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
To solve the problem of color distortion after dehazing in the sky region by using the classical dark channel prior method to process the hazy images with large regions of sky,an improved dark channel image dehazing m...To solve the problem of color distortion after dehazing in the sky region by using the classical dark channel prior method to process the hazy images with large regions of sky,an improved dark channel image dehazing method based on Gaussian mixture model is proposed.Firstly,we use the Gaussian mixture model to model the hazy image,and then use the expectation maximization(EM)algorithm to optimize the parameters,so that the hazy image can be divided into the sky region and the non-sky region.Secondly,the sky region is divided into a light haze region,a medium haze region and a heavy haze region according to the different dark channel values to estimate the transmission respectively.Thirdly,the restored image is obtained by combining the atmospheric scattering model.Finally,adaptive local tone mapping for high dynamic range images is used to adjust the brightness of the restored image.The experimental results show that the proposed method can effectively eliminate the color distortion in the sky region,and the restored image is clearer and has better visual effect.展开更多
It has long been thought that bioprocess, with their inherent measurement difficulties and complex dynamics, posed almost insurmountable problems to engineers. A novel software sensor is proposed to make more effectiv...It has long been thought that bioprocess, with their inherent measurement difficulties and complex dynamics, posed almost insurmountable problems to engineers. A novel software sensor is proposed to make more effective use of those meas- urements that are already available, which enable improvement in fermentation process control. The proposed method is based on mixtures of Gaussian processes (GP) with expectation maximization (EM) algorithm employed for parameter estimation of mixture of models. The mixture model can alleviate computational complexity of GP and also accord with changes of operating condition in fermentation processes, i.e., it would certainly be able to examine what types of process-knowledge would be most relevant for local models’ specific operating points of the process and then combine them into a global one. Demonstrated by on-line estimate of yeast concentration in fermentation industry as an example, it is shown that soft sensor based state estimation is a powerful technique for both enhancing automatic control performance of biological systems and implementing on-line moni- toring and optimization.展开更多
Using a homogenized daily maximum temperature(T_(max))dataset across China,this study characterized the spatiotemporal variation of the onset date of extreme hot days in a year(i.e.,FirstEHD)during 1960-2018.Inhomogen...Using a homogenized daily maximum temperature(T_(max))dataset across China,this study characterized the spatiotemporal variation of the onset date of extreme hot days in a year(i.e.,FirstEHD)during 1960-2018.Inhomogeneous trends of FirstEHD over China during 1960-2018 can be found,with the advanced trend of FirstEHD over most parts in China,while a number of stations in North-Central China(NC)show the delayed trend of FirstEHD.Moreover,there exist interdecadal changes of FirstEHD trend,with a remarkable difference in the trend magnitude before and after the 1990s over South China(SC),and the sign of trend can even reverse from negative to positive after the 1990s in Xinjiang(XJ)and Yangtze River Basin(YR),and from positive to negative in NC.The overall trends of FirstEHD over NC,YR,and XJ during 1960-2018 are dominated by the trends before the 1990s,while they are dominated by the sharp advance after the 1990s over SC.It is further found that the trend of FirstEHD can generally be explained by the long-term trend in T_(max) over most parts of China,but the contribution from T_(max) variabilities is also non-negligible and can even account for more than 75% of the overall trend over NC.The possible factors responsible for the decadal changes in FirstEHD trends are also discussed.展开更多
This paper presents a new online incremental training algorithm of Gaussian mixture model （GMM）, which aims to perform the expectation-maximization（EM） training incrementally to update GMM model parameters online ...This paper presents a new online incremental training algorithm of Gaussian mixture model （GMM）, which aims to perform the expectation-maximization（EM） training incrementally to update GMM model parameters online sample by sample, instead of waiting for a block of data with the sufficient size to start training as in the traditional EM procedure. The proposed method is extended from the split-and-merge EM procedure, so inherently it is also capable escaping from local maxima and reducing the chances of singularities. In the application domain, the algorithm is optimized in the context of speech processing applications. Experiments on the synthetic data show the advantage and efficiency of the new method and the results in a speech processing task also confirm the improvement of system performance.展开更多
Plant utilization is poorly known in South China as compared to North China.Fanchengdui, Zhuweicheng, Shinianshan, and Yinjiaping, which date back to 5-4 ka BP, are typical Neolithic sites located at the middle reache...Plant utilization is poorly known in South China as compared to North China.Fanchengdui, Zhuweicheng, Shinianshan, and Yinjiaping, which date back to 5-4 ka BP, are typical Neolithic sites located at the middle reaches of the Ganjiang River in Jiangxi Province.Due to the lack of systematic plant archaeological work, only rice straw and husk residues have been found in some archaeological sites in Jiangxi Province.Thirteen stone tools excavated from these sites were examined in this study.The results showed that among the plants utilized are Coix spp., Oryza spp., Vigna spp., plants from the tribe Triticeae, roots from some plants of Zingiberaceae, and other species of roots and tubers.More than 457 grains were retrieved from the 13 stone tools.The fact that Coix spp.were found in all stone tools suggests that these species were a major food source during the Neolithic era.In addition, 28 starch grains of Oryza spp.were found in 8 stone tools.The analysis also revealed that not only seeds of Gramineae but also those of Leguminosae, Zingiberaceae and other species of roots and tubers are among the plants utilized in the four Fanchengdui culture sites.These results indicate that ancient plant utilization was rather diverse, and this study elucidates the prehistoric agricultural systems of South China.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National Natural Science Foundation of China(Nos.61841303,61963023)Project of Humanities and Social Sciences of Ministry of Education in China(No.19YJC760012)。
文摘To solve the problem of color distortion after dehazing in the sky region by using the classical dark channel prior method to process the hazy images with large regions of sky,an improved dark channel image dehazing method based on Gaussian mixture model is proposed.Firstly,we use the Gaussian mixture model to model the hazy image,and then use the expectation maximization(EM)algorithm to optimize the parameters,so that the hazy image can be divided into the sky region and the non-sky region.Secondly,the sky region is divided into a light haze region,a medium haze region and a heavy haze region according to the different dark channel values to estimate the transmission respectively.Thirdly,the restored image is obtained by combining the atmospheric scattering model.Finally,adaptive local tone mapping for high dynamic range images is used to adjust the brightness of the restored image.The experimental results show that the proposed method can effectively eliminate the color distortion in the sky region,and the restored image is clearer and has better visual effect.
基金Project (No. 2002AA412010) supported by the National High-TechResearch and Development Program (863) of China
文摘It has long been thought that bioprocess, with their inherent measurement difficulties and complex dynamics, posed almost insurmountable problems to engineers. A novel software sensor is proposed to make more effective use of those meas- urements that are already available, which enable improvement in fermentation process control. The proposed method is based on mixtures of Gaussian processes (GP) with expectation maximization (EM) algorithm employed for parameter estimation of mixture of models. The mixture model can alleviate computational complexity of GP and also accord with changes of operating condition in fermentation processes, i.e., it would certainly be able to examine what types of process-knowledge would be most relevant for local models’ specific operating points of the process and then combine them into a global one. Demonstrated by on-line estimate of yeast concentration in fermentation industry as an example, it is shown that soft sensor based state estimation is a powerful technique for both enhancing automatic control performance of biological systems and implementing on-line moni- toring and optimization.
基金funded by the National Key Research and De-velopment Program of China[Grant number 2017YFA0604304]the National Natural Science Foundation of China[Grant number 41661144032].
文摘Using a homogenized daily maximum temperature(T_(max))dataset across China,this study characterized the spatiotemporal variation of the onset date of extreme hot days in a year(i.e.,FirstEHD)during 1960-2018.Inhomogeneous trends of FirstEHD over China during 1960-2018 can be found,with the advanced trend of FirstEHD over most parts in China,while a number of stations in North-Central China(NC)show the delayed trend of FirstEHD.Moreover,there exist interdecadal changes of FirstEHD trend,with a remarkable difference in the trend magnitude before and after the 1990s over South China(SC),and the sign of trend can even reverse from negative to positive after the 1990s in Xinjiang(XJ)and Yangtze River Basin(YR),and from positive to negative in NC.The overall trends of FirstEHD over NC,YR,and XJ during 1960-2018 are dominated by the trends before the 1990s,while they are dominated by the sharp advance after the 1990s over SC.It is further found that the trend of FirstEHD can generally be explained by the long-term trend in T_(max) over most parts of China,but the contribution from T_(max) variabilities is also non-negligible and can even account for more than 75% of the overall trend over NC.The possible factors responsible for the decadal changes in FirstEHD trends are also discussed.
文摘This paper presents a new online incremental training algorithm of Gaussian mixture model （GMM）, which aims to perform the expectation-maximization（EM） training incrementally to update GMM model parameters online sample by sample, instead of waiting for a block of data with the sufficient size to start training as in the traditional EM procedure. The proposed method is extended from the split-and-merge EM procedure, so inherently it is also capable escaping from local maxima and reducing the chances of singularities. In the application domain, the algorithm is optimized in the context of speech processing applications. Experiments on the synthetic data show the advantage and efficiency of the new method and the results in a speech processing task also confirm the improvement of system performance.
基金supported by National Natural Science Foundation of China(Grant No.41072140)National Plan for Global Change Research(Grant No.2010CB950101)Strategic Priority Research Program of the Chinese Academy of Sciences(Grant Nos.XDA05130603,XDA05130402 and XDA05080100)
文摘Plant utilization is poorly known in South China as compared to North China.Fanchengdui, Zhuweicheng, Shinianshan, and Yinjiaping, which date back to 5-4 ka BP, are typical Neolithic sites located at the middle reaches of the Ganjiang River in Jiangxi Province.Due to the lack of systematic plant archaeological work, only rice straw and husk residues have been found in some archaeological sites in Jiangxi Province.Thirteen stone tools excavated from these sites were examined in this study.The results showed that among the plants utilized are Coix spp., Oryza spp., Vigna spp., plants from the tribe Triticeae, roots from some plants of Zingiberaceae, and other species of roots and tubers.More than 457 grains were retrieved from the 13 stone tools.The fact that Coix spp.were found in all stone tools suggests that these species were a major food source during the Neolithic era.In addition, 28 starch grains of Oryza spp.were found in 8 stone tools.The analysis also revealed that not only seeds of Gramineae but also those of Leguminosae, Zingiberaceae and other species of roots and tubers are among the plants utilized in the four Fanchengdui culture sites.These results indicate that ancient plant utilization was rather diverse, and this study elucidates the prehistoric agricultural systems of South China.
