develops a transductive transfer dictionary learning(TTDL)algorithm.In the TTDL,the source and target domains are transformed fromthe original sample space to a common subspace.TTDL trains a shared discriminative dictionary in this subspace,establishes associations between domains,and also obtains sparse representations of source and target domain data.To obtain an effective shared discriminative dictionary,triple-induced ordinal locality preserving term,Fisher discriminant term,and graph Laplacian regularization termare introduced into the TTDL.The triplet-induced ordinal locality preserving term on sub-space projection preserves the local structure of data in low-dimensional subspaces.The Fisher discriminant term on dictionary improves differences among different sub-dictionaries through intra-class and inter-class scatters.The graph Laplacian regularization term on sparse representation maintains the manifold structure using a semi-supervised weight graphmatrix,which can indirectly improve the discriminative performance of the dictionary.The TTDL is tested on several remote sensing image datasets and has strong discrimination classification performance.展开更多
The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This ...The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This paper investigates impulsive signals detection of a single-point defect rolling bearing and presents a novel data-driven detection approach based on dictionary learning.To overcome the effects harmonic and noise components,we propose an autoregressive-minimum entropy deconvolution model to separate harmonic and deconvolve the effect of the transmission path.To address the shortcomings of conventional sparse representation under the changeable operation environment,we propose an approach that combines K-clustering with singular value decomposition(K-SVD)and split-Bregman to extract impulsive components precisely.Via experiments on synthetic signals and real run-to-failure signals,the excellent performance for different impulsive signals detection verifies the effectiveness and robustness of the proposed approach.Meanwhile,a comparison with the state-of-the-art methods is illustrated,which shows that the proposed approach can provide more accurate detected impulsive signals.展开更多
Sparse-representation-based single-channel source separation,which aims to recover each source’s signal using its corresponding sub-dictionary,has attracted many scholars’attention.The basic premise of this model is...Sparse-representation-based single-channel source separation,which aims to recover each source’s signal using its corresponding sub-dictionary,has attracted many scholars’attention.The basic premise of this model is that each sub-dictionary possesses discriminative information about its corresponding source,and this information can be used to recover almost every sample from that source.However,in a more general sense,the samples from a source are composed not only of discriminative information but also common information shared with other sources.This paper proposes learning a discriminative high-fidelity dictionary to improve the separation performance.The innovations are threefold.Firstly,an extra sub-dictionary was combined into a conventional union dictionary to ensure that the source-specific sub-dictionaries can capture only the purely discriminative information for their corresponding sources because the common information is collected in the additional sub-dictionary.Secondly,a task-driven learning algorithm is designed to optimize the new union dictionary and a set of weights that indicate how much of the common information should be allocated to each source.Thirdly,a source separation scheme based on the learned dictionary is presented.Experimental results on a human speech dataset yield evidence that our algorithm can achieve better separation performance than either state-of-the-art or traditional algorithms.展开更多
Considering the sparsity of hyperspectral images(HSIs),dictionary learning frameworks have been widely used in the field of unsupervised spectral unmixing.However,it is worth mentioning here that existing dictionary l...Considering the sparsity of hyperspectral images(HSIs),dictionary learning frameworks have been widely used in the field of unsupervised spectral unmixing.However,it is worth mentioning here that existing dictionary learning method-based unmixing methods are found to be short of robustness in noisy contexts.To improve the performance,this study specifically puts forward a new unsupervised spectral unmixing solution.For the reason that the solution only functions in a condition that both endmembers and the abundances meet non-negative con-straints,a model is built to solve the unsupervised spectral un-mixing problem on the account of the dictionary learning me-thod.To raise the screening accuracy of final members,a new form of the target function is introduced into dictionary learning practice,which is conducive to the growing robustness of noisy HSI statistics.Then,by introducing the total variation(TV)terms into the proposed spectral unmixing based on robust nonnega-tive dictionary learning(RNDLSU),the context information under HSI space is to be cited as prior knowledge to compute the abundances when performing sparse unmixing operations.Ac-cording to the final results of the experiment,this method makes favorable performance under varying noise conditions,which is especially true under low signal to noise conditions.展开更多
To address the issue of finegrained classification of Internet multimedia traffic from a Quality of Service(QoS) perspective with a suitable granularity, this paper defines a new set of QoS classes and presents a modi...To address the issue of finegrained classification of Internet multimedia traffic from a Quality of Service(QoS) perspective with a suitable granularity, this paper defines a new set of QoS classes and presents a modified K-Singular Value Decomposition(K-SVD) method for multimedia identification. After analyzing several instances of typical Internet multimedia traffic captured in a campus network, this paper defines a new set of QoS classes according to the difference in downstream/upstream rates and proposes a modified K-SVD method that can automatically search for underlying structural patterns in the QoS characteristic space. We define bagQoS-words as the set of specific QoS local patterns, which can be expressed by core QoS characteristics. After the dictionary is constructed with an excess quantity of bag-QoSwords, Locality Constrained Feature Coding(LCFC) features of QoS classes are extracted. By associating a set of characteristics with a percentage of error, an objective function is formulated. In accordance with the modified K-SVD, Internet multimedia traffic can be classified into a corresponding QoS class with a linear Support Vector Machines(SVM) clas-sifier. Our experimental results demonstrate the feasibility of the proposed classification method.展开更多
Enhancing seismic resolution is a key component in seismic data processing, which plays a valuable role in raising the prospecting accuracy of oil reservoirs. However, in noisy situations, existing resolution enhancem...Enhancing seismic resolution is a key component in seismic data processing, which plays a valuable role in raising the prospecting accuracy of oil reservoirs. However, in noisy situations, existing resolution enhancement methods are difficult to yield satisfactory processing outcomes for reservoir characterization. To solve this problem, we develop a new approach for simultaneous denoising and resolution enhancement of seismic data based on convolution dictionary learning. First, an elastic convolution dictionary learning algorithm is presented to efficiently learn a convolution dictionary with stronger representation capability from the noisy data to be processed. Specifically, the algorithm introduces the elastic L1/2 norm as a sparsity constraint and employs a steepest gradient descent strategy to efficiently solve the frequency-domain linear system with substantial computational cost in a half-quadratic splitting framework. Then, based on the learned convolution dictionary, a weighted convolutional sparse representation paradigm is designed to encode the noisy data to acquire an optimal sparse approximation of the effective signal. Subsequently, a high-resolution dictionary with a broadband spectrum is constructed by the proposed parameter scaling strategy and matched filtering technique on the basis of atomic spectrum modeling. Finally, the optimal sparse approximation of the effective signal and the constructed high-resolution dictionary are used for data reconstruction to obtain the seismic signal with high resolution and high signal-to-noise ratio. Synthetic and field dataset examples are executed to check the effectiveness and reliability of the developed method. The results indicate that this method has a more competitive performance in seismic applications compared with the conventional deconvolution and spectral whitening methods.展开更多
文摘Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.
基金supported by the Natural Science Foundation of Wenzhou University of Technology,China(Grant No.:ky202211).
文摘Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.
文摘Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist.
基金supported by the Henan Province Key R&D Project under Grant 241111210400the Henan Provincial Science and Technology Research Project under Grants 252102211047,252102211062,252102211055 and 232102210069+2 种基金the Jiangsu Provincial Scheme Double Initiative Plan JSS-CBS20230474,the XJTLU RDF-21-02-008the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205the Higher Education Teaching Reform Research and Practice Project of Henan Province under Grant 2024SJGLX0126。
文摘Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.
基金the National Natural Science Foundation of China(No.61861023)the Yunnan Fundamental Research Project(No.202301AT070452)。
文摘Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstruction algorithms usually used nonadaptive sparsifying transforms,resulting in a limited reconstruction accuracy.Therefore,we proposed a new model for accurate parallel MRI reconstruction by combining the L0 norm regularization term based on the efficient sum of outer products dictionary learning(SOUPDIL)with the SENSE model,called SOUPDIL-SENSE.The SOUPDIL-SENSE model is mainly solved by utilizing the variable splitting and alternating direction method of multipliers techniques.The experimental results on four human datasets show that the proposed algorithm effectively promotes the image sparsity,eliminates the noise and artifacts of the reconstructed images,and improves the reconstruction accuracy.
基金supported by Western Research Interdisciplinary Initiative R6259A03.
文摘Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.
基金Project supported by the China Outstanding Youth Science Fund Project of the National Natural Science Foundation“Multi-scale Oil and Gas Seepage Mechanics”(No.52122402)Key Project of the National Natural Science Foundation“Scientific Issues on Efficient Production of Gas Reservoirs with Ultra-deep and Ultra-high Pressure”(No.52034010)Outstanding Youth Fund Project of the Shandong Natural Science Foundation“Multi-scale Seepage Theory for Unconventional Reservoirs”(No.ZR2022JQ23).
文摘An accurate and comprehensive understanding of shale pore structure is fundamental and critical for accurate reserves evaluation and efficient hydrocarbon development.Thus,by taking the shale of Paleogene Eocene Shahejie Formation in the Jiyang Depression,Bohai Bay Basin,as an example,the 2D and 3D multi-resolution images of the shale microstructure are obtained by multiple imaging technologies,including X-ray computed tomography,large-field scanning electron microscopy,scanning electron microscopy and focused ion beam scanning electron microscopy.By integrating image processing and machine learning algorithms,the shale pore structure is characterized at a single scale and multi scales.The results are obtained as follows.First,the shale pore space in the study area is mainly composed of microfractures,inorganic pores,organic matters and organic pores,and exclusively shows multi-scale characteristics.Second,there are various types of inorganic pores,and abundant dissolution pores;organic matters are distributed as strips and patches,and no organic pores are found in some organic matters.Third,pores with radius less than 20 nm account for 25%,those with radius between 20 and 50 nm account for 19%,those with radius between 50 and 100 nm account for 29%,those with radius between 100 and 500 nm account for 14%,those with radius between 500 nm and 20 mm account for 11%,and those with radius between 20 and 50 mm account for 2%.Fourth,the organic pores are less connected than the inorganic pores.The connectivity between organic pores and inorganic pores plays a crucial role in hydrocarbon migration,and microfractures control fluid flow channels.Fifth,pores with radius less than 50 nm are dominantly organic pores,those with radius between 50 and 500 nm are mainly organic and inorganic pores,and microfractures mainly contribute to the pores with radius more than 500 nm.It is concluded that a single imaging experiment cannot accurately and comprehensively reveal the multi-scale micro pore structure of a shale reservoir.Through integration of multiple imaging technologies and machine learning algorithms,the shale pore structure can be recognized and characterized at both single scale and multi scales.The proposed new method provides accurate and comprehensive information of multi-scale pore structures.
基金supported by the National Natural Science Foundation of China (No. 51201182)
文摘Impulse components in vibration signals are important fault features of complex machines. Sparse coding （SC） algorithm has been introduced as an impulse feature extraction method, but it could not guarantee a satisfactory performance in processing vibration signals with heavy background noises. In this paper, a method based on fusion sparse coding （FSC） and online dictionary learning is proposed to extract impulses efficiently. Firstly, fusion scheme of different sparse coding algorithms is presented to ensure higher reconstruction accuracy. Then, an improved online dictionary learning method using FSC scheme is established to obtain redundant dictionary and it can capture specific features of training samples and reconstruct the sparse approximation of vibration signals. Simulation shows that this method has a good performance in solving sparse coefficients and training redundant dictionary compared with other methods. Lastly, the proposed method is further applied to processing aircraft engine rotor vibration signals. Compared with other feature extraction approaches, our method can extract impulse features accurately and efficiently from heavy noisy vibration signal, which has significant supports for machinery fault detection and diagnosis.
基金financially supported the Strategic Priority Research Program of the Chinese Academy of Sciences (No. XDA14020102)the National Natural Science Foundation of China (Nos. 41774125,41530320 and 41804098)the Key National Research Project of China (Nos. 2016YFC0303100,2017YFC0601900)。
文摘Time-domain airborne electromagnetic(AEM)data are frequently subject to interference from various types of noise,which can reduce the data quality and affect data inversion and interpretation.Traditional denoising methods primarily deal with data directly,without analyzing the data in detail;thus,the results are not always satisfactory.In this paper,we propose a method based on dictionary learning for EM data denoising.This method uses dictionary learning to perform feature analysis and to extract and reconstruct the true signal.In the process of dictionary learning,the random noise is fi ltered out as residuals.To verify the eff ectiveness of this dictionary learning approach for denoising,we use a fi xed overcomplete discrete cosine transform(ODCT)dictionary algorithm,the method-of-optimal-directions(MOD)dictionary learning algorithm,and the K-singular value decomposition(K-SVD)dictionary learning algorithm to denoise decay curves at single points and to denoise profi le data for diff erent time channels in time-domain AEM.The results show obvious diff erences among the three dictionaries for denoising AEM data,with the K-SVD dictionary achieving the best performance.
基金This research was funded by the National Natural Science Foundation of China(21878124,31771680 and 61773182).
文摘Human action recognition under complex environment is a challenging work.Recently,sparse representation has achieved excellent results of dealing with human action recognition problem under different conditions.The main idea of sparse representation classification is to construct a general classification scheme where the training samples of each class can be considered as the dictionary to express the query class,and the minimal reconstruction error indicates its corresponding class.However,how to learn a discriminative dictionary is still a difficult work.In this work,we make two contributions.First,we build a new and robust human action recognition framework by combining one modified sparse classification model and deep convolutional neural network(CNN)features.Secondly,we construct a novel classification model which consists of the representation-constrained term and the coefficients incoherence term.Experimental results on benchmark datasets show that our modified model can obtain competitive results in comparison to other state-of-the-art models.
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.
基金This work was supported by National Natural Science Foundation of China(NSFC)under Grant No.61771299,No.61771322,No.61375015,No.61301027.
文摘Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.
基金supported in part by the National Natural Science Foundation of China with grants 61525101,91746301,61631003,61601055the Shenzhen Fundamental Research Fund with grant KQTD2015033114415450
文摘Automatic Modulation Classification(AMC) is an important technology used to recognize the modulation type.A dictionary set was trained via signals with known modulation schemes in cooperative scenarios.Then we classify the modulation scheme of the signals received in the non-cooperative environment according to its sparse representation.Furthermore,we proposed a novel approach called Fast Block Coordinate descent Dictionary Learning(FBCDL).Moreover,the convergence of FBCDL was proved and we find that our proposed method achieves lower complexity.Experimental results indicate that our proposed FBCDL achieves better classification accuracy than traditional methods.
基金This work was supported in part by the National Natural Science Foundation of China(61988101)in part by the National Key R&D Program of China(2018YFB1701100).
文摘Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge.However,most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution.In fact,due to the harsh environment of industrial systems,the collected data from real industrial processes are always affected by many factors,such as the changeable operating environment,variation in the raw materials,and production indexes.These factors often cause the distributions of online monitoring data and historical training data to differ,which induces a model mismatch in the process-monitoring task.Thus,it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring.In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments,a robust transfer dictionary learning(RTDL)algorithm is proposed in this paper for industrial process monitoring.The RTDL is a synergy of representative learning and domain adaptive transfer learning.The proposed method regards historical training data and online testing data as the source domain and the target domain,respectively,in the transfer learning problem.Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework,which can reduce the distribution divergence between the source domain and target domain.In this way,a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment.Such a dictionary can effectively improve the performance of process monitoring and mode classification.Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.
基金This research was funded in part by the Natural Science Foundation of Jiangsu Province under Grant BK 20211333by the Science and Technology Project of Changzhou City(CE20215032).
文摘To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of Things,artificial intelligence,and big data,can build a smart environmental monitoring system.Remote sensing image classification is an important research content in ecological environmental monitoring.Remote sensing images contain rich spatial information andmulti-temporal information,but also bring challenges such as difficulty in obtaining classification labels and low classification accuracy.To solve this problem,this study develops a transductive transfer dictionary learning(TTDL)algorithm.In the TTDL,the source and target domains are transformed fromthe original sample space to a common subspace.TTDL trains a shared discriminative dictionary in this subspace,establishes associations between domains,and also obtains sparse representations of source and target domain data.To obtain an effective shared discriminative dictionary,triple-induced ordinal locality preserving term,Fisher discriminant term,and graph Laplacian regularization termare introduced into the TTDL.The triplet-induced ordinal locality preserving term on sub-space projection preserves the local structure of data in low-dimensional subspaces.The Fisher discriminant term on dictionary improves differences among different sub-dictionaries through intra-class and inter-class scatters.The graph Laplacian regularization term on sparse representation maintains the manifold structure using a semi-supervised weight graphmatrix,which can indirectly improve the discriminative performance of the dictionary.The TTDL is tested on several remote sensing image datasets and has strong discrimination classification performance.
基金This work was supported by the National Natural Science Foundation of China(61773080,61633005)the Fundamental Research Funds for the Central Universities(2019CDYGZD001)Scientific Reserve Talent Programs of Chongqing University(cqu2018CDHB1B04).
文摘The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This paper investigates impulsive signals detection of a single-point defect rolling bearing and presents a novel data-driven detection approach based on dictionary learning.To overcome the effects harmonic and noise components,we propose an autoregressive-minimum entropy deconvolution model to separate harmonic and deconvolve the effect of the transmission path.To address the shortcomings of conventional sparse representation under the changeable operation environment,we propose an approach that combines K-clustering with singular value decomposition(K-SVD)and split-Bregman to extract impulsive components precisely.Via experiments on synthetic signals and real run-to-failure signals,the excellent performance for different impulsive signals detection verifies the effectiveness and robustness of the proposed approach.Meanwhile,a comparison with the state-of-the-art methods is illustrated,which shows that the proposed approach can provide more accurate detected impulsive signals.
基金This work was supported by the National Natural Science Foundation of China(62001489)the scientific research planning project of National University of Defense Technology(JS19-04).
文摘Sparse-representation-based single-channel source separation,which aims to recover each source’s signal using its corresponding sub-dictionary,has attracted many scholars’attention.The basic premise of this model is that each sub-dictionary possesses discriminative information about its corresponding source,and this information can be used to recover almost every sample from that source.However,in a more general sense,the samples from a source are composed not only of discriminative information but also common information shared with other sources.This paper proposes learning a discriminative high-fidelity dictionary to improve the separation performance.The innovations are threefold.Firstly,an extra sub-dictionary was combined into a conventional union dictionary to ensure that the source-specific sub-dictionaries can capture only the purely discriminative information for their corresponding sources because the common information is collected in the additional sub-dictionary.Secondly,a task-driven learning algorithm is designed to optimize the new union dictionary and a set of weights that indicate how much of the common information should be allocated to each source.Thirdly,a source separation scheme based on the learned dictionary is presented.Experimental results on a human speech dataset yield evidence that our algorithm can achieve better separation performance than either state-of-the-art or traditional algorithms.
基金supported by the National Natural Science Foundation of China(61801513).
文摘Considering the sparsity of hyperspectral images(HSIs),dictionary learning frameworks have been widely used in the field of unsupervised spectral unmixing.However,it is worth mentioning here that existing dictionary learning method-based unmixing methods are found to be short of robustness in noisy contexts.To improve the performance,this study specifically puts forward a new unsupervised spectral unmixing solution.For the reason that the solution only functions in a condition that both endmembers and the abundances meet non-negative con-straints,a model is built to solve the unsupervised spectral un-mixing problem on the account of the dictionary learning me-thod.To raise the screening accuracy of final members,a new form of the target function is introduced into dictionary learning practice,which is conducive to the growing robustness of noisy HSI statistics.Then,by introducing the total variation(TV)terms into the proposed spectral unmixing based on robust nonnega-tive dictionary learning(RNDLSU),the context information under HSI space is to be cited as prior knowledge to compute the abundances when performing sparse unmixing operations.Ac-cording to the final results of the experiment,this method makes favorable performance under varying noise conditions,which is especially true under low signal to noise conditions.
基金supported in part by the National Natural Science Foundation of China (NO. 61401004, 61271233, 60972038)Plan of introduction and cultivation of university leading talents in Anhui (No.gxfxZ D2016013)+3 种基金the Natural Science Foundation of the Higher Education Institutions of Anhui Province, China (No. KJ2010B357)Startup Project of Anhui Normal University Doctor Scientific Research (No.2016XJJ129)the US National Science Foundation under grants CNS1702957 and ACI-1642133the Wireless Engineering Research and Education Center at Auburn University
文摘To address the issue of finegrained classification of Internet multimedia traffic from a Quality of Service(QoS) perspective with a suitable granularity, this paper defines a new set of QoS classes and presents a modified K-Singular Value Decomposition(K-SVD) method for multimedia identification. After analyzing several instances of typical Internet multimedia traffic captured in a campus network, this paper defines a new set of QoS classes according to the difference in downstream/upstream rates and proposes a modified K-SVD method that can automatically search for underlying structural patterns in the QoS characteristic space. We define bagQoS-words as the set of specific QoS local patterns, which can be expressed by core QoS characteristics. After the dictionary is constructed with an excess quantity of bag-QoSwords, Locality Constrained Feature Coding(LCFC) features of QoS classes are extracted. By associating a set of characteristics with a percentage of error, an objective function is formulated. In accordance with the modified K-SVD, Internet multimedia traffic can be classified into a corresponding QoS class with a linear Support Vector Machines(SVM) clas-sifier. Our experimental results demonstrate the feasibility of the proposed classification method.
基金This work is supported by the Laoshan National Laboratoryof ScienceandTechnologyFoundation(No.LSKj202203400)the National Natural Science Foundation of China(No.41874146).
文摘Enhancing seismic resolution is a key component in seismic data processing, which plays a valuable role in raising the prospecting accuracy of oil reservoirs. However, in noisy situations, existing resolution enhancement methods are difficult to yield satisfactory processing outcomes for reservoir characterization. To solve this problem, we develop a new approach for simultaneous denoising and resolution enhancement of seismic data based on convolution dictionary learning. First, an elastic convolution dictionary learning algorithm is presented to efficiently learn a convolution dictionary with stronger representation capability from the noisy data to be processed. Specifically, the algorithm introduces the elastic L1/2 norm as a sparsity constraint and employs a steepest gradient descent strategy to efficiently solve the frequency-domain linear system with substantial computational cost in a half-quadratic splitting framework. Then, based on the learned convolution dictionary, a weighted convolutional sparse representation paradigm is designed to encode the noisy data to acquire an optimal sparse approximation of the effective signal. Subsequently, a high-resolution dictionary with a broadband spectrum is constructed by the proposed parameter scaling strategy and matched filtering technique on the basis of atomic spectrum modeling. Finally, the optimal sparse approximation of the effective signal and the constructed high-resolution dictionary are used for data reconstruction to obtain the seismic signal with high resolution and high signal-to-noise ratio. Synthetic and field dataset examples are executed to check the effectiveness and reliability of the developed method. The results indicate that this method has a more competitive performance in seismic applications compared with the conventional deconvolution and spectral whitening methods.
