A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec-...A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec- ond step, the discriminant-based methods or clustering-based methods are performed on the reformed distribution. It is focused on the typical clustering methods-Gaussian mixture model （GMM） and its variant to demonstrate the feasibility of the framework. Due to the independence of the first step in its second step, it can be integrated into the pixel-based and the histogram-based methods to improve their segmentation quality. The experiments on artificial and real images show that the framework can achieve effective and robust segmentation results.展开更多
Wireless sensor network(WSN)positioning has a good effect on indoor positioning,so it has received extensive attention in the field of positioning.Non-line-of sight(NLOS)is a primary challenge in indoor complex enviro...Wireless sensor network(WSN)positioning has a good effect on indoor positioning,so it has received extensive attention in the field of positioning.Non-line-of sight(NLOS)is a primary challenge in indoor complex environment.In this paper,a robust localization algorithm based on Gaussian mixture model and fitting polynomial is proposed to solve the problem of NLOS error.Firstly,fitting polynomials are used to predict the measured values.The residuals of predicted and measured values are clustered by Gaussian mixture model(GMM).The LOS probability and NLOS probability are calculated according to the clustering centers.The measured values are filtered by Kalman filter(KF),variable parameter unscented Kalman filter(VPUKF)and variable parameter particle filter(VPPF)in turn.The distance value processed by KF and VPUKF and the distance value processed by KF,VPUKF and VPPF are combined according to probability.Finally,the maximum likelihood method is used to calculate the position coordinate estimation.Through simulation comparison,the proposed algorithm has better positioning accuracy than several comparison algorithms in this paper.And it shows strong robustness in strong NLOS environment.展开更多
The timely and accurately detection of abnormal aircraft trajectory is critical to improving flight safety.However,the existing anomaly detection methods based on machine learning cannot well characterize the features...The timely and accurately detection of abnormal aircraft trajectory is critical to improving flight safety.However,the existing anomaly detection methods based on machine learning cannot well characterize the features of aircraft trajectories.Low anomaly detection accuracy still exists due to the high-dimensionality,heterogeneity and temporality of flight trajectory data.To this end,this paper proposes an abnormal trajectory detection method based on the deep mixture density network(DMDN)to detect flights with unusual data patterns and evaluate flight trajectory safety.The technique consists of two components:Utilization of the deep long short-term memory(LSTM)network to encode features of flight trajectories effectively,and parameterization of the statistical properties of flight trajectory using the Gaussian mixture model(GMM).Experiment results on Guangzhou Baiyun International Airport terminal airspace show that the proposed method can effectively capture the statistical patterns of aircraft trajectories.The model can detect abnormal flights with elevated risks and its performance is superior to two mainstream methods.The proposed model can be used as an assistant decision-making tool for air traffic controllers.展开更多
针对高斯混合模型在模型训练之前无法确定最佳采样点组合方式以及无法确定最佳分布元个数的问题,提出一种基于GMM-Boost的WLAN室内定位方法。首先,采用第二类斯特林数枚举采样点组合方式,比较不同组合方式下高斯混合模型平均定位准确度...针对高斯混合模型在模型训练之前无法确定最佳采样点组合方式以及无法确定最佳分布元个数的问题,提出一种基于GMM-Boost的WLAN室内定位方法。首先,采用第二类斯特林数枚举采样点组合方式,比较不同组合方式下高斯混合模型平均定位准确度,进而确定最佳采样点组合方式。其次,针对每一种样本标签数,采用贝叶斯信息准则(Bayesian Information Criterion,BIC)选择高斯混合模型最优分布元个数。最后,结合Adaboost算法对高斯混合模型进行定位准确度提升。分析结果表明,该算法在定位误差为2 m时定位准确度为71.2%,在小样本量情况下可以获得较低的平均定位误差。与其他算法相比,该算法具有较好的定位准确度和泛化能力。展开更多
A dynamic learning rate Gaussian mixture model（GMM）algorithm is proposed to deal with the problem of slow adaption of GMM in the case of moving object detection in the outdoor surveillance,especially in the presence...A dynamic learning rate Gaussian mixture model（GMM）algorithm is proposed to deal with the problem of slow adaption of GMM in the case of moving object detection in the outdoor surveillance,especially in the presence of sudden illumination changes.The GMM is mostly used for detecting objects in complex scenes for intelligent monitoring systems.To solve this problem,a mixture Gaussian model has been built for each pixel in the video frame,and according to the scene change from the frame difference,the learning rate of GMM can be dynamically adjusted.The experiments show that the proposed method gives good results with an adaptive GMM learning rate when we compare it with GMM method with a fixed learning rate.The method was tested on a certain dataset,and tests in the case of sudden natural light changes show that our method has a better accuracy and lower false alarm rate.展开更多
为提升身份验证系统的安全性,研究声纹识别技术在身份验证系统中的应用与优化。首先,提出一种基于声纹识别的身份验证系统框架。其次,针对声纹特征提取方法,重点研究基于梅尔频率倒谱系数(Mel Frequency Ceptral Coefficient,MFCC)的特...为提升身份验证系统的安全性,研究声纹识别技术在身份验证系统中的应用与优化。首先,提出一种基于声纹识别的身份验证系统框架。其次,针对声纹特征提取方法,重点研究基于梅尔频率倒谱系数(Mel Frequency Ceptral Coefficient,MFCC)的特征提取方法。再次,探讨基于贝叶斯估计的高斯混合模型(Gaussian Mixture Model,GMM)优化方法。最后,进行实验分析,评估识别率、准确率、召回率等性能指标,并与传统GMM方法进行比较。展开更多
基金Supported by the National Natural Science Foundation of China(60505004,60773061)~~
文摘A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec- ond step, the discriminant-based methods or clustering-based methods are performed on the reformed distribution. It is focused on the typical clustering methods-Gaussian mixture model （GMM） and its variant to demonstrate the feasibility of the framework. Due to the independence of the first step in its second step, it can be integrated into the pixel-based and the histogram-based methods to improve their segmentation quality. The experiments on artificial and real images show that the framework can achieve effective and robust segmentation results.
基金supported by the National Natural Science Foundation of China under Grant No.62273083 and No.61973069Natural Science Foundation of Hebei Province under Grant No.F2020501012。
文摘Wireless sensor network(WSN)positioning has a good effect on indoor positioning,so it has received extensive attention in the field of positioning.Non-line-of sight(NLOS)is a primary challenge in indoor complex environment.In this paper,a robust localization algorithm based on Gaussian mixture model and fitting polynomial is proposed to solve the problem of NLOS error.Firstly,fitting polynomials are used to predict the measured values.The residuals of predicted and measured values are clustered by Gaussian mixture model(GMM).The LOS probability and NLOS probability are calculated according to the clustering centers.The measured values are filtered by Kalman filter(KF),variable parameter unscented Kalman filter(VPUKF)and variable parameter particle filter(VPPF)in turn.The distance value processed by KF and VPUKF and the distance value processed by KF,VPUKF and VPPF are combined according to probability.Finally,the maximum likelihood method is used to calculate the position coordinate estimation.Through simulation comparison,the proposed algorithm has better positioning accuracy than several comparison algorithms in this paper.And it shows strong robustness in strong NLOS environment.
基金supported in part by the National Natural Science Foundation of China(Nos.62076126,52075031)Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.SJCX19_0013)。
文摘The timely and accurately detection of abnormal aircraft trajectory is critical to improving flight safety.However,the existing anomaly detection methods based on machine learning cannot well characterize the features of aircraft trajectories.Low anomaly detection accuracy still exists due to the high-dimensionality,heterogeneity and temporality of flight trajectory data.To this end,this paper proposes an abnormal trajectory detection method based on the deep mixture density network(DMDN)to detect flights with unusual data patterns and evaluate flight trajectory safety.The technique consists of two components:Utilization of the deep long short-term memory(LSTM)network to encode features of flight trajectories effectively,and parameterization of the statistical properties of flight trajectory using the Gaussian mixture model(GMM).Experiment results on Guangzhou Baiyun International Airport terminal airspace show that the proposed method can effectively capture the statistical patterns of aircraft trajectories.The model can detect abnormal flights with elevated risks and its performance is superior to two mainstream methods.The proposed model can be used as an assistant decision-making tool for air traffic controllers.
文摘针对高斯混合模型在模型训练之前无法确定最佳采样点组合方式以及无法确定最佳分布元个数的问题,提出一种基于GMM-Boost的WLAN室内定位方法。首先,采用第二类斯特林数枚举采样点组合方式,比较不同组合方式下高斯混合模型平均定位准确度,进而确定最佳采样点组合方式。其次,针对每一种样本标签数,采用贝叶斯信息准则(Bayesian Information Criterion,BIC)选择高斯混合模型最优分布元个数。最后,结合Adaboost算法对高斯混合模型进行定位准确度提升。分析结果表明,该算法在定位误差为2 m时定位准确度为71.2%,在小样本量情况下可以获得较低的平均定位误差。与其他算法相比,该算法具有较好的定位准确度和泛化能力。
文摘A dynamic learning rate Gaussian mixture model（GMM）algorithm is proposed to deal with the problem of slow adaption of GMM in the case of moving object detection in the outdoor surveillance,especially in the presence of sudden illumination changes.The GMM is mostly used for detecting objects in complex scenes for intelligent monitoring systems.To solve this problem,a mixture Gaussian model has been built for each pixel in the video frame,and according to the scene change from the frame difference,the learning rate of GMM can be dynamically adjusted.The experiments show that the proposed method gives good results with an adaptive GMM learning rate when we compare it with GMM method with a fixed learning rate.The method was tested on a certain dataset,and tests in the case of sudden natural light changes show that our method has a better accuracy and lower false alarm rate.
