In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradien...In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradient, the length of the neutral line, and the number of singular points are extracted from SOHO/MDI longitudinal magnetograms as measures. Based on these pa- rameters, the sliding-window method is used to form the sequential data by adding three days evolutionary information. Con- sidering the imbalanced problem in dataset, the K-means clustering, as an unsupervised clustering algorithm, is used to convert imbalanced data to balanced ones. Finally, the learning vector quantity is employed to predict the flares level within 48 hours. Experimental results indicate that the performance of the proposed flare forecasting model with sequential data is improved.展开更多
目的:探讨四维自动左室定量分析技术(4D AUTO LVQ)评价正常人左心室容积及功能的可行性及重复性。方法:在单心动周期(SB,single heart beat)及多心动周期(MB,multi-heartbeat)成像模式下分别采集20例正常志愿者左室三维图像(3-dimension...目的:探讨四维自动左室定量分析技术(4D AUTO LVQ)评价正常人左心室容积及功能的可行性及重复性。方法:在单心动周期(SB,single heart beat)及多心动周期(MB,multi-heartbeat)成像模式下分别采集20例正常志愿者左室三维图像(3-dimensional echocardiography),并分别使用4DAUTO LVQ技术测量左室舒张末容积(LVEDV)、左室收缩末容积(LVESV)及射血分数(EF),同时使用二维双平面Simpson's法及M型Teich-holtz法检测同一组志愿者LVEDV、LVESV和EF。将4种方法所得的测值分别进行比较。结果:①M型测量的LVEDV测值与其他3种方法测值间差异有统计学意义(P<0.05),SB模式及MB模式下4D ATUO LVQ测量的LVEDV相关系数r为0.769;②SB、MB模式下4D ATUO LVQ方法测量的LVESV、双平面Simpson's法测量的LVESV测值与M型测值间差异均有统计学意义(P<0.05),SB与MB模式下测量的LVESV相关系数r为0.86;③SB、MB模式下测量的EF值与双平面Simpson's法及M型测值间差异均有统计学意义(P<0.05),SB与MB模式下测量的EF值相关系数r为0.428;Bland-Altman一致性分析表明4D AUTO LVQ在SB与MB模式下所测容积及EF值具有较高一致性。④SB模式下的3DE图像存储时间短于MB模式图像存储时间,差异有统计学意义(P<0.05);4D AUTO LVQ及Simpson's法后处理时间差异均无统计学意义(P>0.05)。⑤SB与MB模式下4D AUTO LVQ测量LVEF观察者内变异系数分别为8.50%、6.50%,观察者间变异系数分别为7.75%、6.50%。结论:4D AUTO LVQ技术定量分析左室容积及EF有效、可行、快捷,具有临床应用价值。展开更多
提出了一种基于自组织特征映射神经网络的局部矢量量化算法(Local vector quantization algorithm based on Self-O rgan i-zing Feature M app ing neural networks,LSOFM),LSOFM算法是对SOFM算法的一种改进,它将隶属关系引入到参考点...提出了一种基于自组织特征映射神经网络的局部矢量量化算法(Local vector quantization algorithm based on Self-O rgan i-zing Feature M app ing neural networks,LSOFM),LSOFM算法是对SOFM算法的一种改进,它将隶属关系引入到参考点权值的修改中,自组织特征映射神经网络的领域大小的确定依赖于训练矢量与参考点之间的隶属关系。展开更多
Converting between “fuzzy concept” and “numerical value” in computer aided assessment is rather difficult in many applications. This paper presents a LVQ neural network paradigm for sensory evaluation. This intell...Converting between “fuzzy concept” and “numerical value” in computer aided assessment is rather difficult in many applications. This paper presents a LVQ neural network paradigm for sensory evaluation. This intelligent approach utilizes predefined class information for supervised learning in order to solve the converting problem and keep the fuzziness and imprecision of the whole sensory information. The method is validated by the experiment on stimulation evaluation of cigarette sensory.展开更多
基金supported by the National Natural Science Foundation of China (Grant No. 10973020)the Funding Project for Academic Human Resources Development in Institutions of Higher Learning under the Jurisdiction of Beijing Municipality (Grant No. PHR200906210)+1 种基金the Funding Project for Base Construction of Scientific Research of Beijing Municipal Commission of Education (Grant No. WYJD200902)Beijing Philosophy and Social Science Planning Project (Grant No. 09BaJG258)
文摘In this paper, a combined method of unsupervised clustering and learning vector quantity (LVQ) is presented to forecast the occurrence of solar flare. Three magnetic parameters including the maximum horizontal gradient, the length of the neutral line, and the number of singular points are extracted from SOHO/MDI longitudinal magnetograms as measures. Based on these pa- rameters, the sliding-window method is used to form the sequential data by adding three days evolutionary information. Con- sidering the imbalanced problem in dataset, the K-means clustering, as an unsupervised clustering algorithm, is used to convert imbalanced data to balanced ones. Finally, the learning vector quantity is employed to predict the flares level within 48 hours. Experimental results indicate that the performance of the proposed flare forecasting model with sequential data is improved.
文摘目的:探讨四维自动左室定量分析技术(4D AUTO LVQ)评价正常人左心室容积及功能的可行性及重复性。方法:在单心动周期(SB,single heart beat)及多心动周期(MB,multi-heartbeat)成像模式下分别采集20例正常志愿者左室三维图像(3-dimensional echocardiography),并分别使用4DAUTO LVQ技术测量左室舒张末容积(LVEDV)、左室收缩末容积(LVESV)及射血分数(EF),同时使用二维双平面Simpson's法及M型Teich-holtz法检测同一组志愿者LVEDV、LVESV和EF。将4种方法所得的测值分别进行比较。结果:①M型测量的LVEDV测值与其他3种方法测值间差异有统计学意义(P<0.05),SB模式及MB模式下4D ATUO LVQ测量的LVEDV相关系数r为0.769;②SB、MB模式下4D ATUO LVQ方法测量的LVESV、双平面Simpson's法测量的LVESV测值与M型测值间差异均有统计学意义(P<0.05),SB与MB模式下测量的LVESV相关系数r为0.86;③SB、MB模式下测量的EF值与双平面Simpson's法及M型测值间差异均有统计学意义(P<0.05),SB与MB模式下测量的EF值相关系数r为0.428;Bland-Altman一致性分析表明4D AUTO LVQ在SB与MB模式下所测容积及EF值具有较高一致性。④SB模式下的3DE图像存储时间短于MB模式图像存储时间,差异有统计学意义(P<0.05);4D AUTO LVQ及Simpson's法后处理时间差异均无统计学意义(P>0.05)。⑤SB与MB模式下4D AUTO LVQ测量LVEF观察者内变异系数分别为8.50%、6.50%,观察者间变异系数分别为7.75%、6.50%。结论:4D AUTO LVQ技术定量分析左室容积及EF有效、可行、快捷,具有临床应用价值。
文摘提出了一种基于自组织特征映射神经网络的局部矢量量化算法(Local vector quantization algorithm based on Self-O rgan i-zing Feature M app ing neural networks,LSOFM),LSOFM算法是对SOFM算法的一种改进,它将隶属关系引入到参考点权值的修改中,自组织特征映射神经网络的领域大小的确定依赖于训练矢量与参考点之间的隶属关系。
文摘Converting between “fuzzy concept” and “numerical value” in computer aided assessment is rather difficult in many applications. This paper presents a LVQ neural network paradigm for sensory evaluation. This intelligent approach utilizes predefined class information for supervised learning in order to solve the converting problem and keep the fuzziness and imprecision of the whole sensory information. The method is validated by the experiment on stimulation evaluation of cigarette sensory.
