Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from nume...Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from numerous irrelevant and redundant features in high-dimensional imbalanced data,we proposed a novel feature selection method named AMF-SGSK based on adaptive multi-filter and subspace-based gaining sharing knowledge.Firstly,the balanced dataset was obtained by random under-sampling.Secondly,combining the feature importance score with the AUC score for each filter method,we proposed a concept called feature hardness to judge the importance of feature,which could adaptively select the essential features.Finally,the optimal feature subset was obtained by gaining sharing knowledge in multiple subspaces.This approach effectively achieved dimensionality reduction for high-dimensional imbalanced data.The experiment results on 30 benchmark imbalanced datasets showed that AMF-SGSK performed better than other eight commonly used algorithms including BGWO and IG-SSO in terms of F1-score,AUC,and G-mean.The mean values of F1-score,AUC,and Gmean for AMF-SGSK are 0.950,0.967,and 0.965,respectively,achieving the highest among all algorithms.And the mean value of Gmean is higher than those of IG-PSO,ReliefF-GWO,and BGOA by 3.72%,11.12%,and 20.06%,respectively.Furthermore,the selected feature ratio is below 0.01 across the selected ten datasets,further demonstrating the proposed method’s overall superiority over competing approaches.AMF-SGSK could adaptively remove irrelevant and redundant features and effectively improve the classification accuracy of high-dimensional imbalanced data,providing scientific and technological references for practical applications.展开更多
The performance of conventional similarity measurement methods is affected seriously by the curse of dimensionality of high-dimensional data.The reason is that data difference between sparse and noisy dimensionalities...The performance of conventional similarity measurement methods is affected seriously by the curse of dimensionality of high-dimensional data.The reason is that data difference between sparse and noisy dimensionalities occupies a large proportion of the similarity,leading to the dissimilarities between any results.A similarity measurement method of high-dimensional data based on normalized net lattice subspace is proposed.The data range of each dimension is divided into several intervals,and the components in different dimensions are mapped onto the corresponding interval.Only the component in the same or adjacent interval is used to calculate the similarity.To validate this method,three data types are used,and seven common similarity measurement methods are compared.The experimental result indicates that the relative difference of the method is increasing with the dimensionality and is approximately two or three orders of magnitude higher than the conventional method.In addition,the similarity range of this method in different dimensions is [0,1],which is fit for similarity analysis after dimensionality reduction.展开更多
As a crucial data preprocessing method in data mining,feature selection(FS)can be regarded as a bi-objective optimization problem that aims to maximize classification accuracy and minimize the number of selected featu...As a crucial data preprocessing method in data mining,feature selection(FS)can be regarded as a bi-objective optimization problem that aims to maximize classification accuracy and minimize the number of selected features.Evolutionary computing(EC)is promising for FS owing to its powerful search capability.However,in traditional EC-based methods,feature subsets are represented via a length-fixed individual encoding.It is ineffective for high-dimensional data,because it results in a huge search space and prohibitive training time.This work proposes a length-adaptive non-dominated sorting genetic algorithm(LA-NSGA)with a length-variable individual encoding and a length-adaptive evolution mechanism for bi-objective highdimensional FS.In LA-NSGA,an initialization method based on correlation and redundancy is devised to initialize individuals of diverse lengths,and a Pareto dominance-based length change operator is introduced to guide individuals to explore in promising search space adaptively.Moreover,a dominance-based local search method is employed for further improvement.The experimental results based on 12 high-dimensional gene datasets show that the Pareto front of feature subsets produced by LA-NSGA is superior to those of existing algorithms.展开更多
Objective Humans are exposed to complex mixtures of environmental chemicals and other factors that can affect their health.Analysis of these mixture exposures presents several key challenges for environmental epidemio...Objective Humans are exposed to complex mixtures of environmental chemicals and other factors that can affect their health.Analysis of these mixture exposures presents several key challenges for environmental epidemiology and risk assessment,including high dimensionality,correlated exposure,and subtle individual effects.Methods We proposed a novel statistical approach,the generalized functional linear model(GFLM),to analyze the health effects of exposure mixtures.GFLM treats the effect of mixture exposures as a smooth function by reordering exposures based on specific mechanisms and capturing internal correlations to provide a meaningful estimation and interpretation.The robustness and efficiency was evaluated under various scenarios through extensive simulation studies.Results We applied the GFLM to two datasets from the National Health and Nutrition Examination Survey(NHANES).In the first application,we examined the effects of 37 nutrients on BMI(2011–2016 cycles).The GFLM identified a significant mixture effect,with fiber and fat emerging as the nutrients with the greatest negative and positive effects on BMI,respectively.For the second application,we investigated the association between four pre-and perfluoroalkyl substances(PFAS)and gout risk(2007–2018 cycles).Unlike traditional methods,the GFLM indicated no significant association,demonstrating its robustness to multicollinearity.Conclusion GFLM framework is a powerful tool for mixture exposure analysis,offering improved handling of correlated exposures and interpretable results.It demonstrates robust performance across various scenarios and real-world applications,advancing our understanding of complex environmental exposures and their health impacts on environmental epidemiology and toxicology.展开更多
Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmenta...Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.展开更多
Problems existin similarity measurement and index tree construction which affect the performance of nearest neighbor search of high-dimensional data. The equidistance problem is solved using NPsim function to calculat...Problems existin similarity measurement and index tree construction which affect the performance of nearest neighbor search of high-dimensional data. The equidistance problem is solved using NPsim function to calculate similarity. And a sequential NPsim matrix is built to improve indexing performance. To sum up the above innovations,a nearest neighbor search algorithm of high-dimensional data based on sequential NPsim matrix is proposed in comparison with the nearest neighbor search algorithms based on KD-tree or SR-tree on Munsell spectral data set. Experimental results show that the proposed algorithm similarity is better than that of other algorithms and searching speed is more than thousands times of others. In addition,the slow construction speed of sequential NPsim matrix can be increased by using parallel computing.展开更多
High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation lear...High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation learning to an HDI matrix,whose hyper-parameter adaptation can be implemented through a particle swarm optimizer(PSO) to meet scalable requirements.However, conventional PSO is limited by its premature issues,which leads to the accuracy loss of a resultant LFA model. To address this thorny issue, this study merges the information of each particle's state migration into its evolution process following the principle of a generalized momentum method for improving its search ability, thereby building a state-migration particle swarm optimizer(SPSO), whose theoretical convergence is rigorously proved in this study. It is then incorporated into an LFA model for implementing efficient hyper-parameter adaptation without accuracy loss. Experiments on six HDI matrices indicate that an SPSO-incorporated LFA model outperforms state-of-the-art LFA models in terms of prediction accuracy for missing data of an HDI matrix with competitive computational efficiency.Hence, SPSO's use ensures efficient and reliable hyper-parameter adaptation in an LFA model, thus ensuring practicality and accurate representation learning for HDI matrices.展开更多
In this paper,we introduce the censored composite conditional quantile coefficient(cC-CQC)to rank the relative importance of each predictor in high-dimensional censored regression.The cCCQC takes advantage of all usef...In this paper,we introduce the censored composite conditional quantile coefficient(cC-CQC)to rank the relative importance of each predictor in high-dimensional censored regression.The cCCQC takes advantage of all useful information across quantiles and can detect nonlinear effects including interactions and heterogeneity,effectively.Furthermore,the proposed screening method based on cCCQC is robust to the existence of outliers and enjoys the sure screening property.Simulation results demonstrate that the proposed method performs competitively on survival datasets of high-dimensional predictors,particularly when the variables are highly correlated.展开更多
Viticulturists traditionally have a keen interest in studying the relationship between the biochemistry of grapevines’ leaves/petioles and their associated spectral reflectance in order to understand the fruit ripeni...Viticulturists traditionally have a keen interest in studying the relationship between the biochemistry of grapevines’ leaves/petioles and their associated spectral reflectance in order to understand the fruit ripening rate, water status, nutrient levels, and disease risk. In this paper, we implement imaging spectroscopy (hyperspectral) reflectance data, for the reflective 330 - 2510 nm wavelength region (986 total spectral bands), to assess vineyard nutrient status;this constitutes a high dimensional dataset with a covariance matrix that is ill-conditioned. The identification of the variables (wavelength bands) that contribute useful information for nutrient assessment and prediction, plays a pivotal role in multivariate statistical modeling. In recent years, researchers have successfully developed many continuous, nearly unbiased, sparse and accurate variable selection methods to overcome this problem. This paper compares four regularized and one functional regression methods: Elastic Net, Multi-Step Adaptive Elastic Net, Minimax Concave Penalty, iterative Sure Independence Screening, and Functional Data Analysis for wavelength variable selection. Thereafter, the predictive performance of these regularized sparse models is enhanced using the stepwise regression. This comparative study of regression methods using a high-dimensional and highly correlated grapevine hyperspectral dataset revealed that the performance of Elastic Net for variable selection yields the best predictive ability.展开更多
The estimation of covariance matrices is very important in many fields, such as statistics. In real applications, data are frequently influenced by high dimensions and noise. However, most relevant studies are based o...The estimation of covariance matrices is very important in many fields, such as statistics. In real applications, data are frequently influenced by high dimensions and noise. However, most relevant studies are based on complete data. This paper studies the optimal estimation of high-dimensional covariance matrices based on missing and noisy sample under the norm. First, the model with sub-Gaussian additive noise is presented. The generalized sample covariance is then modified to define a hard thresholding estimator , and the minimax upper bound is derived. After that, the minimax lower bound is derived, and it is concluded that the estimator presented in this article is rate-optimal. Finally, numerical simulation analysis is performed. The result shows that for missing samples with sub-Gaussian noise, if the true covariance matrix is sparse, the hard thresholding estimator outperforms the traditional estimate method.展开更多
In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often fa...In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often face challenges with handling high-resolution images and achieving accurate detection against complex backgrounds.To address these issues,this study employs the PatchCore unsupervised anomaly detection algorithm combined with data augmentation techniques to enhance the system’s generalization capability across varying lighting conditions,viewing angles,and object scales.The proposed method is evaluated in a complex industrial detection scenario involving the bogie of an electric multiple unit(EMU).A dataset consisting of complex backgrounds,diverse lighting conditions,and multiple viewing angles is constructed to validate the performance of the detection system in real industrial environments.Experimental results show that the proposed model achieves an average area under the receiver operating characteristic curve(AUROC)of 0.92 and an average F1 score of 0.85.Combined with data augmentation,the proposed model exhibits improvements in AUROC by 0.06 and F1 score by 0.03,demonstrating enhanced accuracy and robustness for foreign object detection in complex industrial settings.In addition,the effects of key factors on detection performance are systematically analyzed,providing practical guidance for parameter selection in real industrial applications.展开更多
Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available f...Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available from real-world systems.To address this issue, Prof.展开更多
An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introdu...An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introduced herewith. A feasible approach to select the “best” data model for an application is to analyze the data which has to be stored in the database. A data model is appropriate for modelling a given task if the information of the application environment can be easily mapped to the data model. Thus, the involved data are analyzed and then object oriented data model appropriate for CAD applications are derived. Based on the reviewed object oriented techniques applied in CAD, object oriented data modelling in CAD is addressed in details. At last 3D geometrical data models and implementation of their data model using the object oriented method are presented.展开更多
It is difficult to parallelize a subsistent sequential algorithm. Through analyzing the sequential algorithm of a Global Atmospheric Data Objective Analysis System, this article puts forward a distributed parallel alg...It is difficult to parallelize a subsistent sequential algorithm. Through analyzing the sequential algorithm of a Global Atmospheric Data Objective Analysis System, this article puts forward a distributed parallel algorithm that statically distributes data on a massively parallel processing (MPP) computer. The algorithm realizes distributed parailelization by extracting the analysis boxes and model grid point Iatitude rows with leaped steps, and by distributing the data to different processors. The parallel algorithm achieves good load balancing, high parallel efficiency, and low parallel cost. Performance experiments on a MPP computer arc also presented.展开更多
Latent factor(LF)models are highly effective in extracting useful knowledge from High-Dimensional and Sparse(HiDS)matrices which are commonly seen in various industrial applications.An LF model usually adopts iterativ...Latent factor(LF)models are highly effective in extracting useful knowledge from High-Dimensional and Sparse(HiDS)matrices which are commonly seen in various industrial applications.An LF model usually adopts iterative optimizers,which may consume many iterations to achieve a local optima,resulting in considerable time cost.Hence,determining how to accelerate the training process for LF models has become a significant issue.To address this,this work proposes a randomized latent factor(RLF)model.It incorporates the principle of randomized learning techniques from neural networks into the LF analysis of HiDS matrices,thereby greatly alleviating computational burden.It also extends a standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix correctly.Experimental results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models,RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data.I provides an important alternative approach to LF analysis of HiDS matrices,which is especially desired for industrial applications demanding highly efficient models.展开更多
Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.T...Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.展开更多
The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data s...The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data can be of importance in object identification, community planning, resource discovery and other areas. In this paper, a data field is presented to express the observed spatial objects and conduct behavior mining on them. First, most of the important aspects are discussed on behavior mining and its implications for the future of data mining. Furthermore, an ideal framework of the behavior mining system is proposed in the network environment. Second, the model of behavior mining is given on the observed spatial objects, including the objects described by the first feature data field and the main feature data field by means of the potential function. Finally, a case study about object identification in public is given and analyzed. The experimental results show that the new model is feasible in behavior mining.展开更多
Aimed at the issue that traditional clustering methods are not appropriate to high-dimensional data, a cuckoo search fuzzy-weighting algorithm for subspace clustering is presented on the basis of the exited soft subsp...Aimed at the issue that traditional clustering methods are not appropriate to high-dimensional data, a cuckoo search fuzzy-weighting algorithm for subspace clustering is presented on the basis of the exited soft subspace clustering algorithm. In the proposed algorithm, a novel objective function is firstly designed by considering the fuzzy weighting within-cluster compactness and the between-cluster separation, and loosening the constraints of dimension weight matrix. Then gradual membership and improved Cuckoo search, a global search strategy, are introduced to optimize the objective function and search subspace clusters, giving novel learning rules for clustering. At last, the performance of the proposed algorithm on the clustering analysis of various low and high dimensional datasets is experimentally compared with that of several competitive subspace clustering algorithms. Experimental studies demonstrate that the proposed algorithm can obtain better performance than most of the existing soft subspace clustering algorithms.展开更多
基金supported by Fundamental Research Program of Shanxi Province(Nos.202203021211088,202403021212254,202403021221109)Graduate Research Innovation Project in Shanxi Province(No.2024KY616).
文摘Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from numerous irrelevant and redundant features in high-dimensional imbalanced data,we proposed a novel feature selection method named AMF-SGSK based on adaptive multi-filter and subspace-based gaining sharing knowledge.Firstly,the balanced dataset was obtained by random under-sampling.Secondly,combining the feature importance score with the AUC score for each filter method,we proposed a concept called feature hardness to judge the importance of feature,which could adaptively select the essential features.Finally,the optimal feature subset was obtained by gaining sharing knowledge in multiple subspaces.This approach effectively achieved dimensionality reduction for high-dimensional imbalanced data.The experiment results on 30 benchmark imbalanced datasets showed that AMF-SGSK performed better than other eight commonly used algorithms including BGWO and IG-SSO in terms of F1-score,AUC,and G-mean.The mean values of F1-score,AUC,and Gmean for AMF-SGSK are 0.950,0.967,and 0.965,respectively,achieving the highest among all algorithms.And the mean value of Gmean is higher than those of IG-PSO,ReliefF-GWO,and BGOA by 3.72%,11.12%,and 20.06%,respectively.Furthermore,the selected feature ratio is below 0.01 across the selected ten datasets,further demonstrating the proposed method’s overall superiority over competing approaches.AMF-SGSK could adaptively remove irrelevant and redundant features and effectively improve the classification accuracy of high-dimensional imbalanced data,providing scientific and technological references for practical applications.
基金Supported by the National Natural Science Foundation of China(No.61502475)the Importation and Development of High-Caliber Talents Project of the Beijing Municipal Institutions(No.CIT&TCD201504039)
文摘The performance of conventional similarity measurement methods is affected seriously by the curse of dimensionality of high-dimensional data.The reason is that data difference between sparse and noisy dimensionalities occupies a large proportion of the similarity,leading to the dissimilarities between any results.A similarity measurement method of high-dimensional data based on normalized net lattice subspace is proposed.The data range of each dimension is divided into several intervals,and the components in different dimensions are mapped onto the corresponding interval.Only the component in the same or adjacent interval is used to calculate the similarity.To validate this method,three data types are used,and seven common similarity measurement methods are compared.The experimental result indicates that the relative difference of the method is increasing with the dimensionality and is approximately two or three orders of magnitude higher than the conventional method.In addition,the similarity range of this method in different dimensions is [0,1],which is fit for similarity analysis after dimensionality reduction.
基金supported in part by the National Natural Science Foundation of China(62172065,62072060)。
文摘As a crucial data preprocessing method in data mining,feature selection(FS)can be regarded as a bi-objective optimization problem that aims to maximize classification accuracy and minimize the number of selected features.Evolutionary computing(EC)is promising for FS owing to its powerful search capability.However,in traditional EC-based methods,feature subsets are represented via a length-fixed individual encoding.It is ineffective for high-dimensional data,because it results in a huge search space and prohibitive training time.This work proposes a length-adaptive non-dominated sorting genetic algorithm(LA-NSGA)with a length-variable individual encoding and a length-adaptive evolution mechanism for bi-objective highdimensional FS.In LA-NSGA,an initialization method based on correlation and redundancy is devised to initialize individuals of diverse lengths,and a Pareto dominance-based length change operator is introduced to guide individuals to explore in promising search space adaptively.Moreover,a dominance-based local search method is employed for further improvement.The experimental results based on 12 high-dimensional gene datasets show that the Pareto front of feature subsets produced by LA-NSGA is superior to those of existing algorithms.
基金supported in part by the Young Scientists Fund of the National Natural Science Foundation of China(Grant Nos.82304253)(and 82273709)the Foundation for Young Talents in Higher Education of Guangdong Province(Grant No.2022KQNCX021)the PhD Starting Project of Guangdong Medical University(Grant No.GDMUB2022054).
文摘Objective Humans are exposed to complex mixtures of environmental chemicals and other factors that can affect their health.Analysis of these mixture exposures presents several key challenges for environmental epidemiology and risk assessment,including high dimensionality,correlated exposure,and subtle individual effects.Methods We proposed a novel statistical approach,the generalized functional linear model(GFLM),to analyze the health effects of exposure mixtures.GFLM treats the effect of mixture exposures as a smooth function by reordering exposures based on specific mechanisms and capturing internal correlations to provide a meaningful estimation and interpretation.The robustness and efficiency was evaluated under various scenarios through extensive simulation studies.Results We applied the GFLM to two datasets from the National Health and Nutrition Examination Survey(NHANES).In the first application,we examined the effects of 37 nutrients on BMI(2011–2016 cycles).The GFLM identified a significant mixture effect,with fiber and fat emerging as the nutrients with the greatest negative and positive effects on BMI,respectively.For the second application,we investigated the association between four pre-and perfluoroalkyl substances(PFAS)and gout risk(2007–2018 cycles).Unlike traditional methods,the GFLM indicated no significant association,demonstrating its robustness to multicollinearity.Conclusion GFLM framework is a powerful tool for mixture exposure analysis,offering improved handling of correlated exposures and interpretable results.It demonstrates robust performance across various scenarios and real-world applications,advancing our understanding of complex environmental exposures and their health impacts on environmental epidemiology and toxicology.
基金supported by National Natural Science Foundation of China(61673186 and 61871196)Beijing Normal University Education Reform Project(jx2024040)Guangdong Undergraduate Universities Teaching Quality and Reform Project(jx2024309).
文摘Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.
基金Supported by the National Natural Science Foundation of China(No.61300078)the Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions(No.CIT&TCD201504039)+1 种基金Funding Project for Academic Human Resources Development in Beijing Union University(No.BPHR2014A03,Rk100201510)"New Start"Academic Research Projects of Beijing Union University(No.Hzk10201501)
文摘Problems existin similarity measurement and index tree construction which affect the performance of nearest neighbor search of high-dimensional data. The equidistance problem is solved using NPsim function to calculate similarity. And a sequential NPsim matrix is built to improve indexing performance. To sum up the above innovations,a nearest neighbor search algorithm of high-dimensional data based on sequential NPsim matrix is proposed in comparison with the nearest neighbor search algorithms based on KD-tree or SR-tree on Munsell spectral data set. Experimental results show that the proposed algorithm similarity is better than that of other algorithms and searching speed is more than thousands times of others. In addition,the slow construction speed of sequential NPsim matrix can be increased by using parallel computing.
基金supported in part by the National Natural Science Foundation of China (62372385, 62272078, 62002337)the Chongqing Natural Science Foundation (CSTB2022NSCQ-MSX1486, CSTB2023NSCQ-LZX0069)the Deanship of Scientific Research at King Abdulaziz University, Jeddah, Saudi Arabia (RG-12-135-43)。
文摘High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation learning to an HDI matrix,whose hyper-parameter adaptation can be implemented through a particle swarm optimizer(PSO) to meet scalable requirements.However, conventional PSO is limited by its premature issues,which leads to the accuracy loss of a resultant LFA model. To address this thorny issue, this study merges the information of each particle's state migration into its evolution process following the principle of a generalized momentum method for improving its search ability, thereby building a state-migration particle swarm optimizer(SPSO), whose theoretical convergence is rigorously proved in this study. It is then incorporated into an LFA model for implementing efficient hyper-parameter adaptation without accuracy loss. Experiments on six HDI matrices indicate that an SPSO-incorporated LFA model outperforms state-of-the-art LFA models in terms of prediction accuracy for missing data of an HDI matrix with competitive computational efficiency.Hence, SPSO's use ensures efficient and reliable hyper-parameter adaptation in an LFA model, thus ensuring practicality and accurate representation learning for HDI matrices.
基金Outstanding Youth Foundation of Hunan Provincial Department of Education(Grant No.22B0911)。
文摘In this paper,we introduce the censored composite conditional quantile coefficient(cC-CQC)to rank the relative importance of each predictor in high-dimensional censored regression.The cCCQC takes advantage of all useful information across quantiles and can detect nonlinear effects including interactions and heterogeneity,effectively.Furthermore,the proposed screening method based on cCCQC is robust to the existence of outliers and enjoys the sure screening property.Simulation results demonstrate that the proposed method performs competitively on survival datasets of high-dimensional predictors,particularly when the variables are highly correlated.
文摘Viticulturists traditionally have a keen interest in studying the relationship between the biochemistry of grapevines’ leaves/petioles and their associated spectral reflectance in order to understand the fruit ripening rate, water status, nutrient levels, and disease risk. In this paper, we implement imaging spectroscopy (hyperspectral) reflectance data, for the reflective 330 - 2510 nm wavelength region (986 total spectral bands), to assess vineyard nutrient status;this constitutes a high dimensional dataset with a covariance matrix that is ill-conditioned. The identification of the variables (wavelength bands) that contribute useful information for nutrient assessment and prediction, plays a pivotal role in multivariate statistical modeling. In recent years, researchers have successfully developed many continuous, nearly unbiased, sparse and accurate variable selection methods to overcome this problem. This paper compares four regularized and one functional regression methods: Elastic Net, Multi-Step Adaptive Elastic Net, Minimax Concave Penalty, iterative Sure Independence Screening, and Functional Data Analysis for wavelength variable selection. Thereafter, the predictive performance of these regularized sparse models is enhanced using the stepwise regression. This comparative study of regression methods using a high-dimensional and highly correlated grapevine hyperspectral dataset revealed that the performance of Elastic Net for variable selection yields the best predictive ability.
文摘The estimation of covariance matrices is very important in many fields, such as statistics. In real applications, data are frequently influenced by high dimensions and noise. However, most relevant studies are based on complete data. This paper studies the optimal estimation of high-dimensional covariance matrices based on missing and noisy sample under the norm. First, the model with sub-Gaussian additive noise is presented. The generalized sample covariance is then modified to define a hard thresholding estimator , and the minimax upper bound is derived. After that, the minimax lower bound is derived, and it is concluded that the estimator presented in this article is rate-optimal. Finally, numerical simulation analysis is performed. The result shows that for missing samples with sub-Gaussian noise, if the true covariance matrix is sparse, the hard thresholding estimator outperforms the traditional estimate method.
文摘In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often face challenges with handling high-resolution images and achieving accurate detection against complex backgrounds.To address these issues,this study employs the PatchCore unsupervised anomaly detection algorithm combined with data augmentation techniques to enhance the system’s generalization capability across varying lighting conditions,viewing angles,and object scales.The proposed method is evaluated in a complex industrial detection scenario involving the bogie of an electric multiple unit(EMU).A dataset consisting of complex backgrounds,diverse lighting conditions,and multiple viewing angles is constructed to validate the performance of the detection system in real industrial environments.Experimental results show that the proposed model achieves an average area under the receiver operating characteristic curve(AUROC)of 0.92 and an average F1 score of 0.85.Combined with data augmentation,the proposed model exhibits improvements in AUROC by 0.06 and F1 score by 0.03,demonstrating enhanced accuracy and robustness for foreign object detection in complex industrial settings.In addition,the effects of key factors on detection performance are systematically analyzed,providing practical guidance for parameter selection in real industrial applications.
基金supported by the grants from CASthe National Key R&D Program of Chinathe National Natural Science Foundation of China
文摘Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available from real-world systems.To address this issue, Prof.
文摘An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introduced herewith. A feasible approach to select the “best” data model for an application is to analyze the data which has to be stored in the database. A data model is appropriate for modelling a given task if the information of the application environment can be easily mapped to the data model. Thus, the involved data are analyzed and then object oriented data model appropriate for CAD applications are derived. Based on the reviewed object oriented techniques applied in CAD, object oriented data modelling in CAD is addressed in details. At last 3D geometrical data models and implementation of their data model using the object oriented method are presented.
文摘It is difficult to parallelize a subsistent sequential algorithm. Through analyzing the sequential algorithm of a Global Atmospheric Data Objective Analysis System, this article puts forward a distributed parallel algorithm that statically distributes data on a massively parallel processing (MPP) computer. The algorithm realizes distributed parailelization by extracting the analysis boxes and model grid point Iatitude rows with leaped steps, and by distributing the data to different processors. The parallel algorithm achieves good load balancing, high parallel efficiency, and low parallel cost. Performance experiments on a MPP computer arc also presented.
基金supported in part by the National Natural Science Foundation of China (6177249391646114)+1 种基金Chongqing research program of technology innovation and application (cstc2017rgzn-zdyfX0020)in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciences
文摘Latent factor(LF)models are highly effective in extracting useful knowledge from High-Dimensional and Sparse(HiDS)matrices which are commonly seen in various industrial applications.An LF model usually adopts iterative optimizers,which may consume many iterations to achieve a local optima,resulting in considerable time cost.Hence,determining how to accelerate the training process for LF models has become a significant issue.To address this,this work proposes a randomized latent factor(RLF)model.It incorporates the principle of randomized learning techniques from neural networks into the LF analysis of HiDS matrices,thereby greatly alleviating computational burden.It also extends a standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix correctly.Experimental results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models,RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data.I provides an important alternative approach to LF analysis of HiDS matrices,which is especially desired for industrial applications demanding highly efficient models.
基金Projects(61001188,1161140319)supported by the National Natural Science Foundation of ChinaProject(2012ZX03001034)supported by the National Science and Technology Major ProjectProject(YETP1202)supported by Beijing Higher Education Young Elite Teacher Project,China
文摘Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.
基金Supported by the National 973 Program of China(No.2006CB701305,No.2007CB310804)the National Natural Science Fundation of China(No.60743001)+1 种基金the Best National Thesis Fundation (No.2005047)the National New Century Excellent Talent Fundation (No.NCET-06-0618)
文摘The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data can be of importance in object identification, community planning, resource discovery and other areas. In this paper, a data field is presented to express the observed spatial objects and conduct behavior mining on them. First, most of the important aspects are discussed on behavior mining and its implications for the future of data mining. Furthermore, an ideal framework of the behavior mining system is proposed in the network environment. Second, the model of behavior mining is given on the observed spatial objects, including the objects described by the first feature data field and the main feature data field by means of the potential function. Finally, a case study about object identification in public is given and analyzed. The experimental results show that the new model is feasible in behavior mining.
基金supported in part by the National Natural Science Foundation of China (Nos. 61303074, 61309013)the Programs for Science, National Key Basic Research and Development Program ("973") of China (No. 2012CB315900)Technology Development of Henan province (Nos.12210231003, 13210231002)
文摘Aimed at the issue that traditional clustering methods are not appropriate to high-dimensional data, a cuckoo search fuzzy-weighting algorithm for subspace clustering is presented on the basis of the exited soft subspace clustering algorithm. In the proposed algorithm, a novel objective function is firstly designed by considering the fuzzy weighting within-cluster compactness and the between-cluster separation, and loosening the constraints of dimension weight matrix. Then gradual membership and improved Cuckoo search, a global search strategy, are introduced to optimize the objective function and search subspace clusters, giving novel learning rules for clustering. At last, the performance of the proposed algorithm on the clustering analysis of various low and high dimensional datasets is experimentally compared with that of several competitive subspace clustering algorithms. Experimental studies demonstrate that the proposed algorithm can obtain better performance than most of the existing soft subspace clustering algorithms.
