Controlled experiments are widely used in many applications to investigate the causal relationship between input factors and experimental outcomes.A completely randomised design is usually used to randomly assign trea...Controlled experiments are widely used in many applications to investigate the causal relationship between input factors and experimental outcomes.A completely randomised design is usually used to randomly assign treatment levels to experimental units.When covariates of the experimental units are available,the experimental design should achieve covariate balancing among the treatment groups,such that the statistical inference of the treatment effects is not confounded with any possible effects of covariates.However,covariate imbalance often exists,because the experiment is carried out based on a single realisation of the complete randomisation.It is more likely to occur and worsen when the size of the experimental units is small or moderate.In this paper,we introduce a new covariate balancing criterion,which measures the differences between kernel density estimates of the covariates of treatment groups.To achieve covariate balance before the treatments are randomly assigned,we partition the experimental units by minimising the criterion,then randomly assign the treatment levels to the partitioned groups.Through numerical examples,weshow that the proposed partition approach can improve the accuracy of the difference-in-mean estimator and outperforms the complete randomisation and rerandomisation approaches.展开更多
Let {Xn, n≥1} be a strictly stationary sequence of random variables, which are either associated or negatively associated, f(.) be their common density. In this paper, the author shows a central limit theorem for a k...Let {Xn, n≥1} be a strictly stationary sequence of random variables, which are either associated or negatively associated, f(.) be their common density. In this paper, the author shows a central limit theorem for a kernel estimate of f(.) under certain regular conditions.展开更多
Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional...Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.展开更多
One-class support vector machine （OCSVM） and support vector data description （SVDD） are two main domain-based one-class （kernel） classifiers. To reveal their relationship with density estimation in the case of t...One-class support vector machine （OCSVM） and support vector data description （SVDD） are two main domain-based one-class （kernel） classifiers. To reveal their relationship with density estimation in the case of the Gaussian kernel, OCSVM and SVDD are firstly unified into the framework of kernel density estimation, and the essential relationship between them is explicitly revealed. Then the result proves that the density estimation induced by OCSVM or SVDD is in agreement with the true density. Meanwhile, it can also reduce the integrated squared error （ISE）. Finally, experiments on several simulated datasets verify the revealed relationships.展开更多
In this paper we study a fractional stochastic heat equation on Rd （d 〉 1） with additive noise /t u（t, x） = Dα/δ u（t, x）＋ b（u（t, x） ） ＋ WH （t, x） where D α/δ is a nonlocal fractional differential...In this paper we study a fractional stochastic heat equation on Rd （d 〉 1） with additive noise /t u（t, x） = Dα/δ u（t, x）＋ b（u（t, x） ） ＋ WH （t, x） where D α/δ is a nonlocal fractional differential operator and W H is a Gaussian-colored noise. We show the existence and the uniqueness of the mild solution for this equation. In addition, in the case of space dimension d = 1, we prove the existence of the density for this solution and we establish lower and upper Gaussian bounds for the density by Malliavin calculus.展开更多
Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the t...Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the two methods is that the components of PCA are still dependent while ICA has no orthogonality constraint and its latentvariables are independent. Process monitoring with PCA often supposes that process data or principal components is Gaussian distribution. However, this kind of constraint cannot be satisfied by several practical processes. To ex-tend the use of PCA, a nonparametric method is added to PCA to overcome the difficulty, and kernel density estimation （KDE） is rather a good choice. Though ICA is based on non-Gaussian distribution intormation, .KDE can help in the close monitoring of the data. Methods, such as PCA, ICA, PCA.with .KDE（KPCA）, and ICA with KDE,（KICA）, are demonstrated and. compared by applying them to a practical industnal Spheripol craft polypropylene catalyzer reactor instead of a laboratory emulator.展开更多
In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd dat...In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.展开更多
Monitoring sensors in complex engineering environments often record abnormal data,leading to significant positioning errors.To reduce the influence of abnormal arrival times,we introduce an innovative,outlier-robust l...Monitoring sensors in complex engineering environments often record abnormal data,leading to significant positioning errors.To reduce the influence of abnormal arrival times,we introduce an innovative,outlier-robust localization method that integrates kernel density estimation(KDE)with damping linear correction to enhance the precision of microseismic/acoustic emission(MS/AE)source positioning.Our approach systematically addresses abnormal arrival times through a three-step process:initial location by 4-arrival combinations,elimination of outliers based on three-dimensional KDE,and refinement using a linear correction with an adaptive damping factor.We validate our method through lead-breaking experiments,demonstrating over a 23%improvement in positioning accuracy with a maximum error of 9.12 mm(relative error of 15.80%)—outperforming 4 existing methods.Simulations under various system errors,outlier scales,and ratios substantiate our method’s superior performance.Field blasting experiments also confirm the practical applicability,with an average positioning error of 11.71 m(relative error of 7.59%),compared to 23.56,66.09,16.95,and 28.52 m for other methods.This research is significant as it enhances the robustness of MS/AE source localization when confronted with data anomalies.It also provides a practical solution for real-world engineering and safety monitoring applications.展开更多
Crowd density is an important factor of crowd stability.Previous crowd density estimation methods are highly dependent on the specific video scene.This paper presented a video scene invariant crowd density estimation ...Crowd density is an important factor of crowd stability.Previous crowd density estimation methods are highly dependent on the specific video scene.This paper presented a video scene invariant crowd density estimation method using Geographic Information Systems(GIS) to monitor crowd size for large areas.The proposed method mapped crowd images to GIS.Then we can estimate crowd density for each camera in GIS using an estimation model obtained by one camera.Test results show that one model obtained by one camera in GIS can be adaptively applied to other cameras in outdoor video scenes.A real-time monitoring system for crowd size in large areas based on scene invariant model has been successfully used in 'Jiangsu Qinhuai Lantern Festival,2012'.It can provide early warning information and scientific basis for safety and security decision making.展开更多
In the process of large-scale,grid-connected wind power operations,it is important to establish an accurate probability distribution model for wind farm fluctuations.In this study,a wind power fluctuation modeling met...In the process of large-scale,grid-connected wind power operations,it is important to establish an accurate probability distribution model for wind farm fluctuations.In this study,a wind power fluctuation modeling method is proposed based on the method of moving average and adaptive nonparametric kernel density estimation(NPKDE)method.Firstly,the method of moving average is used to reduce the fluctuation of the sampling wind power component,and the probability characteristics of the modeling are then determined based on the NPKDE.Secondly,the model is improved adaptively,and is then solved by using constraint-order optimization.The simulation results show that this method has a better accuracy and applicability compared with the modeling method based on traditional parameter estimation,and solves the local adaptation problem of traditional NPKDE.展开更多
A new algorithm for linear instantaneous independent component analysis is proposed based on maximizing the log-likelihood contrast function which can be changed into a gradient equation.An iterative method is introdu...A new algorithm for linear instantaneous independent component analysis is proposed based on maximizing the log-likelihood contrast function which can be changed into a gradient equation.An iterative method is introduced to solve this equation efficiently.The unknown probability density functions as well as their first and second derivatives in the gradient equation are estimated by kernel density method.Computer simulations on artificially generated signals and gray scale natural scene images confirm the efficiency and accuracy of the proposed algorithm.展开更多
An improved method using kernel density estimation （KDE） and confidence level is presented for model validation with small samples. Decision making is a challenging problem because of input uncertainty and only smal...An improved method using kernel density estimation （KDE） and confidence level is presented for model validation with small samples. Decision making is a challenging problem because of input uncertainty and only small samples can be used due to the high costs of experimental measurements. However, model validation provides more confidence for decision makers when improving prediction accuracy at the same time. The confidence level method is introduced and the optimum sample variance is determined using a new method in kernel density estimation to increase the credibility of model validation. As a numerical example, the static frame model validation challenge problem presented by Sandia National Laboratories has been chosen. The optimum bandwidth is selected in kernel density estimation in order to build the probability model based on the calibration data. The model assessment is achieved using validation and accreditation experimental data respectively based on the probability model. Finally, the target structure prediction is performed using validated model, which are consistent with the results obtained by other researchers. The results demonstrate that the method using the improved confidence level and kernel density estimation is an effective approach to solve the model validation problem with small samples.展开更多
In this work,we develop an invertible transport map,called KRnet,for density estimation by coupling the Knothe–Rosenblatt(KR)rearrangement and the flow-based generative model,which generalizes the real-valued non-vol...In this work,we develop an invertible transport map,called KRnet,for density estimation by coupling the Knothe–Rosenblatt(KR)rearrangement and the flow-based generative model,which generalizes the real-valued non-volume preserving(real NVP)model(arX-iv:1605.08803v3).The triangular structure of the KR rearrangement breaks the symmetry of the real NVP in terms of the exchange of information between dimensions,which not only accelerates the training process but also improves the accuracy significantly.We have also introduced several new layers into the generative model to improve both robustness and effectiveness,including a reformulated affine coupling layer,a rotation layer and a component-wise nonlinear invertible layer.The KRnet can be used for both density estimation and sample generation especially when the dimensionality is relatively high.Numerical experiments have been presented to demonstrate the performance of KRnet.展开更多
Anomaly detection is an important method for intrusion detection.In recent years,unsupervised methods have been widely researched because they do not require labeling.For example,a nonlinear autoencoder can use recons...Anomaly detection is an important method for intrusion detection.In recent years,unsupervised methods have been widely researched because they do not require labeling.For example,a nonlinear autoencoder can use reconstruction errors to attain the discrimination threshold.This method is not effective when the model complexity is high or the data contains noise.The method for detecting the density of compressed features in a hidden layer can be used to reduce the influence of noise on the selection of the threshold because the density of abnormal data in hidden layers is smaller than normal data.However,compressed features may lose some of the high-dimensional distribution information of the original data.In this paper,we present an efficient anomaly detection framework for unsupervised anomaly detection,which includes network data capturing,processing,feature extraction,and anomaly detection.We employ a deep autoencoder to obtain compressed features and multi-layer reconstruction errors,and feeds them the same to the Gaussian mixture model to estimate the density.The proposed approach is trained and tested on multiple current intrusion detection datasets and real network scenes,and performance indicators,namely accuracy,recall,and F1-score,are better than other autoencoder models.展开更多
In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis ...In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis density filter algorithm based on marginalized particle and kernel density estimation is proposed, which utilizes the idea of marginalized particle filter to enhance the estimating performance of the PHD. The state variables are decomposed into linear and non-linear parts. The particle filter is adopted to predict and estimate the nonlinear states of multi-target after dimensionality reduction, while the Kalman filter is applied to estimate the linear parts under linear Gaussian condition. Embedding the information of the linear states into the estimated nonlinear states helps to reduce the estimating variance and improve the accuracy of target number estimation. The meanshift kernel density estimation, being of the inherent nature of searching peak value via an adaptive gradient ascent iteration, is introduced to cluster particles and extract target states, which is independent of the target number and can converge to the local peak position of the PHD distribution while avoiding the errors due to the inaccuracy in modeling and parameters estimation. Experiments show that the proposed algorithm can obtain higher tracking accuracy when using fewer sampling particles and is of lower computational complexity compared with the PF-PHD.展开更多
In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The pro...In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The proposed method is called CHK (KDE of Collage error and Hu moment) and it is tested on the Vistex texture database with 640 natural images. Experimental results show that the Average Retrieval Rate (ARR) can reach into 78.18%, which demonstrates that the proposed method performs better than the one with parameters respectively as well as the commonly used histogram method both on retrieval rate and retrieval time.展开更多
In Bayesian multi-target fltering,knowledge of measurement noise variance is very important.Signifcant mismatches in noise parameters will result in biased estimates.In this paper,a new particle flter for a probabilit...In Bayesian multi-target fltering,knowledge of measurement noise variance is very important.Signifcant mismatches in noise parameters will result in biased estimates.In this paper,a new particle flter for a probability hypothesis density（PHD）flter handling unknown measurement noise variances is proposed.The approach is based on marginalizing the unknown parameters out of the posterior distribution by using variational Bayesian（VB）methods.Moreover,the sequential Monte Carlo method is used to approximate the posterior intensity considering non-linear and non-Gaussian conditions.Unlike other particle flters for this challenging class of PHD flters,the proposed method can adaptively learn the unknown and time-varying noise variances while fltering.Simulation results show that the proposed method improves estimation accuracy in terms of both the number of targets and their states.展开更多
Crowd density estimation in wide areas is a challenging problem for visual surveillance. Because of the high risk of degeneration, the safety of public events involving large crowds has always been a major concern. In...Crowd density estimation in wide areas is a challenging problem for visual surveillance. Because of the high risk of degeneration, the safety of public events involving large crowds has always been a major concern. In this paper, we propose a video-based crowd density analysis and prediction system for wide-area surveillance applications. In monocular image sequences, the Accumulated Mosaic Image Difference (AMID) method is applied to extract crowd areas having irregular motion. The specific number of persons and velocity of a crowd can be adequately estimated by our system from the density of crowded areas. Using a multi-camera network, we can obtain predictions of a crowd's density several minutes in advance. The system has been used in real applications, and numerous experiments conducted in real scenes (station, park, plaza) demonstrate the effectiveness and robustness of the proposed method.展开更多
This study examines a new methodology to predict the final seismic mortality from earthquakes in China. Most studies established the association between mortality estimation and seismic intensity without considering t...This study examines a new methodology to predict the final seismic mortality from earthquakes in China. Most studies established the association between mortality estimation and seismic intensity without considering the population density. In China, however, the data are not always available, especially when it comes to the very urgent relief situation in the disaster. And the popu- lation density varies greatly from region to region. This motivates the development of empirical models that use historical death data to provide the path to analyze the death tolls for earthquakes. The present paper employs the average population density to predict the final death tolls in earthquakes using a case-based reasoning model from realistic perspective. To validate the forecasting results, historical data from 18 large-scale earthquakes occurred in China are used to estimate the seismic morality of each case. And a typical earthquake case occurred in the northwest of Sichuan Province is employed to demonstrate the estimation of final death toll. The strength of this paper is that it provides scientific methods with overall forecast errors lower than 20 %, and opens the door for conducting final death forecasts with a qualitative and quantitative approach. Limitations and future research are also analyzed and discussed in the conclusion.展开更多
Tanzania is considered a country with the largest number of African lions (Panthera leo). However, the continued absence of ecological population estimates and understanding of the associated factors influencing lion ...Tanzania is considered a country with the largest number of African lions (Panthera leo). However, the continued absence of ecological population estimates and understanding of the associated factors influencing lion distribution hinders the development of conservation planning. This is particularly true in the Ruaha-Rungwa landscape, where it was estimated that more than 10% of the global lion population currently resides. By using a call-back survey method, we aimed to provide population estimates (population size and density) of African lions in the Ruaha National Park, between wet (March 2019) and dry (October 2019) seasons. We also assessed the key factors that influenced the distribution of the observed lions towards call-back stations. Ferreira & Funston’s (2010) formula was used to calculate population size and in turn used to estimate density in the sampled area, while the Generalized Linear Model (GLMM) with zero-inflated Poisson error distribution was used to determine factors that influence the distribution of the observed lions to call-back stations. The population size we calculated for the sampled area of 3137.2 km<sup>2 </sup>revealed 286 lions (95% CI, 236 - 335) during the wet season, and 196 lions (95% CI, 192 - 200) during the dry season. The density of lions was 9.1/100 km<sup>2 </sup>during the wet season, and 6.3/100 km<sup>2</sup> during the dry season. Distance to water source had a significant negative effect on the distribution of the observed lions to the call-back stations, while habitat had a marginal effect. Our findings show that, although lion population estimates were larger during the wet season than the dry season, the season had no effect on the distribution of the observed lions to call-back stations. We suggest that the proximity to water sources is important in study design. Further, we suggest that density and population size are useful indices in identifying conservation area priorities and lion coexistence strategies.展开更多
基金supported by Division of Mathematical Sciences[grant number 1916467].
文摘Controlled experiments are widely used in many applications to investigate the causal relationship between input factors and experimental outcomes.A completely randomised design is usually used to randomly assign treatment levels to experimental units.When covariates of the experimental units are available,the experimental design should achieve covariate balancing among the treatment groups,such that the statistical inference of the treatment effects is not confounded with any possible effects of covariates.However,covariate imbalance often exists,because the experiment is carried out based on a single realisation of the complete randomisation.It is more likely to occur and worsen when the size of the experimental units is small or moderate.In this paper,we introduce a new covariate balancing criterion,which measures the differences between kernel density estimates of the covariates of treatment groups.To achieve covariate balance before the treatments are randomly assigned,we partition the experimental units by minimising the criterion,then randomly assign the treatment levels to the partitioned groups.Through numerical examples,weshow that the proposed partition approach can improve the accuracy of the difference-in-mean estimator and outperforms the complete randomisation and rerandomisation approaches.
文摘Let {Xn, n≥1} be a strictly stationary sequence of random variables, which are either associated or negatively associated, f(.) be their common density. In this paper, the author shows a central limit theorem for a kernel estimate of f(.) under certain regular conditions.
基金supported by Ongoing Research Funding Program(ORF-2025-488)King Saud University,Riyadh,Saudi Arabia.
文摘Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.
基金Supported by the National Natural Science Foundation of China(60603029)the Natural Science Foundation of Jiangsu Province(BK2007074)the Natural Science Foundation for Colleges and Universities in Jiangsu Province(06KJB520132)~~
文摘One-class support vector machine （OCSVM） and support vector data description （SVDD） are two main domain-based one-class （kernel） classifiers. To reveal their relationship with density estimation in the case of the Gaussian kernel, OCSVM and SVDD are firstly unified into the framework of kernel density estimation, and the essential relationship between them is explicitly revealed. Then the result proves that the density estimation induced by OCSVM or SVDD is in agreement with the true density. Meanwhile, it can also reduce the integrated squared error （ISE）. Finally, experiments on several simulated datasets verify the revealed relationships.
基金Supported by NNSFC(11401313)NSFJS(BK20161579)+2 种基金CPSF(2014M560368,2015T80475)2014 Qing Lan ProjectSupported by MEC Project PAI80160047,Conicyt,Chile
文摘In this paper we study a fractional stochastic heat equation on Rd （d 〉 1） with additive noise /t u（t, x） = Dα/δ u（t, x）＋ b（u（t, x） ） ＋ WH （t, x） where D α/δ is a nonlocal fractional differential operator and W H is a Gaussian-colored noise. We show the existence and the uniqueness of the mild solution for this equation. In addition, in the case of space dimension d = 1, we prove the existence of the density for this solution and we establish lower and upper Gaussian bounds for the density by Malliavin calculus.
基金Supported by the National Natural Science Foundation of China （No.60574047） and the Doctorate Foundation of the State Education Ministry of China （No.20050335018）.
文摘Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the two methods is that the components of PCA are still dependent while ICA has no orthogonality constraint and its latentvariables are independent. Process monitoring with PCA often supposes that process data or principal components is Gaussian distribution. However, this kind of constraint cannot be satisfied by several practical processes. To ex-tend the use of PCA, a nonparametric method is added to PCA to overcome the difficulty, and kernel density estimation （KDE） is rather a good choice. Though ICA is based on non-Gaussian distribution intormation, .KDE can help in the close monitoring of the data. Methods, such as PCA, ICA, PCA.with .KDE（KPCA）, and ICA with KDE,（KICA）, are demonstrated and. compared by applying them to a practical industnal Spheripol craft polypropylene catalyzer reactor instead of a laboratory emulator.
基金the Humanities and Social Science Fund of the Ministry of Education of China(21YJAZH077)。
文摘In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.
基金the financial support provided by the National Key Research and Development Program for Young Scientists(No.2021YFC2900400)Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(CPSF)(No.GZB20230914)+2 种基金National Natural Science Foundation of China(No.52304123)China Postdoctoral Science Foundation(No.2023M730412)Chongqing Outstanding Youth Science Foundation Program(No.CSTB2023NSCQ-JQX0027).
文摘Monitoring sensors in complex engineering environments often record abnormal data,leading to significant positioning errors.To reduce the influence of abnormal arrival times,we introduce an innovative,outlier-robust localization method that integrates kernel density estimation(KDE)with damping linear correction to enhance the precision of microseismic/acoustic emission(MS/AE)source positioning.Our approach systematically addresses abnormal arrival times through a three-step process:initial location by 4-arrival combinations,elimination of outliers based on three-dimensional KDE,and refinement using a linear correction with an adaptive damping factor.We validate our method through lead-breaking experiments,demonstrating over a 23%improvement in positioning accuracy with a maximum error of 9.12 mm(relative error of 15.80%)—outperforming 4 existing methods.Simulations under various system errors,outlier scales,and ratios substantiate our method’s superior performance.Field blasting experiments also confirm the practical applicability,with an average positioning error of 11.71 m(relative error of 7.59%),compared to 23.56,66.09,16.95,and 28.52 m for other methods.This research is significant as it enhances the robustness of MS/AE source localization when confronted with data anomalies.It also provides a practical solution for real-world engineering and safety monitoring applications.
基金The authors would like to thank the reviewers for their detailed reviews and constructive comments. We are also grateful for Sophie Song＇s help on the improving English. This work was supported in part by the ‘Fivetwelfh＇ National Science and Technology Support Program of the Ministry of Science and Technology of China （No. 2012BAH35B02）, the National Natural Science Foundation of China （NSFC） （No. 41401107, No. 41201402, and No. 41201417）.
文摘Crowd density is an important factor of crowd stability.Previous crowd density estimation methods are highly dependent on the specific video scene.This paper presented a video scene invariant crowd density estimation method using Geographic Information Systems(GIS) to monitor crowd size for large areas.The proposed method mapped crowd images to GIS.Then we can estimate crowd density for each camera in GIS using an estimation model obtained by one camera.Test results show that one model obtained by one camera in GIS can be adaptively applied to other cameras in outdoor video scenes.A real-time monitoring system for crowd size in large areas based on scene invariant model has been successfully used in 'Jiangsu Qinhuai Lantern Festival,2012'.It can provide early warning information and scientific basis for safety and security decision making.
基金supported by Science and Technology project of the State Grid Corporation of China“Research on Active Development Planning Technology and Comprehensive Benefit Analysis Method for Regional Smart Grid Comprehensive Demonstration Zone”National Natural Science Foundation of China(51607104)
文摘In the process of large-scale,grid-connected wind power operations,it is important to establish an accurate probability distribution model for wind farm fluctuations.In this study,a wind power fluctuation modeling method is proposed based on the method of moving average and adaptive nonparametric kernel density estimation(NPKDE)method.Firstly,the method of moving average is used to reduce the fluctuation of the sampling wind power component,and the probability characteristics of the modeling are then determined based on the NPKDE.Secondly,the model is improved adaptively,and is then solved by using constraint-order optimization.The simulation results show that this method has a better accuracy and applicability compared with the modeling method based on traditional parameter estimation,and solves the local adaptation problem of traditional NPKDE.
文摘A new algorithm for linear instantaneous independent component analysis is proposed based on maximizing the log-likelihood contrast function which can be changed into a gradient equation.An iterative method is introduced to solve this equation efficiently.The unknown probability density functions as well as their first and second derivatives in the gradient equation are estimated by kernel density method.Computer simulations on artificially generated signals and gray scale natural scene images confirm the efficiency and accuracy of the proposed algorithm.
基金Funding of Jiangsu Innovation Program for Graduate Education (CXZZ11_0193)NUAA Research Funding (NJ2010009)
文摘An improved method using kernel density estimation （KDE） and confidence level is presented for model validation with small samples. Decision making is a challenging problem because of input uncertainty and only small samples can be used due to the high costs of experimental measurements. However, model validation provides more confidence for decision makers when improving prediction accuracy at the same time. The confidence level method is introduced and the optimum sample variance is determined using a new method in kernel density estimation to increase the credibility of model validation. As a numerical example, the static frame model validation challenge problem presented by Sandia National Laboratories has been chosen. The optimum bandwidth is selected in kernel density estimation in order to build the probability model based on the calibration data. The model assessment is achieved using validation and accreditation experimental data respectively based on the probability model. Finally, the target structure prediction is performed using validated model, which are consistent with the results obtained by other researchers. The results demonstrate that the method using the improved confidence level and kernel density estimation is an effective approach to solve the model validation problem with small samples.
基金supported by the National Natural Science Foundation of Unite States (Grants DMS-1620026 and DMS-1913163)supported by the National Natural Science Foundation of China (Grant 11601329)
文摘In this work,we develop an invertible transport map,called KRnet,for density estimation by coupling the Knothe–Rosenblatt(KR)rearrangement and the flow-based generative model,which generalizes the real-valued non-volume preserving(real NVP)model(arX-iv:1605.08803v3).The triangular structure of the KR rearrangement breaks the symmetry of the real NVP in terms of the exchange of information between dimensions,which not only accelerates the training process but also improves the accuracy significantly.We have also introduced several new layers into the generative model to improve both robustness and effectiveness,including a reformulated affine coupling layer,a rotation layer and a component-wise nonlinear invertible layer.The KRnet can be used for both density estimation and sample generation especially when the dimensionality is relatively high.Numerical experiments have been presented to demonstrate the performance of KRnet.
基金This work is supported by the Introducing Program of Dongguan for Leading Talents in Innovation and Entrepreneur(Dongren Han[2018],No.738).
文摘Anomaly detection is an important method for intrusion detection.In recent years,unsupervised methods have been widely researched because they do not require labeling.For example,a nonlinear autoencoder can use reconstruction errors to attain the discrimination threshold.This method is not effective when the model complexity is high or the data contains noise.The method for detecting the density of compressed features in a hidden layer can be used to reduce the influence of noise on the selection of the threshold because the density of abnormal data in hidden layers is smaller than normal data.However,compressed features may lose some of the high-dimensional distribution information of the original data.In this paper,we present an efficient anomaly detection framework for unsupervised anomaly detection,which includes network data capturing,processing,feature extraction,and anomaly detection.We employ a deep autoencoder to obtain compressed features and multi-layer reconstruction errors,and feeds them the same to the Gaussian mixture model to estimate the density.The proposed approach is trained and tested on multiple current intrusion detection datasets and real network scenes,and performance indicators,namely accuracy,recall,and F1-score,are better than other autoencoder models.
基金Project(61101185) supported by the National Natural Science Foundation of ChinaProject(2011AA1221) supported by the National High Technology Research and Development Program of China
文摘In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis density filter algorithm based on marginalized particle and kernel density estimation is proposed, which utilizes the idea of marginalized particle filter to enhance the estimating performance of the PHD. The state variables are decomposed into linear and non-linear parts. The particle filter is adopted to predict and estimate the nonlinear states of multi-target after dimensionality reduction, while the Kalman filter is applied to estimate the linear parts under linear Gaussian condition. Embedding the information of the linear states into the estimated nonlinear states helps to reduce the estimating variance and improve the accuracy of target number estimation. The meanshift kernel density estimation, being of the inherent nature of searching peak value via an adaptive gradient ascent iteration, is introduced to cluster particles and extract target states, which is independent of the target number and can converge to the local peak position of the PHD distribution while avoiding the errors due to the inaccuracy in modeling and parameters estimation. Experiments show that the proposed algorithm can obtain higher tracking accuracy when using fewer sampling particles and is of lower computational complexity compared with the PF-PHD.
基金Supported by the Fundamental Research Funds for the Central Universities (No. NS2012093)
文摘In this paper, we propose a new method that combines collage error in fractal domain and Hu moment invariants for image retrieval with a statistical method - variable bandwidth Kernel Density Estimation (KDE). The proposed method is called CHK (KDE of Collage error and Hu moment) and it is tested on the Vistex texture database with 640 natural images. Experimental results show that the Average Retrieval Rate (ARR) can reach into 78.18%, which demonstrates that the proposed method performs better than the one with parameters respectively as well as the commonly used histogram method both on retrieval rate and retrieval time.
基金supported by National High-tech Research and Development Program of China (No.2011AA7014061)
文摘In Bayesian multi-target fltering,knowledge of measurement noise variance is very important.Signifcant mismatches in noise parameters will result in biased estimates.In this paper,a new particle flter for a probability hypothesis density（PHD）flter handling unknown measurement noise variances is proposed.The approach is based on marginalizing the unknown parameters out of the posterior distribution by using variational Bayesian（VB）methods.Moreover,the sequential Monte Carlo method is used to approximate the posterior intensity considering non-linear and non-Gaussian conditions.Unlike other particle flters for this challenging class of PHD flters,the proposed method can adaptively learn the unknown and time-varying noise variances while fltering.Simulation results show that the proposed method improves estimation accuracy in terms of both the number of targets and their states.
基金supported by the National Natural Science Foundation of China under Grant No. 61175007the National Key Technologies R&D Program under Grant No. 2012BAH07B01the National Key Basic Research Program of China (973 Program) under Grant No. 2012CB316302
文摘Crowd density estimation in wide areas is a challenging problem for visual surveillance. Because of the high risk of degeneration, the safety of public events involving large crowds has always been a major concern. In this paper, we propose a video-based crowd density analysis and prediction system for wide-area surveillance applications. In monocular image sequences, the Accumulated Mosaic Image Difference (AMID) method is applied to extract crowd areas having irregular motion. The specific number of persons and velocity of a crowd can be adequately estimated by our system from the density of crowded areas. Using a multi-camera network, we can obtain predictions of a crowd's density several minutes in advance. The system has been used in real applications, and numerous experiments conducted in real scenes (station, park, plaza) demonstrate the effectiveness and robustness of the proposed method.
基金funded by the National Natural Science Foundation of China (Nos.71271069,71540015,71532004)Foundation of Beijing University of Civil Engineering and Architecture (No.ZF15069)
文摘This study examines a new methodology to predict the final seismic mortality from earthquakes in China. Most studies established the association between mortality estimation and seismic intensity without considering the population density. In China, however, the data are not always available, especially when it comes to the very urgent relief situation in the disaster. And the popu- lation density varies greatly from region to region. This motivates the development of empirical models that use historical death data to provide the path to analyze the death tolls for earthquakes. The present paper employs the average population density to predict the final death tolls in earthquakes using a case-based reasoning model from realistic perspective. To validate the forecasting results, historical data from 18 large-scale earthquakes occurred in China are used to estimate the seismic morality of each case. And a typical earthquake case occurred in the northwest of Sichuan Province is employed to demonstrate the estimation of final death toll. The strength of this paper is that it provides scientific methods with overall forecast errors lower than 20 %, and opens the door for conducting final death forecasts with a qualitative and quantitative approach. Limitations and future research are also analyzed and discussed in the conclusion.
文摘Tanzania is considered a country with the largest number of African lions (Panthera leo). However, the continued absence of ecological population estimates and understanding of the associated factors influencing lion distribution hinders the development of conservation planning. This is particularly true in the Ruaha-Rungwa landscape, where it was estimated that more than 10% of the global lion population currently resides. By using a call-back survey method, we aimed to provide population estimates (population size and density) of African lions in the Ruaha National Park, between wet (March 2019) and dry (October 2019) seasons. We also assessed the key factors that influenced the distribution of the observed lions towards call-back stations. Ferreira & Funston’s (2010) formula was used to calculate population size and in turn used to estimate density in the sampled area, while the Generalized Linear Model (GLMM) with zero-inflated Poisson error distribution was used to determine factors that influence the distribution of the observed lions to call-back stations. The population size we calculated for the sampled area of 3137.2 km<sup>2 </sup>revealed 286 lions (95% CI, 236 - 335) during the wet season, and 196 lions (95% CI, 192 - 200) during the dry season. The density of lions was 9.1/100 km<sup>2 </sup>during the wet season, and 6.3/100 km<sup>2</sup> during the dry season. Distance to water source had a significant negative effect on the distribution of the observed lions to the call-back stations, while habitat had a marginal effect. Our findings show that, although lion population estimates were larger during the wet season than the dry season, the season had no effect on the distribution of the observed lions to call-back stations. We suggest that the proximity to water sources is important in study design. Further, we suggest that density and population size are useful indices in identifying conservation area priorities and lion coexistence strategies.
