Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurr...Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.展开更多
This study introduces a pre-orthogonal adaptive Fourier decomposition(POAFD)to obtain approximations and numerical solutions to the fractional Laplacian initial value problem and the extension problem of Caffarelli an...This study introduces a pre-orthogonal adaptive Fourier decomposition(POAFD)to obtain approximations and numerical solutions to the fractional Laplacian initial value problem and the extension problem of Caffarelli and Silvestre(generalized Poisson equation).As a first step,the method expands the initial data function into a sparse series of the fundamental solutions with fast convergence,and,as a second step,makes use of the semigroup or the reproducing kernel property of each of the expanding entries.Experiments show the effectiveness and efficiency of the proposed series solutions.展开更多
Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many scholars.Inspired by the self-nonself disc...Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many scholars.Inspired by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network privacy.Therefore,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called AttNetNRI.Specifically,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept private.Moreover,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social networks.To evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social networks.The experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding parts.The experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.展开更多
Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in ...Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.展开更多
Deep learning has been a catalyst for a transformative revo-lution in machine learning and computer vision in the past decade.Within these research domains,methods grounded in deep learning have exhibited exceptional ...Deep learning has been a catalyst for a transformative revo-lution in machine learning and computer vision in the past decade.Within these research domains,methods grounded in deep learning have exhibited exceptional performance across a spectrum of tasks.The success of deep learning methods can be attributed to their capability to derive potent representations from data,integral for a myriad of downstream applications.These representations encapsulate the intrinsic structure,fea-tures,or latent variables characterising the underlying statistics of visual data.Despite these achievements,the challenge per-sists in effectively conducting representation learning of visual data with deep models,particularly when confronted with vast and noisy datasets.This special issue is a dedicated platform for researchers worldwide to disseminate their latest,high-quality articles,aiming to enhance readers'comprehension of the principles,limitations,and diverse applications of repre-sentation learning in computer vision.展开更多
Edge devices,due to their limited computational and storage resources,often require the use of compilers for program optimization.Therefore,ensuring the security and reliability of these compilers is of paramount impo...Edge devices,due to their limited computational and storage resources,often require the use of compilers for program optimization.Therefore,ensuring the security and reliability of these compilers is of paramount importance in the emerging field of edge AI.One widely used testing method for this purpose is fuzz testing,which detects bugs by inputting random test cases into the target program.However,this process consumes significant time and resources.To improve the efficiency of compiler fuzz testing,it is common practice to utilize test case prioritization techniques.Some researchers use machine learning to predict the code coverage of test cases,aiming to maximize the test capability for the target compiler by increasing the overall predicted coverage of the test cases.Nevertheless,these methods can only forecast the code coverage of the compiler at a specific optimization level,potentially missing many optimization-related bugs.In this paper,we introduce C-CORE(short for Clustering by Code Representation),the first framework to prioritize test cases according to their code representations,which are derived directly from the source codes.This approach avoids being limited to specific compiler states and extends to a broader range of compiler bugs.Specifically,we first train a scaled pre-trained programming language model to capture as many common features as possible from the test cases generated by a fuzzer.Using this pre-trained model,we then train two downstream models:one for predicting the likelihood of triggering a bug and another for identifying code representations associated with bugs.Subsequently,we cluster the test cases according to their code representations and select the highest-scoring test case from each cluster as the high-quality test case.This reduction in redundant testing cases leads to time savings.Comprehensive evaluation results reveal that code representations are better at distinguishing test capabilities,and C-CORE significantly enhances testing efficiency.Across four datasets,C-CORE increases the average of the percentage of faults detected(APFD)value by 0.16 to 0.31 and reduces test time by over 50% in 46% of cases.When compared to the best results from approaches using predicted code coverage,C-CORE improves the APFD value by 1.1% to 12.3% and achieves an overall time-saving of 159.1%.展开更多
With the increasing demand for electrical services,wind farm layout optimization has been one of the biggest challenges that we have to deal with.Despite the promising performance of the heuristic algorithm on the rou...With the increasing demand for electrical services,wind farm layout optimization has been one of the biggest challenges that we have to deal with.Despite the promising performance of the heuristic algorithm on the route network design problem,the expressive capability and search performance of the algorithm on multi-objective problems remain unexplored.In this paper,the wind farm layout optimization problem is defined.Then,a multi-objective algorithm based on Graph Neural Network(GNN)and Variable Neighborhood Search(VNS)algorithm is proposed.GNN provides the basis representations for the following search algorithm so that the expressiveness and search accuracy of the algorithm can be improved.The multi-objective VNS algorithm is put forward by combining it with the multi-objective optimization algorithm to solve the problem with multiple objectives.The proposed algorithm is applied to the 18-node simulation example to evaluate the feasibility and practicality of the developed optimization strategy.The experiment on the simulation example shows that the proposed algorithm yields a reduction of 6.1% in Point of Common Coupling(PCC)over the current state-of-the-art algorithm,which means that the proposed algorithm designs a layout that improves the quality of the power supply by 6.1%at the same cost.The ablation experiments show that the proposed algorithm improves the power quality by more than 8.6% and 7.8% compared to both the original VNS algorithm and the multi-objective VNS algorithm.展开更多
The systematic method for constructing Lewis representations is a method for representing chemical bonds between atoms in a molecule. It uses symbols to represent the valence electrons of the atoms involved in the bon...The systematic method for constructing Lewis representations is a method for representing chemical bonds between atoms in a molecule. It uses symbols to represent the valence electrons of the atoms involved in the bond. Using a number of rules in a defined order, it is often better suited to complicated cases than the Lewis representation of atoms. This method allows us to determine the formal charge and oxidation number of each atom in the edifice more efficiently than other methods.展开更多
The research consistently highlights the gender disparity in cybersecurity leadership roles, necessitating targeted interventions. Biased recruitment practices, limited STEM education opportunities for girls, and work...The research consistently highlights the gender disparity in cybersecurity leadership roles, necessitating targeted interventions. Biased recruitment practices, limited STEM education opportunities for girls, and workplace culture contribute to this gap. Proposed solutions include addressing biased recruitment through gender-neutral language and blind processes, promoting STEM education for girls to increase qualified female candidates, and fostering inclusive workplace cultures with mentorship and sponsorship programs. Gender parity is crucial for the industry’s success, as embracing diversity enables the cybersecurity sector to leverage various perspectives, drive innovation, and effectively combat cyber threats. Achieving this balance is not just about fairness but also a strategic imperative. By embracing concerted efforts towards gender parity, we can create a more resilient and impactful cybersecurity landscape, benefiting industry and society.展开更多
Sparse representation plays an important role in the research of face recognition.As a deformable sample classification task,face recognition is often used to test the performance of classification algorithms.In face ...Sparse representation plays an important role in the research of face recognition.As a deformable sample classification task,face recognition is often used to test the performance of classification algorithms.In face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition accuracy.Essentially,there may be significant differences between different image samples of the same face,which makes image classification very difficult.Therefore,how to build a robust virtual image representation becomes a vital issue.To solve the above problems,this paper proposes a novel image classification algorithm.First,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual sample.Second,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,respectively.After obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test sample.These two distances are converted into distance scores.Finally,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual image.The fused score will determine the final classification result.The experimental results show that the proposed method outperforms other typical sparse representation classification methods.展开更多
The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using...The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using the complex momentum representation method applied to deformation and continuum coupling.By examining the evolution of the weakly bound and resonant levels near the Fermi surface,s–d orbital reversals and certain prolate deformations were observed.In addition,by analyzing the evolution of the occupation probabilities and density distributions occupied by valence neutrons,we found that the ground state of15B did not exhibit a halo and the ground states of17B and19B exhibited halos at 0.6≤β2≤0.7 and0.3≤β2≤0.7,respectively.The low-l components in the valence levels that are weakly bound or embedded in the continuous spectrum lead to halo formation.展开更多
Approaches for predicting low-lying resonances,uniformly treating bound,and resonant levels have been a long-standing goal in nuclear theory.Accordingly,we explored the viability of the complex momentum representation...Approaches for predicting low-lying resonances,uniformly treating bound,and resonant levels have been a long-standing goal in nuclear theory.Accordingly,we explored the viability of the complex momentum representation(CMR)approach coupled with new potentials.We focus on predicting the energy of the low-lying 2p_(3∕2)resonance in 17 O,which is critical for s-process nucleosynthesis and missing in previous theoretical research.Using a Woods-Saxon potential based on the Koning-Delaroche optical model and constrained by the experimental one-neutron separation energy,we successfully predicted the resonant energy of this level for the first time.Our predictions of the bound levels and 1d_(3∕2)resonance agree well with the measurement results.Additionally,we utilize this approach to study the near-threshold resonances that play a role when forming a two-neutron halo in^(29,31)F.We found that the CMR-based predictions of the bound-level energies and unbound 1f7∕2 level agree well with the results obtained using the scattering phase shift method.Subsequently,we successfully found a solution for the 2p_(3∕2)resonance with energy just above the threshold,which is decisive for halo formation.展开更多
Failuremode and effects analysis(FMEA)is a widely used safety assessmentmethod inmany fields.Z-number was previously applied in FMEA since it can take both possibility and reliability of information into consideration...Failuremode and effects analysis(FMEA)is a widely used safety assessmentmethod inmany fields.Z-number was previously applied in FMEA since it can take both possibility and reliability of information into consideration.However,the use of fuzzy weighted mean to integrate Z-valuations may have some drawbacks and is not suitable for some situations.In this paper,an improved method is proposed based on Z-numbers and the graded mean integration representation(GMIR)to deal with the uncertain information in FMEA.First,Z-numbers are constructed based on the evaluations of risk factors O,S,D for each failure mode by different experts.Second,weights of the three risk factors and experts are determined.Third,the integration representations of Z-numbers are obtained by a newmethod based on the GMIRmethod.Finally,risk priorities of the failure modes are derived considering the weights of experts and risk factors.Two examples and a case study are given to show the use of the proposed method and comparison with other methods.The results show that the proposed method is more reasonable,universal and simple in calculation.展开更多
The traditional malware research is mainly based on its recognition and detection as a breakthrough point,without focusing on its propagation trends or predicting the subsequently infected nodes.The complexity of netw...The traditional malware research is mainly based on its recognition and detection as a breakthrough point,without focusing on its propagation trends or predicting the subsequently infected nodes.The complexity of network structure,diversity of network nodes,and sparsity of data all pose difficulties in predicting propagation.This paper proposes a malware propagation prediction model based on representation learning and Graph Convolutional Networks(GCN)to address the aforementioned problems.First,to solve the problem of the inaccuracy of infection intensity calculation caused by the sparsity of node interaction behavior data in the malware propagation network,a mechanism based on a tensor to mine the infection intensity among nodes is proposed to retain the network structure information.The influence of the relationship between nodes on the infection intensity is also analyzed.Second,given the diversity and complexity of the content and structure of infected and normal nodes in the network,considering the advantages of representation learning in data feature extraction,the corresponding representation learning method is adopted for the characteristics of infection intensity among nodes.This can efficiently calculate the relationship between entities and relationships in low dimensional space to achieve the goal of low dimensional,dense,and real-valued representation learning for the characteristics of propagation spatial data.We also design a new method,Tensor2vec,to learn the potential structural features of malware propagation.Finally,considering the convolution ability of GCN for non-Euclidean data,we propose a dynamic prediction model of malware propagation based on representation learning and GCN to solve the time effectiveness problem of the malware propagation carrier.The experimental results show that the proposed model can effectively predict the behaviors of the nodes in the network and discover the influence of different characteristics of nodes on the malware propagation situation.展开更多
Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts ...Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic information.Therefore,there is ample room for improvement in terms of detection precision.To solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called GRATDet.The method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample data.Each line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the contract.Finally,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability detection.The effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.展开更多
In this study,application of the spectral representation method for generation of endurance time excitation functions is introduced.Using this method,the intensifying acceleration time series is generated so that its ...In this study,application of the spectral representation method for generation of endurance time excitation functions is introduced.Using this method,the intensifying acceleration time series is generated so that its acceleration response spectrum in any desired time duration is compatible with a time-scaled predefined acceleration response spectrum.For this purpose,simulated stationary acceleration time series is multiplied by the time dependent linear modulation function,then using a simple iterative scheme,it is forced to match a target acceleration response spectrum.It is shown that the generated samples have excellent conformity in low frequency,which is useful for nonlinear endurance time analysis.In the second part of this study,it is shown that this procedure can be extended to generate a set of spatially correlated endurance time excitation functions.This makes it possible to assess the performance of long structures under multi-support seismic excitation using endurance time analysis.展开更多
Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency o...Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.展开更多
Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,langua...Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,language,gender,and personality.These variations in speaker-specific properties may hamper the performance of standard representations in downstream tasks such as speech emotion recognition(SER).This study demonstrates the significance of speaker-specific speech characteristics and how considering them can be leveraged to improve the performance of SER models.In the proposed approach,two wav2vec-based modules(a speaker-identification network and an emotion classification network)are trained with the Arcface loss.The speaker-identification network has a single attention block to encode an input audio waveform into a speaker-specific representation.The emotion classification network uses a wav2vec 2.0-backbone as well as four attention blocks to encode the same input audio waveform into an emotion representation.These two representations are then fused into a single vector representation containing emotion and speaker-specific information.Experimental results showed that the use of speaker-specific characteristics improves SER performance.Additionally,combining these with an angular marginal loss such as the Arcface loss improves intra-class compactness while increasing inter-class separability,as demonstrated by the plots of t-distributed stochastic neighbor embeddings(t-SNE).The proposed approach outperforms previous methods using similar training strategies,with a weighted accuracy(WA)of 72.14%and unweighted accuracy(UA)of 72.97%on the Interactive Emotional Dynamic Motion Capture(IEMOCAP)dataset.This demonstrates its effectiveness and potential to enhance human-machine interaction through more accurate emotion recognition in speech.展开更多
Unconstrained face images are interfered by many factors such as illumination,posture,expression,occlusion,age,accessories and so on,resulting in the randomness of the noise pollution implied in the original samples.I...Unconstrained face images are interfered by many factors such as illumination,posture,expression,occlusion,age,accessories and so on,resulting in the randomness of the noise pollution implied in the original samples.In order to improve the sample quality,a weighted block cooperative sparse representation algorithm is proposed based on visual saliency dictionary.First,the algorithm uses the biological visual attention mechanism to quickly and accurately obtain the face salient target and constructs the visual salient dictionary.Then,a block cooperation framework is presented to perform sparse coding for different local structures of human face,and the weighted regular term is introduced in the sparse representation process to enhance the identification of information hidden in the coding coefficients.Finally,by synthesising the sparse representation results of all visual salient block dictionaries,the global coding residual is obtained and the class label is given.The experimental results on four databases,that is,AR,extended Yale B,LFW and PubFig,indicate that the combination of visual saliency dictionary,block cooperative sparse representation and weighted constraint coding can effectively enhance the accuracy of sparse representation of the samples to be tested and improve the performance of unconstrained face recognition.展开更多
Biological slices are an effective tool for studying the physiological structure and evolutionmechanism of biological systems.However,due to the complexity of preparation technology and the presence of many uncontroll...Biological slices are an effective tool for studying the physiological structure and evolutionmechanism of biological systems.However,due to the complexity of preparation technology and the presence of many uncontrollable factors during the preparation processing,leads to problems such as difficulty in preparing slice images and breakage of slice images.Therefore,we proposed a biological slice image small-scale corruption inpainting algorithm with interpretability based on multi-layer deep sparse representation,achieving the high-fidelity reconstruction of slice images.We further discussed the relationship between deep convolutional neural networks and sparse representation,ensuring the high-fidelity characteristic of the algorithm first.A novel deep wavelet dictionary is proposed that can better obtain image prior and possess learnable feature.And multi-layer deep sparse representation is used to implement dictionary learning,acquiring better signal expression.Compared with methods such as NLABH,Shearlet,Partial Differential Equation(PDE),K-Singular Value Decomposition(K-SVD),Convolutional Sparse Coding,and Deep Image Prior,the proposed algorithm has better subjective reconstruction and objective evaluation with small-scale image data,which realized high-fidelity inpainting,under the condition of small-scale image data.And theOn2-level time complexitymakes the proposed algorithm practical.The proposed algorithm can be effectively extended to other cross-sectional image inpainting problems,such as magnetic resonance images,and computed tomography images.展开更多
基金the National Natural Science Founda-tion of China(62062062)hosted by Gulila Altenbek.
文摘Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.
基金supported by the Science and Technology Development Fund of Macao SAR(FDCT0128/2022/A,0020/2023/RIB1,0111/2023/AFJ,005/2022/ALC)the Shandong Natural Science Foundation of China(ZR2020MA004)+2 种基金the National Natural Science Foundation of China(12071272)the MYRG 2018-00168-FSTZhejiang Provincial Natural Science Foundation of China(LQ23A010014).
文摘This study introduces a pre-orthogonal adaptive Fourier decomposition(POAFD)to obtain approximations and numerical solutions to the fractional Laplacian initial value problem and the extension problem of Caffarelli and Silvestre(generalized Poisson equation).As a first step,the method expands the initial data function into a sparse series of the fundamental solutions with fast convergence,and,as a second step,makes use of the semigroup or the reproducing kernel property of each of the expanding entries.Experiments show the effectiveness and efficiency of the proposed series solutions.
基金supported by the National Natural Science Foundation of China(Nos.62006001,62372001)the Natural Science Foundation of Chongqing City(Grant No.CSTC2021JCYJ-MSXMX0002).
文摘Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many scholars.Inspired by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network privacy.Therefore,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called AttNetNRI.Specifically,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept private.Moreover,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social networks.To evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social networks.The experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding parts.The experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.
文摘Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.
文摘Deep learning has been a catalyst for a transformative revo-lution in machine learning and computer vision in the past decade.Within these research domains,methods grounded in deep learning have exhibited exceptional performance across a spectrum of tasks.The success of deep learning methods can be attributed to their capability to derive potent representations from data,integral for a myriad of downstream applications.These representations encapsulate the intrinsic structure,fea-tures,or latent variables characterising the underlying statistics of visual data.Despite these achievements,the challenge per-sists in effectively conducting representation learning of visual data with deep models,particularly when confronted with vast and noisy datasets.This special issue is a dedicated platform for researchers worldwide to disseminate their latest,high-quality articles,aiming to enhance readers'comprehension of the principles,limitations,and diverse applications of repre-sentation learning in computer vision.
文摘Edge devices,due to their limited computational and storage resources,often require the use of compilers for program optimization.Therefore,ensuring the security and reliability of these compilers is of paramount importance in the emerging field of edge AI.One widely used testing method for this purpose is fuzz testing,which detects bugs by inputting random test cases into the target program.However,this process consumes significant time and resources.To improve the efficiency of compiler fuzz testing,it is common practice to utilize test case prioritization techniques.Some researchers use machine learning to predict the code coverage of test cases,aiming to maximize the test capability for the target compiler by increasing the overall predicted coverage of the test cases.Nevertheless,these methods can only forecast the code coverage of the compiler at a specific optimization level,potentially missing many optimization-related bugs.In this paper,we introduce C-CORE(short for Clustering by Code Representation),the first framework to prioritize test cases according to their code representations,which are derived directly from the source codes.This approach avoids being limited to specific compiler states and extends to a broader range of compiler bugs.Specifically,we first train a scaled pre-trained programming language model to capture as many common features as possible from the test cases generated by a fuzzer.Using this pre-trained model,we then train two downstream models:one for predicting the likelihood of triggering a bug and another for identifying code representations associated with bugs.Subsequently,we cluster the test cases according to their code representations and select the highest-scoring test case from each cluster as the high-quality test case.This reduction in redundant testing cases leads to time savings.Comprehensive evaluation results reveal that code representations are better at distinguishing test capabilities,and C-CORE significantly enhances testing efficiency.Across four datasets,C-CORE increases the average of the percentage of faults detected(APFD)value by 0.16 to 0.31 and reduces test time by over 50% in 46% of cases.When compared to the best results from approaches using predicted code coverage,C-CORE improves the APFD value by 1.1% to 12.3% and achieves an overall time-saving of 159.1%.
基金supported by the Natural Science Foundation of Zhejiang Province(LY19A020001).
文摘With the increasing demand for electrical services,wind farm layout optimization has been one of the biggest challenges that we have to deal with.Despite the promising performance of the heuristic algorithm on the route network design problem,the expressive capability and search performance of the algorithm on multi-objective problems remain unexplored.In this paper,the wind farm layout optimization problem is defined.Then,a multi-objective algorithm based on Graph Neural Network(GNN)and Variable Neighborhood Search(VNS)algorithm is proposed.GNN provides the basis representations for the following search algorithm so that the expressiveness and search accuracy of the algorithm can be improved.The multi-objective VNS algorithm is put forward by combining it with the multi-objective optimization algorithm to solve the problem with multiple objectives.The proposed algorithm is applied to the 18-node simulation example to evaluate the feasibility and practicality of the developed optimization strategy.The experiment on the simulation example shows that the proposed algorithm yields a reduction of 6.1% in Point of Common Coupling(PCC)over the current state-of-the-art algorithm,which means that the proposed algorithm designs a layout that improves the quality of the power supply by 6.1%at the same cost.The ablation experiments show that the proposed algorithm improves the power quality by more than 8.6% and 7.8% compared to both the original VNS algorithm and the multi-objective VNS algorithm.
文摘The systematic method for constructing Lewis representations is a method for representing chemical bonds between atoms in a molecule. It uses symbols to represent the valence electrons of the atoms involved in the bond. Using a number of rules in a defined order, it is often better suited to complicated cases than the Lewis representation of atoms. This method allows us to determine the formal charge and oxidation number of each atom in the edifice more efficiently than other methods.
文摘The research consistently highlights the gender disparity in cybersecurity leadership roles, necessitating targeted interventions. Biased recruitment practices, limited STEM education opportunities for girls, and workplace culture contribute to this gap. Proposed solutions include addressing biased recruitment through gender-neutral language and blind processes, promoting STEM education for girls to increase qualified female candidates, and fostering inclusive workplace cultures with mentorship and sponsorship programs. Gender parity is crucial for the industry’s success, as embracing diversity enables the cybersecurity sector to leverage various perspectives, drive innovation, and effectively combat cyber threats. Achieving this balance is not just about fairness but also a strategic imperative. By embracing concerted efforts towards gender parity, we can create a more resilient and impactful cybersecurity landscape, benefiting industry and society.
基金supported by the Research Foundation for Advanced Talents of Guizhou University under Grant(2016)No.49,Key Disciplines of Guizhou Province Computer Science and Technology(ZDXK[2018]007)Research Projects of Innovation Group of Education(QianJiaoHeKY[2021]022)supported by the National Natural Science Foundation of China(62062023).
文摘Sparse representation plays an important role in the research of face recognition.As a deformable sample classification task,face recognition is often used to test the performance of classification algorithms.In face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition accuracy.Essentially,there may be significant differences between different image samples of the same face,which makes image classification very difficult.Therefore,how to build a robust virtual image representation becomes a vital issue.To solve the above problems,this paper proposes a novel image classification algorithm.First,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual sample.Second,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,respectively.After obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test sample.These two distances are converted into distance scores.Finally,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual image.The fused score will determine the final classification result.The experimental results show that the proposed method outperforms other typical sparse representation classification methods.
基金the National Natural Science Foundation of China(Nos.12205001,11935001,and 12204001)the Scientific Research program of Anhui University of Finance and Economics(Nos.ACKYC22080 and ACKYC220801).
文摘The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using the complex momentum representation method applied to deformation and continuum coupling.By examining the evolution of the weakly bound and resonant levels near the Fermi surface,s–d orbital reversals and certain prolate deformations were observed.In addition,by analyzing the evolution of the occupation probabilities and density distributions occupied by valence neutrons,we found that the ground state of15B did not exhibit a halo and the ground states of17B and19B exhibited halos at 0.6≤β2≤0.7 and0.3≤β2≤0.7,respectively.The low-l components in the valence levels that are weakly bound or embedded in the continuous spectrum lead to halo formation.
基金supported by the National Natural Science Foundation of China(Nos.12175010,11375022,11775014)Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDB34010000)US Department of Energy Office of Science,Office of Nuclear Physics,under Award Number DE-AC05-00OR22725.
文摘Approaches for predicting low-lying resonances,uniformly treating bound,and resonant levels have been a long-standing goal in nuclear theory.Accordingly,we explored the viability of the complex momentum representation(CMR)approach coupled with new potentials.We focus on predicting the energy of the low-lying 2p_(3∕2)resonance in 17 O,which is critical for s-process nucleosynthesis and missing in previous theoretical research.Using a Woods-Saxon potential based on the Koning-Delaroche optical model and constrained by the experimental one-neutron separation energy,we successfully predicted the resonant energy of this level for the first time.Our predictions of the bound levels and 1d_(3∕2)resonance agree well with the measurement results.Additionally,we utilize this approach to study the near-threshold resonances that play a role when forming a two-neutron halo in^(29,31)F.We found that the CMR-based predictions of the bound-level energies and unbound 1f7∕2 level agree well with the results obtained using the scattering phase shift method.Subsequently,we successfully found a solution for the 2p_(3∕2)resonance with energy just above the threshold,which is decisive for halo formation.
基金supported by Shanghai Rising-Star Program(Grant No.21QA1403400)Shanghai Natural Science Foundation(Grant No.19ZR1420700)Shanghai Key Laboratory of Power Station Automation Technology(Grant No.13DZ2273800).
文摘Failuremode and effects analysis(FMEA)is a widely used safety assessmentmethod inmany fields.Z-number was previously applied in FMEA since it can take both possibility and reliability of information into consideration.However,the use of fuzzy weighted mean to integrate Z-valuations may have some drawbacks and is not suitable for some situations.In this paper,an improved method is proposed based on Z-numbers and the graded mean integration representation(GMIR)to deal with the uncertain information in FMEA.First,Z-numbers are constructed based on the evaluations of risk factors O,S,D for each failure mode by different experts.Second,weights of the three risk factors and experts are determined.Third,the integration representations of Z-numbers are obtained by a newmethod based on the GMIRmethod.Finally,risk priorities of the failure modes are derived considering the weights of experts and risk factors.Two examples and a case study are given to show the use of the proposed method and comparison with other methods.The results show that the proposed method is more reasonable,universal and simple in calculation.
基金This research is partially supported by the National Natural Science Foundation of China(Grant No.61772098)Chongqing Technology Innovation and Application Development Project(Grant No.cstc2020jscxmsxmX0150)+2 种基金Chongqing Science and Technology Innovation Leading Talent Support Program(CSTCCXLJRC201908)Basic and Advanced Research Projects of CSTC(No.cstc2019jcyj-zdxmX0008)Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.KJZD-K201900605).
文摘The traditional malware research is mainly based on its recognition and detection as a breakthrough point,without focusing on its propagation trends or predicting the subsequently infected nodes.The complexity of network structure,diversity of network nodes,and sparsity of data all pose difficulties in predicting propagation.This paper proposes a malware propagation prediction model based on representation learning and Graph Convolutional Networks(GCN)to address the aforementioned problems.First,to solve the problem of the inaccuracy of infection intensity calculation caused by the sparsity of node interaction behavior data in the malware propagation network,a mechanism based on a tensor to mine the infection intensity among nodes is proposed to retain the network structure information.The influence of the relationship between nodes on the infection intensity is also analyzed.Second,given the diversity and complexity of the content and structure of infected and normal nodes in the network,considering the advantages of representation learning in data feature extraction,the corresponding representation learning method is adopted for the characteristics of infection intensity among nodes.This can efficiently calculate the relationship between entities and relationships in low dimensional space to achieve the goal of low dimensional,dense,and real-valued representation learning for the characteristics of propagation spatial data.We also design a new method,Tensor2vec,to learn the potential structural features of malware propagation.Finally,considering the convolution ability of GCN for non-Euclidean data,we propose a dynamic prediction model of malware propagation based on representation learning and GCN to solve the time effectiveness problem of the malware propagation carrier.The experimental results show that the proposed model can effectively predict the behaviors of the nodes in the network and discover the influence of different characteristics of nodes on the malware propagation situation.
基金supported by the Science and Technology Program Project(No.2020A02001-1)of Xinjiang Autonomous Region,China.
文摘Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic information.Therefore,there is ample room for improvement in terms of detection precision.To solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called GRATDet.The method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample data.Each line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the contract.Finally,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability detection.The effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.
文摘In this study,application of the spectral representation method for generation of endurance time excitation functions is introduced.Using this method,the intensifying acceleration time series is generated so that its acceleration response spectrum in any desired time duration is compatible with a time-scaled predefined acceleration response spectrum.For this purpose,simulated stationary acceleration time series is multiplied by the time dependent linear modulation function,then using a simple iterative scheme,it is forced to match a target acceleration response spectrum.It is shown that the generated samples have excellent conformity in low frequency,which is useful for nonlinear endurance time analysis.In the second part of this study,it is shown that this procedure can be extended to generate a set of spatially correlated endurance time excitation functions.This makes it possible to assess the performance of long structures under multi-support seismic excitation using endurance time analysis.
基金This work was supported by the National Natural Science Foundation of China(62073087,62071132,61973090).
文摘Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.
基金supported by the Chung-Ang University Graduate Research Scholarship in 2021.
文摘Speech emotion recognition is essential for frictionless human-machine interaction,where machines respond to human instructions with context-aware actions.The properties of individuals’voices vary with culture,language,gender,and personality.These variations in speaker-specific properties may hamper the performance of standard representations in downstream tasks such as speech emotion recognition(SER).This study demonstrates the significance of speaker-specific speech characteristics and how considering them can be leveraged to improve the performance of SER models.In the proposed approach,two wav2vec-based modules(a speaker-identification network and an emotion classification network)are trained with the Arcface loss.The speaker-identification network has a single attention block to encode an input audio waveform into a speaker-specific representation.The emotion classification network uses a wav2vec 2.0-backbone as well as four attention blocks to encode the same input audio waveform into an emotion representation.These two representations are then fused into a single vector representation containing emotion and speaker-specific information.Experimental results showed that the use of speaker-specific characteristics improves SER performance.Additionally,combining these with an angular marginal loss such as the Arcface loss improves intra-class compactness while increasing inter-class separability,as demonstrated by the plots of t-distributed stochastic neighbor embeddings(t-SNE).The proposed approach outperforms previous methods using similar training strategies,with a weighted accuracy(WA)of 72.14%and unweighted accuracy(UA)of 72.97%on the Interactive Emotional Dynamic Motion Capture(IEMOCAP)dataset.This demonstrates its effectiveness and potential to enhance human-machine interaction through more accurate emotion recognition in speech.
基金Natural Science Foundation of Jiangsu Province,Grant/Award Number:BK20170765National Natural Science Foundation of China,Grant/Award Number:61703201+1 种基金Future Network Scientific Research Fund Project,Grant/Award Number:FNSRFP2021YB26Science Foundation of Nanjing Institute of Technology,Grant/Award Numbers:ZKJ202002,ZKJ202003,and YKJ202019。
文摘Unconstrained face images are interfered by many factors such as illumination,posture,expression,occlusion,age,accessories and so on,resulting in the randomness of the noise pollution implied in the original samples.In order to improve the sample quality,a weighted block cooperative sparse representation algorithm is proposed based on visual saliency dictionary.First,the algorithm uses the biological visual attention mechanism to quickly and accurately obtain the face salient target and constructs the visual salient dictionary.Then,a block cooperation framework is presented to perform sparse coding for different local structures of human face,and the weighted regular term is introduced in the sparse representation process to enhance the identification of information hidden in the coding coefficients.Finally,by synthesising the sparse representation results of all visual salient block dictionaries,the global coding residual is obtained and the class label is given.The experimental results on four databases,that is,AR,extended Yale B,LFW and PubFig,indicate that the combination of visual saliency dictionary,block cooperative sparse representation and weighted constraint coding can effectively enhance the accuracy of sparse representation of the samples to be tested and improve the performance of unconstrained face recognition.
基金supported by the National Natural Science Foundation of China(Grant No.61871380)the Shandong Provincial Natural Science Foundation(Grant No.ZR2020MF019)Beijing Natural Science Foundation(Grant No.4172034).
文摘Biological slices are an effective tool for studying the physiological structure and evolutionmechanism of biological systems.However,due to the complexity of preparation technology and the presence of many uncontrollable factors during the preparation processing,leads to problems such as difficulty in preparing slice images and breakage of slice images.Therefore,we proposed a biological slice image small-scale corruption inpainting algorithm with interpretability based on multi-layer deep sparse representation,achieving the high-fidelity reconstruction of slice images.We further discussed the relationship between deep convolutional neural networks and sparse representation,ensuring the high-fidelity characteristic of the algorithm first.A novel deep wavelet dictionary is proposed that can better obtain image prior and possess learnable feature.And multi-layer deep sparse representation is used to implement dictionary learning,acquiring better signal expression.Compared with methods such as NLABH,Shearlet,Partial Differential Equation(PDE),K-Singular Value Decomposition(K-SVD),Convolutional Sparse Coding,and Deep Image Prior,the proposed algorithm has better subjective reconstruction and objective evaluation with small-scale image data,which realized high-fidelity inpainting,under the condition of small-scale image data.And theOn2-level time complexitymakes the proposed algorithm practical.The proposed algorithm can be effectively extended to other cross-sectional image inpainting problems,such as magnetic resonance images,and computed tomography images.
