Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors.In the past,in the rocky desertification areas,supervised classification and uns...Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors.In the past,in the rocky desertification areas,supervised classification and unsupervised classification are often used to classify the remote sensing image.But they only use pixel brightness characteristics to classify it.So the classification accuracy is low and can not meet the needs of practical application.Decision tree classification is a new technology for remote sensing image classification.In this study,we select the rocky desertification areas Kaizuo Township as a case study,use the ASTER image data,DEM and lithology data,by extracting the normalized difference vegetation index,ratio vegetation index,terrain slope and other data to establish classification rules to build decision trees.In the ENVI software support,we access the classification images.By calculating the classification accuracy and kappa coefficient,we find that better classification results can be obtained,desertification information can be extracted automatically and if more remote sensing image bands used,higher resolution DEM employed and less errors data reduced during processing,classification accuracy can be improve further.展开更多
Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the im...Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the image. An improved FCM algorithm is proposed to improve the antinoise performance of FCM algorithm. The new algorithm is formulated by incorporating the spatial neighborhood information into the membership function for clustering. The distribution statistics of the neighborhood pixels and the prior probability are used to form a new membership func- tion. It is not only effective to remove the noise spots but also can reduce the misclassified pixels. Experimental results indicate that the proposed algorithm is more accurate and robust to noise than the standard FCM algorithm.展开更多
If the constraint boundary relates to a bifurcation parameter, a bifurcation is said to be parametrically constrained. Relying upon some substitution, a parametrically constrained bifurcation is transformed to an unco...If the constraint boundary relates to a bifurcation parameter, a bifurcation is said to be parametrically constrained. Relying upon some substitution, a parametrically constrained bifurcation is transformed to an unconstrained bifurcation about new variables. A general form of transition sets of the parametrically constrained bifurcation is derived. The result indicates that only the constrained bifurcation set is influenced by parametric constraints, while other transition sets are the same as those of the corresponding nonparametrically constrained bifurcation. Taking parametrically constrained pitchfork bifurcation problems as examples, effects of parametric constraints on bifurcation classification are discussed.展开更多
A wide range of techniques has been developed to image biological samples at high spatial and temporal resolution.In this paper,we report recent results from deep-UV confocal fAuorescence microscopy to image inherent ...A wide range of techniques has been developed to image biological samples at high spatial and temporal resolution.In this paper,we report recent results from deep-UV confocal fAuorescence microscopy to image inherent emission from fuorophores such as tryptophan,and structured ilumination microscopy(SIM)of biological materials.One motivation for developing deep-UV fhuorescence imaging and SIM is to provide methods to complement our measurements in the emerging field of X-ray coherent diffractive imaging.展开更多
Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be di...Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be difficult. This paper investigates Neyman- Pearson classification with convex loss function in the arbitrary class of real measurable functions. A general condition is given under which Neyman-Pearson classification with convex loss function has the same classifier as that with indicator loss function. We give analysis to NP-ERM with convex loss function and prove it＇s performance guarantees. An example of complexity penalty pair about convex loss function risk in terms of Rademacher averages is studied, which produces a tight PAC bound of the NP-ERM with convex loss function.展开更多
To attain the volumetric information of the optic radiation in normal human brains, we per- formed diffusion tensor imaging examination in 13 healthy volunteers. Simultaneously, we used a brain normalization method to...To attain the volumetric information of the optic radiation in normal human brains, we per- formed diffusion tensor imaging examination in 13 healthy volunteers. Simultaneously, we used a brain normalization method to reduce individual brain variation and increase the accuracy of volumetric information analysis. In addition, tractography-based group mapping method was also used to investigate the probability and distribution of the optic radiation pathways. Our results showed that the measured optic radiation fiber tract volume was a range of about 0.16% and that the fractional anisotropy value was about 0.53. Moreover, the optic radiation probability fiber pathway that was determined with diffusion tensor tractography-based group mapping was able to detect the location relatively accurately. We believe that our methods and results are help- ful in the study of optic radiation fiber tract information.展开更多
文摘Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors.In the past,in the rocky desertification areas,supervised classification and unsupervised classification are often used to classify the remote sensing image.But they only use pixel brightness characteristics to classify it.So the classification accuracy is low and can not meet the needs of practical application.Decision tree classification is a new technology for remote sensing image classification.In this study,we select the rocky desertification areas Kaizuo Township as a case study,use the ASTER image data,DEM and lithology data,by extracting the normalized difference vegetation index,ratio vegetation index,terrain slope and other data to establish classification rules to build decision trees.In the ENVI software support,we access the classification images.By calculating the classification accuracy and kappa coefficient,we find that better classification results can be obtained,desertification information can be extracted automatically and if more remote sensing image bands used,higher resolution DEM employed and less errors data reduced during processing,classification accuracy can be improve further.
基金supported by the National Natural Science Foundation of China(6087403160740430664)
文摘Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the image. An improved FCM algorithm is proposed to improve the antinoise performance of FCM algorithm. The new algorithm is formulated by incorporating the spatial neighborhood information into the membership function for clustering. The distribution statistics of the neighborhood pixels and the prior probability are used to form a new membership func- tion. It is not only effective to remove the noise spots but also can reduce the misclassified pixels. Experimental results indicate that the proposed algorithm is more accurate and robust to noise than the standard FCM algorithm.
基金Project supported by the National Natural Science Foundation of China (Nos. 10872142 and10632040)the New Century Excellent Talents Plan of the Ministry of Education of China(No. NCET-05-0247)the Key Project of Tianjin (No. 09JCZDJC26800)
文摘If the constraint boundary relates to a bifurcation parameter, a bifurcation is said to be parametrically constrained. Relying upon some substitution, a parametrically constrained bifurcation is transformed to an unconstrained bifurcation about new variables. A general form of transition sets of the parametrically constrained bifurcation is derived. The result indicates that only the constrained bifurcation set is influenced by parametric constraints, while other transition sets are the same as those of the corresponding nonparametrically constrained bifurcation. Taking parametrically constrained pitchfork bifurcation problems as examples, effects of parametric constraints on bifurcation classification are discussed.
基金We acknowledge the support of the Australian Research Council for the Center of Excellence for Coherent X-ray Science(CE0561787).
文摘A wide range of techniques has been developed to image biological samples at high spatial and temporal resolution.In this paper,we report recent results from deep-UV confocal fAuorescence microscopy to image inherent emission from fuorophores such as tryptophan,and structured ilumination microscopy(SIM)of biological materials.One motivation for developing deep-UV fhuorescence imaging and SIM is to provide methods to complement our measurements in the emerging field of X-ray coherent diffractive imaging.
基金This is a Plenary Report on the International Symposium on Approximation Theory and Remote SensingApplications held in Kunming, China in April 2006Supported in part by NSF of China under grants 10571010 , 10171007 and Startup Grant for Doctoral Researchof Beijing University of Technology
文摘Neyman-Pearson classification has been studied in several articles before. But they all proceeded in the classes of indicator functions with indicator function as the loss function, which make the calculation to be difficult. This paper investigates Neyman- Pearson classification with convex loss function in the arbitrary class of real measurable functions. A general condition is given under which Neyman-Pearson classification with convex loss function has the same classifier as that with indicator loss function. We give analysis to NP-ERM with convex loss function and prove it＇s performance guarantees. An example of complexity penalty pair about convex loss function risk in terms of Rademacher averages is studied, which produces a tight PAC bound of the NP-ERM with convex loss function.
文摘To attain the volumetric information of the optic radiation in normal human brains, we per- formed diffusion tensor imaging examination in 13 healthy volunteers. Simultaneously, we used a brain normalization method to reduce individual brain variation and increase the accuracy of volumetric information analysis. In addition, tractography-based group mapping method was also used to investigate the probability and distribution of the optic radiation pathways. Our results showed that the measured optic radiation fiber tract volume was a range of about 0.16% and that the fractional anisotropy value was about 0.53. Moreover, the optic radiation probability fiber pathway that was determined with diffusion tensor tractography-based group mapping was able to detect the location relatively accurately. We believe that our methods and results are help- ful in the study of optic radiation fiber tract information.
