An algorithm, Clustering Algorithm Based On Sparse Feature Vector (CABOSFV),was proposed for the high dimensional clustering of binary sparse data. This algorithm compressesthe data effectively by using a tool 'Sp...An algorithm, Clustering Algorithm Based On Sparse Feature Vector (CABOSFV),was proposed for the high dimensional clustering of binary sparse data. This algorithm compressesthe data effectively by using a tool 'Sparse Feature Vector', thus reduces the data scaleenormously, and can get the clustering result with only one data scan. Both theoretical analysis andempirical tests showed that CABOSFV is of low computational complexity. The algorithm findsclusters in high dimensional large datasets efficiently and handles noise effectively.展开更多
During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable landscapes.However,due to the ...During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable landscapes.However,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision variables.To tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal solutions.The proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search space.More importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by GPUs.While existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real variables.Furthermore,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.展开更多
Traditional unsupervised seismic facies analysis techniques need to assume that seismic data obey mixed Gaussian distribution.However,fi eld seismic data may not meet this condition,thereby leading to wrong classifi c...Traditional unsupervised seismic facies analysis techniques need to assume that seismic data obey mixed Gaussian distribution.However,fi eld seismic data may not meet this condition,thereby leading to wrong classifi cation in the application of this technology.This paper introduces a spectral clustering technique for unsupervised seismic facies analysis.This algorithm is based on on the idea of a graph to cluster the data.Its kem is that seismic data are regarded as points in space,points can be connected with the edge and construct to graphs.When the graphs are divided,the weights of the edges between the different subgraphs are as low as possible,whereas the weights of the inner edges of the subgraph should be as high as possible.That has high computational complexity and entails large memory consumption for spectral clustering algorithm.To solve the problem this paper introduces the idea of sparse representation into spectral clustering.Through the selection of a small number of local sparse representation points,the spectral clustering matrix of all sample points is approximately represented to reduce the cost of spectral clustering operation.Verifi cation of physical model and fi eld data shows that the proposed approach can obtain more accurate seismic facies classification results without considering the data meet any hypothesis.The computing efficiency of this new method is better than that of the conventional spectral clustering method,thereby meeting the application needs of fi eld seismic data.展开更多
A clustering algorithm based on Sparse Projection (SP), called Sparse Projection Clus- tering (SPC), is proposed in this letter. The basic idea is applying SP to project the observed data onto a high-dimensional spars...A clustering algorithm based on Sparse Projection (SP), called Sparse Projection Clus- tering (SPC), is proposed in this letter. The basic idea is applying SP to project the observed data onto a high-dimensional sparse space, which is a nonlinear mapping with an explicit form and the K-means clustering algorithm can be therefore used to explore the inherent data patterns in the new space. The proposed algorithm is applied to cluster a complete artificial dataset and an incomplete real dataset. In comparison with the kernel K-means clustering algorithm, the proposed algorithm is more efficient.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
Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on a...Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on aerial image recognition have been widely used, such as RGB-based and HIS-based methods. However, these methods are susceptible to background factors causing interference and false detection. To alleviate these problems, we investigate two subspace clustering methods based on sparse and collaborative representation, respectively, to detect and locate forest fires. Firstly, subspace clustering segments flame from the whole image. Afterwards, sparse or collaborative representation is employed to represent most of the flame information in a dictionary with l1-regularization or l2-regularization term, which results in fewer reconstruction errors. Experimental results show that the proposed SSC and CSC substantially outperform the state-of-the art methods.展开更多
Blind separation of sparse sources （BSSS） is discussed. The BSSS method based on the conventional K-means clustering is very fast and is also easy to implement. However, the accuracy of this method is generally not ...Blind separation of sparse sources （BSSS） is discussed. The BSSS method based on the conventional K-means clustering is very fast and is also easy to implement. However, the accuracy of this method is generally not satisfactory. The contribution of the vector x（t） with different modules is theoretically proved to be unequal, and a weighted K-means clustering method is proposed on this grounds. The proposed algorithm is not only as fast as the conventional K-means clustering method, but can also achieve considerably accurate results, which is demonstrated by numerical experiments.展开更多
功能超网络广泛地应用于脑疾病诊断和分类研究中,而现有的关于超网络创建的研究缺乏解释分组效应的能力或者仅考虑到脑区间组级的信息,这样构建的脑功能超网络会丢失一些有用的连接或包含一些虚假的信息,因此,考虑到脑区间的组结构问题...功能超网络广泛地应用于脑疾病诊断和分类研究中,而现有的关于超网络创建的研究缺乏解释分组效应的能力或者仅考虑到脑区间组级的信息,这样构建的脑功能超网络会丢失一些有用的连接或包含一些虚假的信息,因此,考虑到脑区间的组结构问题,引入sparse group Lasso(sgLasso)方法进一步改善超网络的创建。首先,利用sgLasso方法进行超网络创建;然后,引入两组超网络特有的属性指标进行特征提取以及特征选择,这些指标分别是基于单一节点的聚类系数和基于一对节点的聚类系数;最后,将特征选择后得到的两组有显著差异的特征通过多核学习进行特征融合和分类。实验结果表明,所提方法经过多特征融合取得了87.88%的分类准确率。该结果表明为了改善脑功能超网络的创建,需要考虑到组信息,但不能逼迫使用整组信息,可以适当地对组结构进行扩展。展开更多
Computer Tomography in medical imaging provides human internal body pictures in the digital form. The more quality images it provides, the better information we get. Normally, medical imaging can be constructed by pro...Computer Tomography in medical imaging provides human internal body pictures in the digital form. The more quality images it provides, the better information we get. Normally, medical imaging can be constructed by projection data from several perspectives. In this paper, our research challenges and describes a numerical method for refining the image of a Region of Interest (ROI) by constructing support within a standard CT image. It is obvious that the quality of tomographic slice is affected by artifacts. CT using filter and K-means clustering provides a way to reconstruct an ROI with minimal artifacts and improve the degree of the spatial resolution. Experimental results are presented for improving the reconstructed images, showing that the approach enhances the overall resolution and contrast of ROI images. Our method provides a number of advantages: robustness with noise in projection data and support construction without the need to acquire any additional setup.展开更多
Designing a sparse array with reduced transmit/receive modules(TRMs)is vital for some applications where the antenna system’s size,weight,allowed operating space,and cost are limited.Sparse arrays exhibit distinct ar...Designing a sparse array with reduced transmit/receive modules(TRMs)is vital for some applications where the antenna system’s size,weight,allowed operating space,and cost are limited.Sparse arrays exhibit distinct architectures,roughly classified into three categories:Thinned arrays,nonuniformly spaced arrays,and clustered arrays.While numerous advanced synthesis methods have been presented for the three types of sparse arrays in recent years,a comprehensive review of the latest development in sparse array synthesis is lacking.This work aims to fill this gap by thoroughly summarizing these techniques.The study includes synthesis examples to facilitate a comparative analysis of different techniques in terms of both accuracy and efficiency.Thus,this review is intended to assist researchers and engineers in related fields,offering a clear understanding of the development and distinctions among sparse array synthesis techniques.展开更多
Due to the large scale and high dimension of teaching data,the using of traditional clustering algorithms has problems such as high computational complexity and low accuracy.Therefore,this paper proposes a weighted bl...Due to the large scale and high dimension of teaching data,the using of traditional clustering algorithms has problems such as high computational complexity and low accuracy.Therefore,this paper proposes a weighted block sparse subspace clustering algorithm based on information entropy.The introduction of information entropy weight and block diagonal constraints can obtain the prior probability that two pixels belong to the same category before the simulation experiment,thereby positively intervening that the solutions solved by the model tend to be the optimal approximate solutions of the block diagonal structure.It can enable the model to obtain the performance against noise and outliers,and thereby improving the discriminative ability of the model classification.The experimental results show that the average probability Rand index of the proposed method is 0.86,which is higher than that of other algorithms.The average information change index of the proposed method is 1.55,which is lower than that of other algorithms,proving its strong robustness.On different datasets,the misclassification rates of the design method are 1.2%and 0.9%respectively,which proves that its classification accuracy is relatively high.The proposed method has high reliability in processing highdimensional teaching data.It can play an important role in the field of educational data analysis and provide strong support for intelligent teaching.展开更多
Edge machine learning creates a new computational paradigm by enabling the deployment of intelligent applications at the network edge.It enhances application efficiency and responsiveness by performing inference and t...Edge machine learning creates a new computational paradigm by enabling the deployment of intelligent applications at the network edge.It enhances application efficiency and responsiveness by performing inference and training tasks closer to data sources.However,it encounters several challenges in practice.The variance in hardware specifications and performance across different devices presents a major issue for the training and inference tasks.Additionally,edge devices typically possess limited network bandwidth and computing resources compared with data centers.Moreover,existing distributed training architectures often fail to consider the constraints of resources and communication efficiency in edge environments.In this paper,we propose DSparse,a method for distributed training based on sparse update in edge clusters with various memory capacities.It aims at maximizing the utilization of memory resources across all devices within a cluster.To reduce memory consumption during the training process,we adopt sparse update to prioritize the updating of selected layers on the devices in the cluster,which not only lowers memory usage but also reduces the data volume of parameters and the time required for parameter aggregation.Furthermore,DSparse utilizes a parameter aggregation mechanism based on multi-process groups,subdividing the aggregation tasks into AllReduce and Broadcast types,thereby further reducing the communication frequency for parameter aggregation.Experimental results using the MobileNetV2 model on the CIFAR-10 dataset demonstrate that DSparse reduces memory consumption by an average of 59.6%across seven devices,with a 75.4%reduction in parameter aggregation time,while maintaining model precision.展开更多
Hyperspectral imagery generally contains a very large amount of data due to hundreds of spectral bands.Band selection is often applied firstly to reduce computational cost and facilitate subsequent tasks such as land-...Hyperspectral imagery generally contains a very large amount of data due to hundreds of spectral bands.Band selection is often applied firstly to reduce computational cost and facilitate subsequent tasks such as land-cover classification and higher level image analysis.In this paper,we propose a new band selection algorithm using sparse nonnegative matrix factorization(sparse NMF).Though acting as a clustering method for band selection,sparse NMF need not consider the distance metric between different spectral bands,which is often the key step for most common clustering-based band selection methods.By imposing sparsity on the coefficient matrix,the bands'clustering assignments can be easily indicated through the largest entry in each column of the matrix.Experimental results showed that sparse NMF provides considerable insight into the clustering-based band selection problem and the selected bands are good for land-cover classification.展开更多
Indoor environment quality(IEQ)is one of the most concerned building performances during the operation stage.The non-uniform spatial distribution of various IEQ parameters in large-scale public buildings has been demo...Indoor environment quality(IEQ)is one of the most concerned building performances during the operation stage.The non-uniform spatial distribution of various IEQ parameters in large-scale public buildings has been demonstrated to be an essential factor affecting occupant comfort and building energy consumption.Currently,IEQ sensors have been widely employed in buildings to monitor thermal,visual,acoustic and air quality.However,there is a lack of effective methods for exploring the typical spatial distribution of indoor environmental quality parameters,which is crucial for assessing and controlling non-uniform indoor environments.In this study,a novel clustering method for extracting IEQ spatial distribution patterns is proposed.Firstly,representation vectors reflecting IEQ distributions in the concerned space are generated based on the low-rank sparse representation.Secondly,a multi-step clustering method,which addressed the problems of the“curse of dimensionality”,is designed to obtain typical IEQ distribution patterns of the entire indoor space.The proposed method was applied to the analysis of indoor thermal environment in Beijing Daxing international airport terminal.As a result,four typical temperature spatial distribution patterns of the terminal were extracted from a four-month monitoring,which had been validated for their good representativeness.These typical patterns revealed typical environmental issues in the terminal,such as long-term localized overheating and temperature increases due to a sudden influx of people.The extracted typical IEQ spatial distribution patterns could assist building operators in effectively assessing the uneven distribution of IEQ space under current environmental conditions,facilitating targeted environmental improvements,optimization of thermal comfort levels,and application of energy-saving measures.展开更多
In this paper,we propose an image denoising method combining the priors of non-local self similarity(NSS),low rank and group sparsity.In the proposed scheme,the image is decomposed into overlapping patches,and then th...In this paper,we propose an image denoising method combining the priors of non-local self similarity(NSS),low rank and group sparsity.In the proposed scheme,the image is decomposed into overlapping patches,and then these patches are classified by the K-means clustering.Patches in each cluster are stacked into a matrix and then are decomposed into low frequency component and high frequency component through 2-D wavelet transform.Intuitively,the low frequency component should be a low rank matrix.We show that the high frequency component can be recovered by weighted mixed norm minimization which is also known as group sparse model.Then we propose an image denoising model using nuclear norm and weighted mixed norm as regularizers to enforce the priors on the low and high frequency.The proposed model can be solved efficiently in the framework of alternating direction multiplier method(ADMM)algorithm.Several experiments are carried out to verify the performance of the proposed model.展开更多
Sparse subspace clustering(SSC)is a spectral clustering methodology.Since high-dimensional data are often dispersed over the union of many low-dimensional subspaces,their representation in a suitable dictionary is spa...Sparse subspace clustering(SSC)is a spectral clustering methodology.Since high-dimensional data are often dispersed over the union of many low-dimensional subspaces,their representation in a suitable dictionary is sparse.Therefore,SSC is an effective technology for diagnosing mechanical system faults.Its main purpose is to create a representation model that can reveal the real subspace structure of high-dimensional data,construct a similarity matrix by using the sparse representation coefficients of high-dimensional data,and then cluster the obtained representation coefficients and similarity matrix in subspace.However,the design of SSC algorithm is based on global expression in which each data point is represented by all possible cluster data points.This leads to nonzero terms in nondiagonal blocks of similar matrices,which reduces the recognition performance of matrices.To improve the clustering ability of SSC for rolling bearing and the robustness of the algorithm in the presence of a large number of background noise,a simultaneous dimensionality reduction subspace clustering technology is provided in this work.Through the feature extraction of envelope signal,the dimension of the feature matrix is reduced by singular value decomposition,and the Euclidean distance between samples is replaced by correlation distance.A dimension reduction graph-based SSC technology is established.Simulation and bearing data of Western Reserve University show that the proposed algorithm can improve the accuracy and compactness of clustering.展开更多
文摘An algorithm, Clustering Algorithm Based On Sparse Feature Vector (CABOSFV),was proposed for the high dimensional clustering of binary sparse data. This algorithm compressesthe data effectively by using a tool 'Sparse Feature Vector', thus reduces the data scaleenormously, and can get the clustering result with only one data scan. Both theoretical analysis andempirical tests showed that CABOSFV is of low computational complexity. The algorithm findsclusters in high dimensional large datasets efficiently and handles noise effectively.
基金This work was supported in part by the National Key Research and Development Program of China(2018AAA0100100)the National Natural Science Foundation of China(61822301,61876123,61906001)+2 种基金the Collaborative Innovation Program of Universities in Anhui Province(GXXT-2020-051)the Hong Kong Scholars Program(XJ2019035)Anhui Provincial Natural Science Foundation(1908085QF271).
文摘During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable landscapes.However,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision variables.To tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal solutions.The proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search space.More importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by GPUs.While existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real variables.Furthermore,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.
基金This work was supported by National Natural Science Foundation of China(Nos.U1562218,41604107,and 41804126).
文摘Traditional unsupervised seismic facies analysis techniques need to assume that seismic data obey mixed Gaussian distribution.However,fi eld seismic data may not meet this condition,thereby leading to wrong classifi cation in the application of this technology.This paper introduces a spectral clustering technique for unsupervised seismic facies analysis.This algorithm is based on on the idea of a graph to cluster the data.Its kem is that seismic data are regarded as points in space,points can be connected with the edge and construct to graphs.When the graphs are divided,the weights of the edges between the different subgraphs are as low as possible,whereas the weights of the inner edges of the subgraph should be as high as possible.That has high computational complexity and entails large memory consumption for spectral clustering algorithm.To solve the problem this paper introduces the idea of sparse representation into spectral clustering.Through the selection of a small number of local sparse representation points,the spectral clustering matrix of all sample points is approximately represented to reduce the cost of spectral clustering operation.Verifi cation of physical model and fi eld data shows that the proposed approach can obtain more accurate seismic facies classification results without considering the data meet any hypothesis.The computing efficiency of this new method is better than that of the conventional spectral clustering method,thereby meeting the application needs of fi eld seismic data.
基金Supported by the National Natural Science Foundation of China (No.60872123)the Joint Fund of the National Natural Science Foundation and the Guangdong Provin-cial Natural Science Foundation (No.U0835001)
文摘A clustering algorithm based on Sparse Projection (SP), called Sparse Projection Clus- tering (SPC), is proposed in this letter. The basic idea is applying SP to project the observed data onto a high-dimensional sparse space, which is a nonlinear mapping with an explicit form and the K-means clustering algorithm can be therefore used to explore the inherent data patterns in the new space. The proposed algorithm is applied to cluster a complete artificial dataset and an incomplete real dataset. In comparison with the kernel K-means clustering algorithm, the proposed algorithm is more efficient.
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.
文摘Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on aerial image recognition have been widely used, such as RGB-based and HIS-based methods. However, these methods are susceptible to background factors causing interference and false detection. To alleviate these problems, we investigate two subspace clustering methods based on sparse and collaborative representation, respectively, to detect and locate forest fires. Firstly, subspace clustering segments flame from the whole image. Afterwards, sparse or collaborative representation is employed to represent most of the flame information in a dictionary with l1-regularization or l2-regularization term, which results in fewer reconstruction errors. Experimental results show that the proposed SSC and CSC substantially outperform the state-of-the art methods.
基金the National Natural Science Foundation of China (60672061)
文摘Blind separation of sparse sources （BSSS） is discussed. The BSSS method based on the conventional K-means clustering is very fast and is also easy to implement. However, the accuracy of this method is generally not satisfactory. The contribution of the vector x（t） with different modules is theoretically proved to be unequal, and a weighted K-means clustering method is proposed on this grounds. The proposed algorithm is not only as fast as the conventional K-means clustering method, but can also achieve considerably accurate results, which is demonstrated by numerical experiments.
文摘功能超网络广泛地应用于脑疾病诊断和分类研究中,而现有的关于超网络创建的研究缺乏解释分组效应的能力或者仅考虑到脑区间组级的信息,这样构建的脑功能超网络会丢失一些有用的连接或包含一些虚假的信息,因此,考虑到脑区间的组结构问题,引入sparse group Lasso(sgLasso)方法进一步改善超网络的创建。首先,利用sgLasso方法进行超网络创建;然后,引入两组超网络特有的属性指标进行特征提取以及特征选择,这些指标分别是基于单一节点的聚类系数和基于一对节点的聚类系数;最后,将特征选择后得到的两组有显著差异的特征通过多核学习进行特征融合和分类。实验结果表明,所提方法经过多特征融合取得了87.88%的分类准确率。该结果表明为了改善脑功能超网络的创建,需要考虑到组信息,但不能逼迫使用整组信息,可以适当地对组结构进行扩展。
文摘Computer Tomography in medical imaging provides human internal body pictures in the digital form. The more quality images it provides, the better information we get. Normally, medical imaging can be constructed by projection data from several perspectives. In this paper, our research challenges and describes a numerical method for refining the image of a Region of Interest (ROI) by constructing support within a standard CT image. It is obvious that the quality of tomographic slice is affected by artifacts. CT using filter and K-means clustering provides a way to reconstruct an ROI with minimal artifacts and improve the degree of the spatial resolution. Experimental results are presented for improving the reconstructed images, showing that the approach enhances the overall resolution and contrast of ROI images. Our method provides a number of advantages: robustness with noise in projection data and support construction without the need to acquire any additional setup.
基金supported by the National Natural Science Foundation of China under Grant No.U2341208.
文摘Designing a sparse array with reduced transmit/receive modules(TRMs)is vital for some applications where the antenna system’s size,weight,allowed operating space,and cost are limited.Sparse arrays exhibit distinct architectures,roughly classified into three categories:Thinned arrays,nonuniformly spaced arrays,and clustered arrays.While numerous advanced synthesis methods have been presented for the three types of sparse arrays in recent years,a comprehensive review of the latest development in sparse array synthesis is lacking.This work aims to fill this gap by thoroughly summarizing these techniques.The study includes synthesis examples to facilitate a comparative analysis of different techniques in terms of both accuracy and efficiency.Thus,this review is intended to assist researchers and engineers in related fields,offering a clear understanding of the development and distinctions among sparse array synthesis techniques.
文摘Due to the large scale and high dimension of teaching data,the using of traditional clustering algorithms has problems such as high computational complexity and low accuracy.Therefore,this paper proposes a weighted block sparse subspace clustering algorithm based on information entropy.The introduction of information entropy weight and block diagonal constraints can obtain the prior probability that two pixels belong to the same category before the simulation experiment,thereby positively intervening that the solutions solved by the model tend to be the optimal approximate solutions of the block diagonal structure.It can enable the model to obtain the performance against noise and outliers,and thereby improving the discriminative ability of the model classification.The experimental results show that the average probability Rand index of the proposed method is 0.86,which is higher than that of other algorithms.The average information change index of the proposed method is 1.55,which is lower than that of other algorithms,proving its strong robustness.On different datasets,the misclassification rates of the design method are 1.2%and 0.9%respectively,which proves that its classification accuracy is relatively high.The proposed method has high reliability in processing highdimensional teaching data.It can play an important role in the field of educational data analysis and provide strong support for intelligent teaching.
基金supported by the National Natural Science Foundation of China under Grant Nos.62072434 and U23B2004the Innovation Funding of Institute of Computing Technology,Chinese Academy of Sciences,under Grant Nos.E361050 and E361030.
文摘Edge machine learning creates a new computational paradigm by enabling the deployment of intelligent applications at the network edge.It enhances application efficiency and responsiveness by performing inference and training tasks closer to data sources.However,it encounters several challenges in practice.The variance in hardware specifications and performance across different devices presents a major issue for the training and inference tasks.Additionally,edge devices typically possess limited network bandwidth and computing resources compared with data centers.Moreover,existing distributed training architectures often fail to consider the constraints of resources and communication efficiency in edge environments.In this paper,we propose DSparse,a method for distributed training based on sparse update in edge clusters with various memory capacities.It aims at maximizing the utilization of memory resources across all devices within a cluster.To reduce memory consumption during the training process,we adopt sparse update to prioritize the updating of selected layers on the devices in the cluster,which not only lowers memory usage but also reduces the data volume of parameters and the time required for parameter aggregation.Furthermore,DSparse utilizes a parameter aggregation mechanism based on multi-process groups,subdividing the aggregation tasks into AllReduce and Broadcast types,thereby further reducing the communication frequency for parameter aggregation.Experimental results using the MobileNetV2 model on the CIFAR-10 dataset demonstrate that DSparse reduces memory consumption by an average of 59.6%across seven devices,with a 75.4%reduction in parameter aggregation time,while maintaining model precision.
基金Project(No.60872071)supported by the National Natural Science Foundation of China
文摘Hyperspectral imagery generally contains a very large amount of data due to hundreds of spectral bands.Band selection is often applied firstly to reduce computational cost and facilitate subsequent tasks such as land-cover classification and higher level image analysis.In this paper,we propose a new band selection algorithm using sparse nonnegative matrix factorization(sparse NMF).Though acting as a clustering method for band selection,sparse NMF need not consider the distance metric between different spectral bands,which is often the key step for most common clustering-based band selection methods.By imposing sparsity on the coefficient matrix,the bands'clustering assignments can be easily indicated through the largest entry in each column of the matrix.Experimental results showed that sparse NMF provides considerable insight into the clustering-based band selection problem and the selected bands are good for land-cover classification.
基金the China National Key Research and Development Program(Grant No.2022YFC3801300)the Young Scientists Fund of the National Natural Science Foundation of China(Grant No.52208113)+1 种基金the Key Program of National Natural Science Foundation of China(Grant No.52130803)the Hang Lung Center for Real Estate,Tsinghua University.The authors also express special thanks to the Command Center of Beijing Daxing International Airport for their long-term and strong support to this research.
文摘Indoor environment quality(IEQ)is one of the most concerned building performances during the operation stage.The non-uniform spatial distribution of various IEQ parameters in large-scale public buildings has been demonstrated to be an essential factor affecting occupant comfort and building energy consumption.Currently,IEQ sensors have been widely employed in buildings to monitor thermal,visual,acoustic and air quality.However,there is a lack of effective methods for exploring the typical spatial distribution of indoor environmental quality parameters,which is crucial for assessing and controlling non-uniform indoor environments.In this study,a novel clustering method for extracting IEQ spatial distribution patterns is proposed.Firstly,representation vectors reflecting IEQ distributions in the concerned space are generated based on the low-rank sparse representation.Secondly,a multi-step clustering method,which addressed the problems of the“curse of dimensionality”,is designed to obtain typical IEQ distribution patterns of the entire indoor space.The proposed method was applied to the analysis of indoor thermal environment in Beijing Daxing international airport terminal.As a result,four typical temperature spatial distribution patterns of the terminal were extracted from a four-month monitoring,which had been validated for their good representativeness.These typical patterns revealed typical environmental issues in the terminal,such as long-term localized overheating and temperature increases due to a sudden influx of people.The extracted typical IEQ spatial distribution patterns could assist building operators in effectively assessing the uneven distribution of IEQ space under current environmental conditions,facilitating targeted environmental improvements,optimization of thermal comfort levels,and application of energy-saving measures.
基金Supported by the National Natural Science Foundation of China(61701004)Outstanding Young Talents Support Program of Anhui Province
文摘In this paper,we propose an image denoising method combining the priors of non-local self similarity(NSS),low rank and group sparsity.In the proposed scheme,the image is decomposed into overlapping patches,and then these patches are classified by the K-means clustering.Patches in each cluster are stacked into a matrix and then are decomposed into low frequency component and high frequency component through 2-D wavelet transform.Intuitively,the low frequency component should be a low rank matrix.We show that the high frequency component can be recovered by weighted mixed norm minimization which is also known as group sparse model.Then we propose an image denoising model using nuclear norm and weighted mixed norm as regularizers to enforce the priors on the low and high frequency.The proposed model can be solved efficiently in the framework of alternating direction multiplier method(ADMM)algorithm.Several experiments are carried out to verify the performance of the proposed model.
基金The present work is supported by the National Key R&D Program(No.2020YFB2007700)the National Natural Science Foundation of China(Nos.11790282,11802184,11902205,12002221,12032017)+1 种基金the S&T Program of Hebei(No.20310803D)the Natural Science Foundation of Hebei Province(No.A2020210028).
文摘Sparse subspace clustering(SSC)is a spectral clustering methodology.Since high-dimensional data are often dispersed over the union of many low-dimensional subspaces,their representation in a suitable dictionary is sparse.Therefore,SSC is an effective technology for diagnosing mechanical system faults.Its main purpose is to create a representation model that can reveal the real subspace structure of high-dimensional data,construct a similarity matrix by using the sparse representation coefficients of high-dimensional data,and then cluster the obtained representation coefficients and similarity matrix in subspace.However,the design of SSC algorithm is based on global expression in which each data point is represented by all possible cluster data points.This leads to nonzero terms in nondiagonal blocks of similar matrices,which reduces the recognition performance of matrices.To improve the clustering ability of SSC for rolling bearing and the robustness of the algorithm in the presence of a large number of background noise,a simultaneous dimensionality reduction subspace clustering technology is provided in this work.Through the feature extraction of envelope signal,the dimension of the feature matrix is reduced by singular value decomposition,and the Euclidean distance between samples is replaced by correlation distance.A dimension reduction graph-based SSC technology is established.Simulation and bearing data of Western Reserve University show that the proposed algorithm can improve the accuracy and compactness of clustering.
文摘在高压并联电抗器声纹信号监测系统中,长时海量无标签声纹的高维非平稳性导致特征提取困难、无监督聚类适应性差。由此提出了一种基于深度自适应K-means++算法(deep adaptive K-means++clustering algorithm,DAKCA)的750 kV电抗器声纹聚类方法。首先通过采用两阶段无监督策略微调的改进堆叠稀疏自编码器(stacked sparse autoencoder,SSAE),对快速傅里叶变换后的归一化频域数据提取电抗器原始声纹32维深度特征。进一步提出了依据最近邻聚类有效性指标(clustering validation index based on nearest neighbors,CVNN)的自适应K-means++聚类算法,构建了能自适应确定最优聚类个数的电抗器声纹聚类模型。最后通过西北地区某750 kV电抗器实测声纹数据集进行了验证。结果表明,DAKCA算法对无标签声纹数据在不同样本均衡程度下能够稳定提取32维深度特征,并实现最优聚类,为直接高效利用电抗器无标签声纹数据提供了参考。
