The geological data are constructed in vector format in geographical information system (GIS) while other data such as remote sensing images, geographical data and geochemical data are saved in raster ones. This paper...The geological data are constructed in vector format in geographical information system (GIS) while other data such as remote sensing images, geographical data and geochemical data are saved in raster ones. This paper converts the vector data into 8 bit images according to their importance to mineralization each by programming. We can communicate the geological meaning with the raster images by this method. The paper also fuses geographical data and geochemical data with the programmed strata data. The result shows that image fusion can express different intensities effectively and visualize the structure characters in 2 dimensions. Furthermore, it also can produce optimized information from multi-source data and express them more directly.展开更多
This paper studies urban waterlog_draining decision support system based on the 4D data fusion technique.4D data includes DEM,DOQ,DLG and DRG.It supplies entire databases for waterlog forecast and analysis together wi...This paper studies urban waterlog_draining decision support system based on the 4D data fusion technique.4D data includes DEM,DOQ,DLG and DRG.It supplies entire databases for waterlog forecast and analysis together with non_spatial fundamental database.Data composition and reasoning are two key steps of 4D data fusion.Finally,this paper gives a real case: Ezhou Waterlog_Draining Decision Support System (EWDSS) with two application models,i.e.,DEM application model,water generating and draining model.展开更多
In this work, we developed a method to efficiently optimize the kernel function for combined data of various different sources with their corresponding kernels being already available. The vectorization of the combine...In this work, we developed a method to efficiently optimize the kernel function for combined data of various different sources with their corresponding kernels being already available. The vectorization of the combined data is achieved by a weighted concatenation of the existing data vectors. This induces a kernel matrix composed of the existing kernels as blocks along the main diagonal, weighted according to the corresponding the subspaces span by the data. The induced block kernel matrix is optimized in the platform of least-squares support vector machines simultaneously as the LS-SVM is being trained, by solving an extended set of linear equations, other than a quadratically constrained quadratic programming as in a previous method. The method is tested on a benchmark dataset, and the performance is significantly improved from the highest ROC score 0.84 using individual data source to ROC score 0.92 with data fusion.展开更多
To aim at the problem that the horizontal directivity index of the vector hy- drophone vertical array is not higher than that of a vector hydrophone, the high-resolution azimuth estimation algorithm based on the data ...To aim at the problem that the horizontal directivity index of the vector hy- drophone vertical array is not higher than that of a vector hydrophone, the high-resolution azimuth estimation algorithm based on the data fusion method was presented. The proposed algorithnl first employs MUSIC algorithm to estimate the azimuth of each divided sub-band signal, and then the estimated azimuths of multiple hydrophones are processed by using the data fusion technique. The high-resolution estimated result is achieved finally by adopting the weighted histogram statistics method. The results of the simulation and sea trials indicated that the proposed algorithm has better azimuth estimation performance than MUSIC algorithm of a single vector hydrophone and the data fusion technique based on the acoustic energy flux method. The better performance is reflected in the aspects of the estimation precision, the probability of correct estimation, the capability to distinguish multi-objects and the inhibition of the noise sub-bands.展开更多
支持矢量数据描述(Support vector data description,SVDD)是一种单值分类方法,可以解决故障诊断中故障样本缺乏的问题。矢双谱方法是基于全矢谱信息融合的双谱分析方法,能够有效融合旋转机械的双通道信息,更加全面、准确地反映信号中...支持矢量数据描述(Support vector data description,SVDD)是一种单值分类方法,可以解决故障诊断中故障样本缺乏的问题。矢双谱方法是基于全矢谱信息融合的双谱分析方法,能够有效融合旋转机械的双通道信息,更加全面、准确地反映信号中所包含的非线性故障特征信息。为实现在缺乏故障样本的情况下,对设备故障进行有效的智能诊断,提出一种矢双谱和SVDD相结合的智能故障诊断方法。采用矢双谱对双通道信号进行处理并提取特征矢量,作为SVDD的输入参数,建立起分类模型即可对机器运行状态进行分类。将该方法应用于齿轮箱的故障诊断中,结果表明可有效提取齿轮箱信号的特征信息,提高SVDD在故障诊断中的准确度。展开更多
文摘The geological data are constructed in vector format in geographical information system (GIS) while other data such as remote sensing images, geographical data and geochemical data are saved in raster ones. This paper converts the vector data into 8 bit images according to their importance to mineralization each by programming. We can communicate the geological meaning with the raster images by this method. The paper also fuses geographical data and geochemical data with the programmed strata data. The result shows that image fusion can express different intensities effectively and visualize the structure characters in 2 dimensions. Furthermore, it also can produce optimized information from multi-source data and express them more directly.
文摘This paper studies urban waterlog_draining decision support system based on the 4D data fusion technique.4D data includes DEM,DOQ,DLG and DRG.It supplies entire databases for waterlog forecast and analysis together with non_spatial fundamental database.Data composition and reasoning are two key steps of 4D data fusion.Finally,this paper gives a real case: Ezhou Waterlog_Draining Decision Support System (EWDSS) with two application models,i.e.,DEM application model,water generating and draining model.
文摘In this work, we developed a method to efficiently optimize the kernel function for combined data of various different sources with their corresponding kernels being already available. The vectorization of the combined data is achieved by a weighted concatenation of the existing data vectors. This induces a kernel matrix composed of the existing kernels as blocks along the main diagonal, weighted according to the corresponding the subspaces span by the data. The induced block kernel matrix is optimized in the platform of least-squares support vector machines simultaneously as the LS-SVM is being trained, by solving an extended set of linear equations, other than a quadratically constrained quadratic programming as in a previous method. The method is tested on a benchmark dataset, and the performance is significantly improved from the highest ROC score 0.84 using individual data source to ROC score 0.92 with data fusion.
基金the leaders of the State Key Laboratory of Acoustics Institute of Acoustics,Chinese Academy of Sciences,for their project support
文摘To aim at the problem that the horizontal directivity index of the vector hy- drophone vertical array is not higher than that of a vector hydrophone, the high-resolution azimuth estimation algorithm based on the data fusion method was presented. The proposed algorithnl first employs MUSIC algorithm to estimate the azimuth of each divided sub-band signal, and then the estimated azimuths of multiple hydrophones are processed by using the data fusion technique. The high-resolution estimated result is achieved finally by adopting the weighted histogram statistics method. The results of the simulation and sea trials indicated that the proposed algorithm has better azimuth estimation performance than MUSIC algorithm of a single vector hydrophone and the data fusion technique based on the acoustic energy flux method. The better performance is reflected in the aspects of the estimation precision, the probability of correct estimation, the capability to distinguish multi-objects and the inhibition of the noise sub-bands.
文摘支持矢量数据描述(Support vector data description,SVDD)是一种单值分类方法,可以解决故障诊断中故障样本缺乏的问题。矢双谱方法是基于全矢谱信息融合的双谱分析方法,能够有效融合旋转机械的双通道信息,更加全面、准确地反映信号中所包含的非线性故障特征信息。为实现在缺乏故障样本的情况下,对设备故障进行有效的智能诊断,提出一种矢双谱和SVDD相结合的智能故障诊断方法。采用矢双谱对双通道信号进行处理并提取特征矢量,作为SVDD的输入参数,建立起分类模型即可对机器运行状态进行分类。将该方法应用于齿轮箱的故障诊断中,结果表明可有效提取齿轮箱信号的特征信息,提高SVDD在故障诊断中的准确度。
