A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

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++.

An Enhanced Multiview Transformer for Population Density Estimation Using Cellular Mobility Data in Smart City

This paper addresses the problem of predicting population density leveraging cellular station data.As wireless communication devices are commonly used,cellular station data has become integral for estimating population figures and studying their movement,thereby implying significant contributions to urban planning.However,existing research grapples with issues pertinent to preprocessing base station data and the modeling of population prediction.To address this,we propose methodologies for preprocessing cellular station data to eliminate any irregular or redundant data.The preprocessing reveals a distinct cyclical characteristic and high-frequency variation in population shift.Further,we devise a multi-view enhancement model grounded on the Transformer(MVformer),targeting the improvement of the accuracy of extended time-series population predictions.Comparative experiments,conducted on the above-mentioned population dataset using four alternate Transformer-based models,indicate that our proposedMVformer model enhances prediction accuracy by approximately 30%for both univariate and multivariate time-series prediction assignments.The performance of this model in tasks pertaining to population prediction exhibits commendable results.

Probability distribution of wind power volatility based on the moving average method and improved nonparametric kernel density estimation

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.

Deep density estimation via invertible block-triangular mapping

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.

Improved Logistic Regression Algorithm Based on Kernel Density Estimation for Multi-Classification with Non-Equilibrium Samples

Logistic regression is often used to solve linear binary classification problems such as machine vision,speech recognition,and handwriting recognition.However,it usually fails to solve certain nonlinear multi-classification problem,such as problem with non-equilibrium samples.Many scholars have proposed some methods,such as neural network,least square support vector machine,AdaBoost meta-algorithm,etc.These methods essentially belong to machine learning categories.In this work,based on the probability theory and statistical principle,we propose an improved logistic regression algorithm based on kernel density estimation for solving nonlinear multi-classification.We have compared our approach with other methods using non-equilibrium samples,the results show that our approach guarantees sample integrity and achieves superior classification.

Diversity Sampling Based Kernel Density Estimation for Background Modeling

A novel diversity-sampling based nonparametric multi-modal background model is proposed. Using the samples having more popular and various intensity values in the training sequence, a nonparametric model is built for background subtraction. According to the related intensifies, different weights are given to the distinct samples in kernel density estimation. This avoids repeated computation using all samples, and makes computation more efficient in the evaluation phase. Experimental results show the validity of the diversity- sampling scheme and robustness of the proposed model in moving objects segmentation. The proposed algorithm can be used in outdoor surveillance systems.

Density Estimation Using Gumbel Kernel Estimator

In this article, our proposed kernel estimator, named as Gumbel kernel, which broadened the class of non-negative, asymmetric kernel density estimators. Such kernel estimator can be used in nonparametric estimation of the probability density function (pdf). When the density functions have limited bounded support on [0, ∞) and they are liberated of boundary bias, always non-negative and obtain the optimal rate of convergence for the mean integrated squared error (MISE). The bias, variance and the optimal bandwidth of the proposed estimators are investigated on theoretical grounds as well as on simulation basis. Further, the applicability of the proposed estimator is compared to Weibull kernel estimator, where performance of newly proposed kernel is outstanding.

Wavelet-Based Density Estimation in Presence of Additive Noise under Various Dependence Structures

We study the following model: . The aim is to estimate the distribution of X when only are observed. In the classical model, the distribution of is assumed to be known, and this is often considered as an important drawback of this simple model. Indeed, in most practical applications, the distribution of the errors cannot be perfectly known. In this paper, the author will construct wavelet estimators and analyze their asymptotic mean integrated squared error for additive noise models under certain dependent conditions, the strong mixing case, the β-mixing case and the ρ-mixing case. Under mild conditions on the family of wavelets, the estimator is shown to be -consistent and fast rates of convergence have been established.

Asymptotic normality of error density estimator in stationary and explosive autoregressive models

In this paper,we consider the limit distribution of the error density function estima-tor in the rst-order autoregressive models with negatively associated and positively associated random errors.Under mild regularity assumptions,some asymptotic normality results of the residual density estimator are obtained when the autoregressive models are stationary process and explosive process.In order to illustrate these results,some simulations such as con dence intervals and mean integrated square errors are provided in this paper.It shows that the residual density estimator can replace the density\estimator"which contains errors.

Wind speed model based on kernel density estimation and its application in reliability assessment of generating systems

An accurate probability distribution model of wind speed is critical to the assessment of reliability contribution of wind energy to power systems. Most of current models are built using the parametric density estimation(PDE) methods, which usually assume that the wind speed are subordinate to a certain known distribution(e.g. Weibull distribution and Normal distribution) and estimate the parameters of models with the historical data. This paper presents a kernel density estimation(KDE) method which is a nonparametric way to estimate the probability density function(PDF) of wind speed. The method is a kind of data-driven approach without making any assumption on the form of the underlying wind speed distribution, and capable of uncovering the statistical information hidden in the historical data. The proposed method is compared with three parametric models using wind data from six sites.The results indicate that the KDE outperforms the PDE in terms of accuracy and flexibility in describing the longterm wind speed distributions for all sites. A sensitivity analysis with respect to kernel functions is presented and Gauss kernel function is proved to be the best one. Case studies on a standard IEEE reliability test system(IEEERTS) have verified the applicability and effectiveness of the proposed model in evaluating the reliability performance of wind farms.

Development and application of traffic accident density estimation models using kernel density estimation

Traffic accident frequency has been decreasing in Japan in recent years. Nevertheless, many accidents still occur on residential roads. Area-wide traffic calming measures including Zone 30, which discourages traffic by setting a speed limit of 30 km/h in residential areas, have been implemented. However, no objective implementation method has been established. Development of a model for traffic accident density estimation explained by GIS data can enable the determination of dangerous areas objectively and easily, indicating where area-wide traffic calming can be implemented preferentially. This study examined the relations between traffic accidents and city characteristics, such as population, road factors, and spatial factors. A model was developed to estimate traffic accident density. Kernel density estimation （KDE） techniques were used to assess the relations efficiently. Besides, 16 models were developed by combining accident locations, accident types, and data types. By using them, the applicability of traffic accident density estimation models was examined. Results obtained using Spearman rank correlation show high coefficients between the predicted number and the actual number. The model can indicate the relative accident risk in cities. Results of this study can be used for objective determination of areas where area-wide traffic calming can be implemented preferentially, even if sufficient traffic accident data are not available.

Dm-KDE： dynamical kernel density estimation by sequences of KDE estimators with fixed number of components over data streams

In many data stream mining applications, traditional density estimation methods such as kemel density estimation, reduced set density estimation can not be applied to the density estimation of data streams because of their high computational burden, processing time and intensive memory allocation requirement. In order to reduce the time and space complexity, a novel density estimation method Dm-KDE over data streams based on the proposed algorithm m-KDE which can be used to design a KDE estimator with the fixed number of kernel components for a dataset is proposed. In this method, Dm-KDE sequence entries are created by algorithm m-KDE instead of all kemels obtained from other density estimation methods. In order to further reduce the storage space, Dm-KDE sequence entries can be merged by calculating their KL divergences. Finally, the probability density functions over arbitrary time or entire time can be estimated through the obtained estimation model. In contrast to the state-of-the-art algorithm SOMKE, the distinctive advantage of the proposed algorithm Dm-KDE exists in that it can achieve the same accuracy with much less fixed number of kernel components such that it is suitable for the scenarios where higher on-line computation about the kernel density estimation over data streams is required. We compare Dm-KDE with SOMKE and M-kernel in terms of density estimation accuracy and running time for various stationary datasets. We also apply Dm-KDE to evolving data streams. Experimental results illustrate the effectiveness of the pro- posed method.

Static Frame Model Validation with Small Samples Solution Using Improved Kernel Density Estimation and Confidence Level Method

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.

RCV-based error density estimation in the ultrahigh dimensional additive model

In this paper,we mainly study how to estimate the error density in the ultrahigh dimensional sparse additive model,where the number of variables is larger than the sample size.First,a smoothing method based on B-splines is applied to the estimation of regression functions.Second,an improved two-stage refitted crossvalidation(RCV)procedure by random splitting technique is used to obtain the residuals of the model,and then the residual-based kernel method is applied to estimate the error density function.Under suitable sparse conditions,the large sample properties of the estimator,including the weak and strong consistency,as well as normality and the law of the iterated logarithm,are obtained.Especially,the relationship between the sparsity and the convergence rate of the kernel density estimator is given.The methodology is illustrated by simulations and a real data example,which suggests that the proposed method performs well.

Fish Density Estimation with Multi-Scale Context Enhanced Convolutional Neural Network

With the development of fishery industry,accurate estimation of the number of fish in aquaculture waters is of great importance to fish behavior analysis,bait feeding and fishery resource investigation.In this paper,we propose a method for fish density estimation based on the multi-scale context enhanced convolutional network,which could map a fish school image taken at any angle to a density map,and calculate the number of fish in the image finally.In order to eliminate the influence of camera perspective effect and image resolution on density estimation,multi-scale filters are utilized in a convolutional neural network to process fish image in parallel.And then,the context enhancement module is merged in the network structure to help the network understand the global context information of the image.Finally,different feature maps are merged together to construct the density map of fish school images,and finally get the number of fish in the image.In order to make the effectiveness of our method valid,we test the proposed method on DlouDataset.The results show that the proposed method has lower mean square error and mean absolute error,which is helpful to improve the accuracy of the fish counting in dense fish school images.

Kernel Density Estimation Based Multiphase Fuzzy Region Competition Method for Texture Image Segmentation

In this paper,we propose a multiphase fuzzy region competition model for texture image segmentation.In the functional,each region is represented by a fuzzy membership function and a probability density function that is estimated by a nonparametric kernel density estimation.The overall algorithm is very efficient as both the fuzzy membership function and the probability density function can be implemented easily.We apply the proposed method to synthetic and natural texture images,and synthetic aperture radar images.Our experimental results have shown that the proposed method is competitive with the other state-of-the-art segmentation methods.

Volumetric magnetic resonance imaging classification for Alzheimer＇s disease based on kernel density estimation of local features

Background The classification of Alzheimer＇s disease （AD） from magnetic resonance imaging （MRI） has been challenged by lack of effective and reliable biomarkers due to inter-subject variability. This article presents a classification method for AD based on kernel density estimation （KDE） of local features. Methods First, a large number of local features were extracted from stable image blobs to represent various anatomical patterns for potential effective biomarkers. Based on distinctive descriptors and locations, the local features were robustly clustered to identify correspondences of the same underlying patterns. Then, the KDE was used to estimate distribution parameters of the correspondences by weighting contributions according to their distances. Thus, biomarkers could be reliably quantified by reducing the effects of further away correspondences which were more likely noises from inter-subject variability. Finally, the Bayes classifier was applied on the distribution parameters for the classification of AD. Results Experiments were performed on different divisions of a publicly available database to investigate the accuracy and the effects of age and AD severity. Our method achieved an equal error classification rate of 0.85 for subject aged 60-80 years exhibiting mild AD and outperformed a recent local feature-based work regardless of both effects. Conclusions We proposed a volumetric brain MRI classification method for neurodegenerative disease based on statistics of local features using KDE. The method may be potentially useful for the computer-aided diagnosis in clinical settings.

Bioinspired polarized light compass in moonlit sky for heading determination based on probability density estimation

Bioinspired polarized skylight navigation,which can be used in unfamiliar territories,is an important alternative autonomous navigation technique in the absence of Global Navigation Satellite System(GNSS).However,the polarization pattern in night environment with noise effects and model uncertainties is a less explored area.Although several decades have passed since the first publication about the polarization of the moonlit night sky,the usefulness of nocturnal polarization navigation is only sporadic in previous researches.This study demonstrates that the nocturnal polarized light is capable of providing accurate and stable navigation information in dim light outdoor environment.Based on the statistical characteristics of Angle of Polarization(Ao P)error,a probability density estimation method is proposed for heading determination.To illustrate the application potentials,the simulation and outdoor experiments are performed.Resultingly,the proposed method robustly models the distribution of Ao P error and gives accurate heading estimation evaluated by Standard Deviation(STD)which is 0.32°in a clear night sky and 0.47°in a cloudy night sky.

Robust Error Density Estimation in Ultrahigh Dimensional Sparse Linear Model

This paper focuses on error density estimation in ultrahigh dimensional sparse linear model,where the error term may have a heavy-tailed distribution.First,an improved two-stage refitted crossvalidation method combined with some robust variable screening procedures such as RRCS and variable selection methods such as LAD-SCAD is used to obtain the submodel,and then the residual-based kernel density method is applied to estimate the error density through LAD regression.Under given conditions,the large sample properties of the estimator are also established.Especially,we explicitly give the relationship between the sparsity and the convergence rate of the kernel density estimator.The simulation results show that the proposed error density estimator has a good performance.A real data example is presented to illustrate our methods.

Anisotropic density estimation for photon mapping

Photon mapping is a widely used technique for global illumination rendering. In the density estimation step of photon mapping, the indirect radiance at a shading point is estimated through a filtering process using nearby stored photons; an isotropic filtering kernel is usually used. However,using an isotropic kernel is not always the optimal choice, especially for cases when eye paths intersect with surfaces with anisotropic BRDFs. In this paper,we propose an anisotropic filtering kernel for density estimation to handle such anisotropic eye paths.The anisotropic filtering kernel is derived from the recently introduced anisotropic spherical Gaussian representation of BRDFs. Compared to conventional photon mapping, our method is able to reduce rendering errors with negligible additional cost when rendering scenes containing anisotropic BRDFs.