In distributed fusion,when one or more sensors are disturbed by faults,a common problem is that their local estimations are inconsistent with those of other fault-free sensors.Most of the existing fault-tolerant distr...In distributed fusion,when one or more sensors are disturbed by faults,a common problem is that their local estimations are inconsistent with those of other fault-free sensors.Most of the existing fault-tolerant distributed fusion algorithms,such as the Covariance Union(CU)and Faulttolerant Generalized Convex Combination(FGCC),are only used for the point estimation case where local estimates and their associated error covariances are provided.A treatment with focus on the fault-tolerant distributed fusions of arbitrary local Probability Density Functions(PDFs)is lacking.For this problem,we first propose Kullback–Leibler Divergence(KLD)and reversed KLD induced functional Fuzzy c-Means(FCM)clustering algorithms to soft cluster all local PDFs,respectively.On this basis,two fault-tolerant distributed fusion algorithms of arbitrary local PDFs are then developed.They select the representing PDF of the cluster with the largest sum of memberships as the fused PDF.Numerical examples verify the better fault tolerance of the developed two distributed fusion algorithms.展开更多
Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy cl...Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.展开更多
Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin s...Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between samples.To overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering model.We creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion module.By this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one cluster.In addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering methods.The code is available at https://github.com/songzuolong/MNF-MDSC(accessed on 25 December 2024).展开更多
The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show...The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show limitations with the inherent uncertainty and imprecision of such data,as they rely on a single-dimensional membership value.To overcome these limitations,we propose an auto-weighted multi-view neutrosophic fuzzy clustering(AW-MVNFC)algorithm.Our method leverages the neutrosophic framework,an extension of fuzzy sets,to explicitly model imprecision and ambiguity through three membership degrees.The core novelty of AWMVNFC lies in a hierarchical weighting strategy that adaptively learns the contributions of both individual data views and the importance of each feature within a view.Through a unified objective function,AW-MVNFC jointly optimizes the neutrosophic membership assignments,cluster centers,and the distributions of view and feature weights.Comprehensive experiments conducted on synthetic and real-world datasets demonstrate that our algorithm achieves more accurate and stable clustering than existing methods,demonstrating its effectiveness in handling the complexities of multi-view data.展开更多
Platinum-based(Pt)catalysts are notoriously susceptible to deactivation in industrial chemical processes due to carbon monoxide(CO)poisoning.Overcoming this poisoning deactivation of Pt-based catalysts while enhancing...Platinum-based(Pt)catalysts are notoriously susceptible to deactivation in industrial chemical processes due to carbon monoxide(CO)poisoning.Overcoming this poisoning deactivation of Pt-based catalysts while enhancing their catalytic activity,selectivity,and durability remains a major challenge.Herein,we propose a strategy to enhance the CO tolerance of Pt clusters(Pt_n)by introducing neighboring functionalized vip single atoms(such as Fe,Co,Ni,Cu,Sb,and Bi).Among them,antimony(Sb)single atoms(SAs)exhibit significant performance enhancement,achieving 99%CO selectivity and 33.6%CO_(2)conversion at 450℃,Experimental results and density functional theory(DFT)calculations indicate the optimization arises from the electronic interaction between neighboring functionalized Sb SAs and Pt clusters,leading to optimal 5d electron redistribution in Pt clusters compared to other functionalized vip single atoms.The redistribution of 5d electrons weaken both theσdonation andπbackdonation interactions,resulting in a weakened bond strength with CO and enhancing catalyst activity and selectivity.In situ environmental transmission electron microscopy(ETEM)further demonstrates the exception thermal stability of the catalyst,even under H_(2)at 700℃.Notably,the functionalized Sb SAs also improve CO tolerance in various heterogenous catalysts,including Co/CeO_(2),Ni/CeO_(2),Pt/Al_(2)O_(3),and Pt/CeO_(2)-C.This finding provides an effective approach to overcome the primary challenge of CO poisoning in Pt-based catalysts,making their broader applications in various industrial catalysts.展开更多
Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, t...Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, these existing algorithms create only the hard and fuzzy partitions for multi-view objects,which are often located in highly-overlapping areas of multi-view feature space. The adoption of hard and fuzzy partition ignores the ambiguity and uncertainty in the assignment of objects, likely leading to performance degradation. To address these issues, we propose a novel sparse reconstructive multi-view evidential clustering algorithm(SRMVEC). Based on a sparse reconstructive procedure, SRMVEC learns a shared affinity matrix across views, and maps multi-view objects to a 2-dimensional humanreadable chart by calculating 2 newly defined mathematical metrics for each object. From this chart, users can detect the number of clusters and select several objects existing in the dataset as cluster centers. Then, SRMVEC derives a credal partition under the framework of evidence theory, improving the fault tolerance of clustering. Ablation studies show the benefits of adopting the sparse reconstructive procedure and evidence theory. Besides,SRMVEC delivers effectiveness on benchmark datasets by outperforming some state-of-the-art methods.展开更多
Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The signif...Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The significance of low-rank prior in MVSC is emphasized, highlighting its role in capturing the global data structure across views for improved performance. However, it faces challenges with outlier sensitivity due to its reliance on the Frobenius norm for error measurement. Addressing this, our paper proposes a Low-Rank Multi-view Subspace Clustering Based on Sparse Regularization (LMVSC- Sparse) approach. Sparse regularization helps in selecting the most relevant features or views for clustering while ignoring irrelevant or noisy ones. This leads to a more efficient and effective representation of the data, improving the clustering accuracy and robustness, especially in the presence of outliers or noisy data. By incorporating sparse regularization, LMVSC-Sparse can effectively handle outlier sensitivity, which is a common challenge in traditional MVSC methods relying solely on low-rank priors. Then Alternating Direction Method of Multipliers (ADMM) algorithm is employed to solve the proposed optimization problems. Our comprehensive experiments demonstrate the efficiency and effectiveness of LMVSC-Sparse, offering a robust alternative to traditional MVSC methods.展开更多
We employed random distributions and gradient descent methods for the Generator Coordinate Method(GCM)to identify effective basis wave functions,taking halo nuclei ^(6)He and ^(6)Li as examples.By comparing the ground...We employed random distributions and gradient descent methods for the Generator Coordinate Method(GCM)to identify effective basis wave functions,taking halo nuclei ^(6)He and ^(6)Li as examples.By comparing the ground state(0^(+))energy of ^(6)He and the excited state(0^(+))energy of 6 Li calculated with various random distributions and manually selected generation coordinates,we found that the heavy tail characteristic of the logistic distribution better describes the features of the halo nuclei.Subsequently,the Adam algorithm from machine learning was applied to optimize the basis wave functions,indicating that a limited number of basis wave functions can approximate the converged values.These results offer some empirical insights for selecting basis wave functions and contribute to the broader application of machine learning methods in predicting effective basis wave functions.展开更多
The existing multi-view subspace clustering algorithms based on tensor singular value decomposition(t-SVD)predominantly utilize tensor nuclear norm to explore the intra view correlation between views of the same sampl...The existing multi-view subspace clustering algorithms based on tensor singular value decomposition(t-SVD)predominantly utilize tensor nuclear norm to explore the intra view correlation between views of the same samples,while neglecting the correlation among the samples within different views.Moreover,the tensor nuclear norm is not fully considered as a convex approximation of the tensor rank function.Treating different singular values equally may result in suboptimal tensor representation.A hypergraph regularized multi-view subspace clustering algorithm with dual tensor log-determinant(HRMSC-DTL)was proposed.The algorithm used subspace learning in each view to learn a specific set of affinity matrices,and introduced a non-convex tensor log-determinant function to replace the tensor nuclear norm to better improve global low-rankness.It also introduced hyper-Laplacian regularization to preserve the local geometric structure embedded in the high-dimensional space.Furthermore,it rotated the original tensor and incorporated a dual tensor mechanism to fully exploit the intra view correlation of the original tensor and the inter view correlation of the rotated tensor.At the same time,an alternating direction of multipliers method(ADMM)was also designed to solve non-convex optimization model.Experimental evaluations on seven widely used datasets,along with comparisons to several state-of-the-art algorithms,demonstrated the superiority and effectiveness of the HRMSC-DTL algorithm in terms of clustering performance.展开更多
Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewpriv...Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.展开更多
It is challenging to cluster multi-view data in which the clusters have overlapping areas.Existing multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them int...It is challenging to cluster multi-view data in which the clusters have overlapping areas.Existing multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them into single clusters,increasing clustering errors.Our solution,the multi-view dynamic kernelized evidential clustering method(MvDKE),addresses this by assigning these objects to meta-clusters,a union of several related singleton clusters,effectively capturing the local imprecision in overlapping areas.MvDKE offers two main advantages:firstly,it significantly reduces computational complexity through a dynamic framework for evidential clustering,and secondly,it adeptly handles non-spherical data using kernel techniques within its objective function.Experiments on various datasets confirm MvDKE's superior ability to accurately characterize the local imprecision in multi-view non-spherical data,achieving better efficiency and outperforming existing methods in overall performance.展开更多
Modularity is the key to improving the cost-variety trade-off in product development. To achieve the functional independency and structural independency of modules, a method of clustering components to identify module...Modularity is the key to improving the cost-variety trade-off in product development. To achieve the functional independency and structural independency of modules, a method of clustering components to identify modules based on functional and structural analysis was presented. Two stages were included in the method. In the first stage the products’ function was analyzed to determine the primary level of modules. Then the objective function for modules identifying was formulated to achieve functional independency of modules. Finally the genetic algorithm was used to solve the combinatorial optimization problem in modules identifying to form the primary modules of products. In the second stage the cohesion degree of modules and the coupling degree between modules were analyzed. Based on this structural analysis the modular scheme was refined according to the thinking of structural independency. A case study on the gear reducer was conducted to illustrate the validity of the presented method.展开更多
The internal structures as well as adsorption and hopping energies of monomers, dimers, trimers, tetramers, pentamers and hexamers of water on Pd（111） have been studied by density functional theory （DFT） plane-wav...The internal structures as well as adsorption and hopping energies of monomers, dimers, trimers, tetramers, pentamers and hexamers of water on Pd（111） have been studied by density functional theory （DFT） plane-wave pseudopotential method which performs the firstprinciples quantum-mechanical calculations to explore the properties of crystals and surfaces in materials. Based on the calculations, we suppose that their absorption is via one water molecule for monomers, dimmers and trimers, but three water molecules for pentamers and hexamers. Moreover, there is one water molecule bonding with Pd atom by O atom in pentamers and hexamers, which explains why pentamers and hexamers are stable. The binding energies of polymers may be used to explain why the trimer comes close to two nearby monomers to form a stable pentamer instead of tetramer. And the difference of mobility of small water clusters is due to their different hopping energies.展开更多
In recent years, functional data has been widely used in finance, medicine, biology and other fields. The current clustering analysis can solve the problems in finite-dimensional space, but it is difficult to be direc...In recent years, functional data has been widely used in finance, medicine, biology and other fields. The current clustering analysis can solve the problems in finite-dimensional space, but it is difficult to be directly used for the clustering of functional data. In this paper, we propose a new unsupervised clustering algorithm based on adaptive weights. In the absence of initialization parameter, we use entropy-type penalty terms and fuzzy partition matrix to find the optimal number of clusters. At the same time, we introduce a measure based on adaptive weights to reflect the difference in information content between different clustering metrics. Simulation experiments show that the proposed algorithm has higher purity than some algorithms.展开更多
We study the geometries, stabilities, electronic and magnetic properties of （MgO）n （n=2-10） clusters doped with a single Mn atom using the density functional theory with the gener- alized gradient approximation. T...We study the geometries, stabilities, electronic and magnetic properties of （MgO）n （n=2-10） clusters doped with a single Mn atom using the density functional theory with the gener- alized gradient approximation. The optimized geometries show that the impurity Mn atom prefers to replace the Mg atom which has low coordination number in all the lowest-energy MnMgn-1On （n=2-10） structures. The stability analysis clearly represents that the average binding energies of the doped clusters are larger than those of the corresponding pure （MgO）n clusters. Maximum peaks of the second order energy differences are observed for MnMg~_1On clusters at n=6, 9, implying that these clusters exhibit higher stability than their neighboring clusters. In addition, all the Mn-doped Mg clusters exhibit high total magnetic moments with the exception of MnMgO2 which has 3.00μB. Their magnetic behavior is attributed to the impurity Mn atom, the charge transfer modes, and the size of MnMgn- 1On clusters.展开更多
Functional networks(FNs)hold significant promise in understanding brain function.Independent component analysis(ICA)has been applied in estimating FNs from functional magnetic resonance imaging(fMRI).However,determini...Functional networks(FNs)hold significant promise in understanding brain function.Independent component analysis(ICA)has been applied in estimating FNs from functional magnetic resonance imaging(fMRI).However,determining an optimal model order for ICA remains challenging,leading to criticism about the reliability of FN estimation.Here,we propose a SMART(splitting-merging assisted reliable)ICA method that automatically extracts reliable FNs by clustering independent components(ICs)obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model orders.We extend SMART ICA to multi-subject fMRI analysis,validating its effectiveness using simulated and real fMRI data.Based on simulated data,the method accurately estimates both group-common and group-unique components and demonstrates robustness to parameters.Using two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects,the resulting reliable group-level FNs are greatly similar between the two cohorts,and interestingly the subject-specific FNs show progressive changes while age increases.Furthermore,both small-scale and large-scale brain FN templates are provided as benchmarks for future studies.Taken together,SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data,while also providing linkages between different FNs.展开更多
Understanding the mechanisms of community assembly is a key question in ecology.Metal pollution may result in significant changes in bird community structure and diversity,with implications for ecosystem processes and...Understanding the mechanisms of community assembly is a key question in ecology.Metal pollution may result in significant changes in bird community structure and diversity,with implications for ecosystem processes and function.However,the relative importance of these pro-cesses in shaping the bird community at the polluted area is still not clear.Here,we explored bird species richness,functional,and phylogenetic diversity,and the assembly processes of community at the mine region of southwest China.Our results showed that the 3 dimensions of diversity at the mine area were lower than that at the reference sites.In the community assembly,the result was O<NRI/NFR1<1.96,which indicated deterministic processes(environmental filtering)might drive community clustering.The results of the neutral community model,and normalized stochasticity ratio,showed the dominant role of stochastic processes in shaping the bird community assembly.We further quanti-fied the community-level habitat niche breadth(Bcom),and we found that there was no difference in Bcom-value between the mine area and reference sites.This indicates that the bird communities at the mine area and 3 reference sites were not subjected to extreme environmental selection(same or different resource allocation)to form a highly specialized niche.These findings provide insights into the distribution patterns and dominant ecological processes of bird communities under metal exposure,and extend the knowledge in community assembly mechanisms of bird communities living in the mine area.展开更多
The clustering evaluation can be used to scientifically classify the objects to be evaluated according to the information aggregation of various evaluation rules. In grey weighted clustering evaluation, the index clus...The clustering evaluation can be used to scientifically classify the objects to be evaluated according to the information aggregation of various evaluation rules. In grey weighted clustering evaluation, the index clustering rule relies on the construction of the whitenization weight function, while the existing construction method of the linear function lacks the construction mechanism analysis and validity explanation. A normative construction principle is put forward by analyzing the construction mechanism of the function. Through proving the normative principle of the function,the basic modal function(BMF) is proposed and characterized by different function forms. Then, a new type of the whitenization weight function and its grey clustering evaluation model algorithm are given by studying the mechanism and nature of the construction of different forms of the function. Finally, the comparative study for self-innovation capability of defense science and technology industry(DSTI) is taken as an example. The results show that the different construction ways of the function have an effect on the clustering result. The proposed construction mechanism can better explain the index clustering rules and evaluation effectiveness,which will perfect the theoretical system of grey clustering evaluation and be applied to practice effectively.展开更多
The growth pattern and electronic properties of TiGen^- （n=7-12） clusters were investigated using anion photoelectron spectroscopy and density functional theory calculations. For both anionic and neutral TiGen clust...The growth pattern and electronic properties of TiGen^- （n=7-12） clusters were investigated using anion photoelectron spectroscopy and density functional theory calculations. For both anionic and neutral TiGen clusters, a half-encapsulated boat-shaped structure appears at n=8, and the boat-shaped structure is gradually covered by the additional Ge atoms to form Gen cage at n=9-11. TiGe12^- cluster has a distorted hexagonal prism cage structure. According to the natural population analysis, the electron transfers from the Gen framework to the Ti atom for TiGen^-/0 clusters at n=8-12, implying that the electron transfer pattern is related to the structural evolution.展开更多
The geometries of MgnNi2（n = 1 6） clusters are studied by using the hybrid density functional theory （B3LYP） with LANL2DZ basis sets. For the ground-state structures of MgnNi2 clusters, the stabilities and the ele...The geometries of MgnNi2（n = 1 6） clusters are studied by using the hybrid density functional theory （B3LYP） with LANL2DZ basis sets. For the ground-state structures of MgnNi2 clusters, the stabilities and the electronic properties are investigated. The results show that the groundstate structures and symmetries of Mg clusters change greatly due to the Ni atoms. The average binding energies have a growing tendency while the energy gaps have a declining tendency. In addition, the ionization energies exhibit an odd-even oscillation feature. We also conclude that n = 3, 5 are the magic numbers of the MgnNi2 clusters. The Mg3Ni2 and Mg5Ni2 clusters are more stable than neighbouring clusters, and the MgaNi2 cluster exhibits a higher chemical activity.展开更多
基金supported in part by the Open Fund of Intelligent Control Laboratory,China(No.ICL-2023–0202)in part by National Key R&D Program of China(Nos.2021YFC2202600,2021YFC2202603)。
文摘In distributed fusion,when one or more sensors are disturbed by faults,a common problem is that their local estimations are inconsistent with those of other fault-free sensors.Most of the existing fault-tolerant distributed fusion algorithms,such as the Covariance Union(CU)and Faulttolerant Generalized Convex Combination(FGCC),are only used for the point estimation case where local estimates and their associated error covariances are provided.A treatment with focus on the fault-tolerant distributed fusions of arbitrary local Probability Density Functions(PDFs)is lacking.For this problem,we first propose Kullback–Leibler Divergence(KLD)and reversed KLD induced functional Fuzzy c-Means(FCM)clustering algorithms to soft cluster all local PDFs,respectively.On this basis,two fault-tolerant distributed fusion algorithms of arbitrary local PDFs are then developed.They select the representing PDF of the cluster with the largest sum of memberships as the fused PDF.Numerical examples verify the better fault tolerance of the developed two distributed fusion algorithms.
基金funded by the Research Project:THTETN.05/24-25,VietnamAcademy of Science and Technology.
文摘Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.
基金supported by the National Key R&D Program of China(2023YFC3304600).
文摘Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between samples.To overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering model.We creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion module.By this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one cluster.In addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering methods.The code is available at https://github.com/songzuolong/MNF-MDSC(accessed on 25 December 2024).
文摘The increasing prevalence of multi-view data has made multi-view clustering a crucial technique for discovering latent structures from heterogeneous representations.However,traditional fuzzy clustering algorithms show limitations with the inherent uncertainty and imprecision of such data,as they rely on a single-dimensional membership value.To overcome these limitations,we propose an auto-weighted multi-view neutrosophic fuzzy clustering(AW-MVNFC)algorithm.Our method leverages the neutrosophic framework,an extension of fuzzy sets,to explicitly model imprecision and ambiguity through three membership degrees.The core novelty of AWMVNFC lies in a hierarchical weighting strategy that adaptively learns the contributions of both individual data views and the importance of each feature within a view.Through a unified objective function,AW-MVNFC jointly optimizes the neutrosophic membership assignments,cluster centers,and the distributions of view and feature weights.Comprehensive experiments conducted on synthetic and real-world datasets demonstrate that our algorithm achieves more accurate and stable clustering than existing methods,demonstrating its effectiveness in handling the complexities of multi-view data.
基金financially supported by the Shanghai RisingStar Program(No.23QA1403700)the National Natural Science Foundation of China(NSFC,Grant No.U2230102)+1 种基金the sponsored by National Key Research and Development Program of China(No.2021YFB3502200)the Shanghai Technical Service Center of Science and Engineering Computing,Shanghai University.
文摘Platinum-based(Pt)catalysts are notoriously susceptible to deactivation in industrial chemical processes due to carbon monoxide(CO)poisoning.Overcoming this poisoning deactivation of Pt-based catalysts while enhancing their catalytic activity,selectivity,and durability remains a major challenge.Herein,we propose a strategy to enhance the CO tolerance of Pt clusters(Pt_n)by introducing neighboring functionalized vip single atoms(such as Fe,Co,Ni,Cu,Sb,and Bi).Among them,antimony(Sb)single atoms(SAs)exhibit significant performance enhancement,achieving 99%CO selectivity and 33.6%CO_(2)conversion at 450℃,Experimental results and density functional theory(DFT)calculations indicate the optimization arises from the electronic interaction between neighboring functionalized Sb SAs and Pt clusters,leading to optimal 5d electron redistribution in Pt clusters compared to other functionalized vip single atoms.The redistribution of 5d electrons weaken both theσdonation andπbackdonation interactions,resulting in a weakened bond strength with CO and enhancing catalyst activity and selectivity.In situ environmental transmission electron microscopy(ETEM)further demonstrates the exception thermal stability of the catalyst,even under H_(2)at 700℃.Notably,the functionalized Sb SAs also improve CO tolerance in various heterogenous catalysts,including Co/CeO_(2),Ni/CeO_(2),Pt/Al_(2)O_(3),and Pt/CeO_(2)-C.This finding provides an effective approach to overcome the primary challenge of CO poisoning in Pt-based catalysts,making their broader applications in various industrial catalysts.
基金supported in part by NUS startup grantthe National Natural Science Foundation of China (52076037)。
文摘Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, these existing algorithms create only the hard and fuzzy partitions for multi-view objects,which are often located in highly-overlapping areas of multi-view feature space. The adoption of hard and fuzzy partition ignores the ambiguity and uncertainty in the assignment of objects, likely leading to performance degradation. To address these issues, we propose a novel sparse reconstructive multi-view evidential clustering algorithm(SRMVEC). Based on a sparse reconstructive procedure, SRMVEC learns a shared affinity matrix across views, and maps multi-view objects to a 2-dimensional humanreadable chart by calculating 2 newly defined mathematical metrics for each object. From this chart, users can detect the number of clusters and select several objects existing in the dataset as cluster centers. Then, SRMVEC derives a credal partition under the framework of evidence theory, improving the fault tolerance of clustering. Ablation studies show the benefits of adopting the sparse reconstructive procedure and evidence theory. Besides,SRMVEC delivers effectiveness on benchmark datasets by outperforming some state-of-the-art methods.
文摘Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The significance of low-rank prior in MVSC is emphasized, highlighting its role in capturing the global data structure across views for improved performance. However, it faces challenges with outlier sensitivity due to its reliance on the Frobenius norm for error measurement. Addressing this, our paper proposes a Low-Rank Multi-view Subspace Clustering Based on Sparse Regularization (LMVSC- Sparse) approach. Sparse regularization helps in selecting the most relevant features or views for clustering while ignoring irrelevant or noisy ones. This leads to a more efficient and effective representation of the data, improving the clustering accuracy and robustness, especially in the presence of outliers or noisy data. By incorporating sparse regularization, LMVSC-Sparse can effectively handle outlier sensitivity, which is a common challenge in traditional MVSC methods relying solely on low-rank priors. Then Alternating Direction Method of Multipliers (ADMM) algorithm is employed to solve the proposed optimization problems. Our comprehensive experiments demonstrate the efficiency and effectiveness of LMVSC-Sparse, offering a robust alternative to traditional MVSC methods.
基金supported by the National Key R&D Program of China(No.2023YFA1606701)the National Natural Science Foundation of China(Nos.12175042,11890710,11890714,12047514,12147101,and 12347106)+1 种基金Guangdong Major Project of Basic and Applied Basic Research(No.2020B0301030008)China National Key R&D Program(No.2022YFA1602402).
文摘We employed random distributions and gradient descent methods for the Generator Coordinate Method(GCM)to identify effective basis wave functions,taking halo nuclei ^(6)He and ^(6)Li as examples.By comparing the ground state(0^(+))energy of ^(6)He and the excited state(0^(+))energy of 6 Li calculated with various random distributions and manually selected generation coordinates,we found that the heavy tail characteristic of the logistic distribution better describes the features of the halo nuclei.Subsequently,the Adam algorithm from machine learning was applied to optimize the basis wave functions,indicating that a limited number of basis wave functions can approximate the converged values.These results offer some empirical insights for selecting basis wave functions and contribute to the broader application of machine learning methods in predicting effective basis wave functions.
基金supported by National Natural Science Foundation of China(No.61806006)Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘The existing multi-view subspace clustering algorithms based on tensor singular value decomposition(t-SVD)predominantly utilize tensor nuclear norm to explore the intra view correlation between views of the same samples,while neglecting the correlation among the samples within different views.Moreover,the tensor nuclear norm is not fully considered as a convex approximation of the tensor rank function.Treating different singular values equally may result in suboptimal tensor representation.A hypergraph regularized multi-view subspace clustering algorithm with dual tensor log-determinant(HRMSC-DTL)was proposed.The algorithm used subspace learning in each view to learn a specific set of affinity matrices,and introduced a non-convex tensor log-determinant function to replace the tensor nuclear norm to better improve global low-rankness.It also introduced hyper-Laplacian regularization to preserve the local geometric structure embedded in the high-dimensional space.Furthermore,it rotated the original tensor and incorporated a dual tensor mechanism to fully exploit the intra view correlation of the original tensor and the inter view correlation of the rotated tensor.At the same time,an alternating direction of multipliers method(ADMM)was also designed to solve non-convex optimization model.Experimental evaluations on seven widely used datasets,along with comparisons to several state-of-the-art algorithms,demonstrated the superiority and effectiveness of the HRMSC-DTL algorithm in terms of clustering performance.
文摘Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.
基金supported in part by the Youth Foundation of Shanxi Province(5113240053)the Fundamental Research Funds for the Central Universities(G2023KY05102)+2 种基金the Natural Science Foundation of China(61976120)the Natural Science Foundation of Jiangsu Province(BK20231337)the Natural Science Key Foundation of Jiangsu Education Department(21KJA510004)。
文摘It is challenging to cluster multi-view data in which the clusters have overlapping areas.Existing multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them into single clusters,increasing clustering errors.Our solution,the multi-view dynamic kernelized evidential clustering method(MvDKE),addresses this by assigning these objects to meta-clusters,a union of several related singleton clusters,effectively capturing the local imprecision in overlapping areas.MvDKE offers two main advantages:firstly,it significantly reduces computational complexity through a dynamic framework for evidential clustering,and secondly,it adeptly handles non-spherical data using kernel techniques within its objective function.Experiments on various datasets confirm MvDKE's superior ability to accurately characterize the local imprecision in multi-view non-spherical data,achieving better efficiency and outperforming existing methods in overall performance.
基金National Basic Research Programme of China (973 Program) (No. 2003CB317005)Key Project of Chinese Ministry of Educa-tion (No. 105065)
文摘Modularity is the key to improving the cost-variety trade-off in product development. To achieve the functional independency and structural independency of modules, a method of clustering components to identify modules based on functional and structural analysis was presented. Two stages were included in the method. In the first stage the products’ function was analyzed to determine the primary level of modules. Then the objective function for modules identifying was formulated to achieve functional independency of modules. Finally the genetic algorithm was used to solve the combinatorial optimization problem in modules identifying to form the primary modules of products. In the second stage the cohesion degree of modules and the coupling degree between modules were analyzed. Based on this structural analysis the modular scheme was refined according to the thinking of structural independency. A case study on the gear reducer was conducted to illustrate the validity of the presented method.
基金Supported by the Natural Science Foundation of Yunnan Province (No. 2004B0003M)
文摘The internal structures as well as adsorption and hopping energies of monomers, dimers, trimers, tetramers, pentamers and hexamers of water on Pd（111） have been studied by density functional theory （DFT） plane-wave pseudopotential method which performs the firstprinciples quantum-mechanical calculations to explore the properties of crystals and surfaces in materials. Based on the calculations, we suppose that their absorption is via one water molecule for monomers, dimmers and trimers, but three water molecules for pentamers and hexamers. Moreover, there is one water molecule bonding with Pd atom by O atom in pentamers and hexamers, which explains why pentamers and hexamers are stable. The binding energies of polymers may be used to explain why the trimer comes close to two nearby monomers to form a stable pentamer instead of tetramer. And the difference of mobility of small water clusters is due to their different hopping energies.
文摘In recent years, functional data has been widely used in finance, medicine, biology and other fields. The current clustering analysis can solve the problems in finite-dimensional space, but it is difficult to be directly used for the clustering of functional data. In this paper, we propose a new unsupervised clustering algorithm based on adaptive weights. In the absence of initialization parameter, we use entropy-type penalty terms and fuzzy partition matrix to find the optimal number of clusters. At the same time, we introduce a measure based on adaptive weights to reflect the difference in information content between different clustering metrics. Simulation experiments show that the proposed algorithm has higher purity than some algorithms.
文摘We study the geometries, stabilities, electronic and magnetic properties of （MgO）n （n=2-10） clusters doped with a single Mn atom using the density functional theory with the gener- alized gradient approximation. The optimized geometries show that the impurity Mn atom prefers to replace the Mg atom which has low coordination number in all the lowest-energy MnMgn-1On （n=2-10） structures. The stability analysis clearly represents that the average binding energies of the doped clusters are larger than those of the corresponding pure （MgO）n clusters. Maximum peaks of the second order energy differences are observed for MnMg~_1On clusters at n=6, 9, implying that these clusters exhibit higher stability than their neighboring clusters. In addition, all the Mn-doped Mg clusters exhibit high total magnetic moments with the exception of MnMgO2 which has 3.00μB. Their magnetic behavior is attributed to the impurity Mn atom, the charge transfer modes, and the size of MnMgn- 1On clusters.
基金supported by the National Natural Science Foundation of China(62076157 and 61703253)the Fund Program for the Scientific Activities of Selected Returned Overseas Professionals in Shanxi Province(20210033)the National Institutes of Health(R01MH123610 and R01EB006841).
文摘Functional networks(FNs)hold significant promise in understanding brain function.Independent component analysis(ICA)has been applied in estimating FNs from functional magnetic resonance imaging(fMRI).However,determining an optimal model order for ICA remains challenging,leading to criticism about the reliability of FN estimation.Here,we propose a SMART(splitting-merging assisted reliable)ICA method that automatically extracts reliable FNs by clustering independent components(ICs)obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model orders.We extend SMART ICA to multi-subject fMRI analysis,validating its effectiveness using simulated and real fMRI data.Based on simulated data,the method accurately estimates both group-common and group-unique components and demonstrates robustness to parameters.Using two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects,the resulting reliable group-level FNs are greatly similar between the two cohorts,and interestingly the subject-specific FNs show progressive changes while age increases.Furthermore,both small-scale and large-scale brain FN templates are provided as benchmarks for future studies.Taken together,SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data,while also providing linkages between different FNs.
文摘Understanding the mechanisms of community assembly is a key question in ecology.Metal pollution may result in significant changes in bird community structure and diversity,with implications for ecosystem processes and function.However,the relative importance of these pro-cesses in shaping the bird community at the polluted area is still not clear.Here,we explored bird species richness,functional,and phylogenetic diversity,and the assembly processes of community at the mine region of southwest China.Our results showed that the 3 dimensions of diversity at the mine area were lower than that at the reference sites.In the community assembly,the result was O<NRI/NFR1<1.96,which indicated deterministic processes(environmental filtering)might drive community clustering.The results of the neutral community model,and normalized stochasticity ratio,showed the dominant role of stochastic processes in shaping the bird community assembly.We further quanti-fied the community-level habitat niche breadth(Bcom),and we found that there was no difference in Bcom-value between the mine area and reference sites.This indicates that the bird communities at the mine area and 3 reference sites were not subjected to extreme environmental selection(same or different resource allocation)to form a highly specialized niche.These findings provide insights into the distribution patterns and dominant ecological processes of bird communities under metal exposure,and extend the knowledge in community assembly mechanisms of bird communities living in the mine area.
基金supported by the National Natural Science Foundation of China(71671090)the Aeronautical Science Foundation of China(2016ZG52068)+1 种基金the Liberal Arts and Social Sciences Foundation of the Ministry of Education(MOE)in China(15YJCZH189)the Qinglan Project for Excellent Youth or Middle-aged Academic Leaders in Jiangsu Province
文摘The clustering evaluation can be used to scientifically classify the objects to be evaluated according to the information aggregation of various evaluation rules. In grey weighted clustering evaluation, the index clustering rule relies on the construction of the whitenization weight function, while the existing construction method of the linear function lacks the construction mechanism analysis and validity explanation. A normative construction principle is put forward by analyzing the construction mechanism of the function. Through proving the normative principle of the function,the basic modal function(BMF) is proposed and characterized by different function forms. Then, a new type of the whitenization weight function and its grey clustering evaluation model algorithm are given by studying the mechanism and nature of the construction of different forms of the function. Finally, the comparative study for self-innovation capability of defense science and technology industry(DSTI) is taken as an example. The results show that the different construction ways of the function have an effect on the clustering result. The proposed construction mechanism can better explain the index clustering rules and evaluation effectiveness,which will perfect the theoretical system of grey clustering evaluation and be applied to practice effectively.
基金Wei-jun Zheng acknowledges the Knowledge Innovation Program of the Chinese Academy of Sciences （No.KJCX2-EW-H01） and Hong-guang Xu acknowl- edges the National Natural Science Foundation of China （No.21103202） for financial support. The theoretical calculations were conducted on the ScGrid and Deep- Comp 7000 of the Supercomputing Center, Computer Network Information Center of the Chinese Academy of Sciences.
文摘The growth pattern and electronic properties of TiGen^- （n=7-12） clusters were investigated using anion photoelectron spectroscopy and density functional theory calculations. For both anionic and neutral TiGen clusters, a half-encapsulated boat-shaped structure appears at n=8, and the boat-shaped structure is gradually covered by the additional Ge atoms to form Gen cage at n=9-11. TiGe12^- cluster has a distorted hexagonal prism cage structure. According to the natural population analysis, the electron transfers from the Gen framework to the Ti atom for TiGen^-/0 clusters at n=8-12, implying that the electron transfer pattern is related to the structural evolution.
基金Project supported by the National Natural Science Foundation of China (Grant No. 10676022)
文摘The geometries of MgnNi2（n = 1 6） clusters are studied by using the hybrid density functional theory （B3LYP） with LANL2DZ basis sets. For the ground-state structures of MgnNi2 clusters, the stabilities and the electronic properties are investigated. The results show that the groundstate structures and symmetries of Mg clusters change greatly due to the Ni atoms. The average binding energies have a growing tendency while the energy gaps have a declining tendency. In addition, the ionization energies exhibit an odd-even oscillation feature. We also conclude that n = 3, 5 are the magic numbers of the MgnNi2 clusters. The Mg3Ni2 and Mg5Ni2 clusters are more stable than neighbouring clusters, and the MgaNi2 cluster exhibits a higher chemical activity.
