Excellent mechanical property of the anti-compression or high collapse pressure has become an essential feature of new coronary stents. How to determine the design parameters of stent becomes the key to improve the st...Excellent mechanical property of the anti-compression or high collapse pressure has become an essential feature of new coronary stents. How to determine the design parameters of stent becomes the key to improve the stent quality. An integrated approach using radial basis function neural network （RBFNN） and genetic algorithm （GA） for the optimization of anti-compression mechanical property of stent is presented in this paper. First, finite element simulation and RBFNN are used to map the complex non-linear relationship between the collapse pressure and stent design parameters. Then GA is employed with the fitness function based on an RBFNN model for arriving at optimum configuration of the stent by maximizing the collapse pressure. The results of numerical experiment demonstrate that the combination of RBFNN and GA is an effective approach for the mechanical properties optimization of stent.展开更多
数字图像取证是计算机取证、信息安全领域的一门新学科。为实现照片图像与真实感计算机图形的可靠识别,提出一种基于图像稀疏表示的数字图像取证方法,该方法在抵抗压缩方面具有较好性能,从而保证图像压缩不会改变照片图像与真实感计算...数字图像取证是计算机取证、信息安全领域的一门新学科。为实现照片图像与真实感计算机图形的可靠识别,提出一种基于图像稀疏表示的数字图像取证方法,该方法在抵抗压缩方面具有较好性能,从而保证图像压缩不会改变照片图像与真实感计算机图形的真实性本质。Tetrolet变换为保护图像局部几何结构,在L1-范数最小约束下搜索4×4图像块的最优覆盖(Covering)形式,获得图像的稀疏表示。观察自适应值c的统计分布,得到一幅图像中117种Covering出现次数的归一化直方图,从而得到图像的HoC(histogram of covering)特征。实验结果表明,在饱和度(S)分量提取的HoC特征能够很好地刻画照片图像与真实感计算机图形在局部几何结构上的不同统计特性,算法在识别能力、泛化能力,尤其是抵抗压缩能力上表现出良好性能,能够应用于图像真实性检测及照片图像与计算机图形的自动分类。展开更多
基金supported by National Basic Research Program of China (973 program,No.2006CB708610)Jiangsu Provincial Key Natural Science Foundation of China (No.BK2006709)Doctoral Foundation of Ministry of Education of China (No.20060286012).
文摘Excellent mechanical property of the anti-compression or high collapse pressure has become an essential feature of new coronary stents. How to determine the design parameters of stent becomes the key to improve the stent quality. An integrated approach using radial basis function neural network （RBFNN） and genetic algorithm （GA） for the optimization of anti-compression mechanical property of stent is presented in this paper. First, finite element simulation and RBFNN are used to map the complex non-linear relationship between the collapse pressure and stent design parameters. Then GA is employed with the fitness function based on an RBFNN model for arriving at optimum configuration of the stent by maximizing the collapse pressure. The results of numerical experiment demonstrate that the combination of RBFNN and GA is an effective approach for the mechanical properties optimization of stent.
文摘数字图像取证是计算机取证、信息安全领域的一门新学科。为实现照片图像与真实感计算机图形的可靠识别,提出一种基于图像稀疏表示的数字图像取证方法,该方法在抵抗压缩方面具有较好性能,从而保证图像压缩不会改变照片图像与真实感计算机图形的真实性本质。Tetrolet变换为保护图像局部几何结构,在L1-范数最小约束下搜索4×4图像块的最优覆盖(Covering)形式,获得图像的稀疏表示。观察自适应值c的统计分布,得到一幅图像中117种Covering出现次数的归一化直方图,从而得到图像的HoC(histogram of covering)特征。实验结果表明,在饱和度(S)分量提取的HoC特征能够很好地刻画照片图像与真实感计算机图形在局部几何结构上的不同统计特性,算法在识别能力、泛化能力,尤其是抵抗压缩能力上表现出良好性能,能够应用于图像真实性检测及照片图像与计算机图形的自动分类。
