Molecular programming is applied to minimum spanning problem whose solution requires encoding of real values in DNA strands. A new encoding scheme is proposed for real values that is biologically plausible and has a f...Molecular programming is applied to minimum spanning problem whose solution requires encoding of real values in DNA strands. A new encoding scheme is proposed for real values that is biologically plausible and has a fixed code length. According to the characteristics of the problem, a DNA algorithm solving the minimum spanning tree problem is given. The effectiveness of the proposed method is verified by simulation. The advantages and disadvantages of this algorithm are discussed.展开更多
Based on the graphic theory and improved genetic algorithm,an improved genetic algorithm to search the minimum spanning trees is given . The algorithm uses binary code to represent the problem of minimum spanning tree...Based on the graphic theory and improved genetic algorithm,an improved genetic algorithm to search the minimum spanning trees is given . The algorithm uses binary code to represent the problem of minimum spanning trees. It designs the corresponding fitness function,operator and few controlling strategies to improve its speed and evolutionary efficiency.Only one solution can be gotten with running traditional al-gorithem atone time.The new algorithm can get a set of the solutions with higher probability in a shorter time.The experiment shows that it has a better performance than traditional methods.展开更多
针对医学图像配准鲁棒性强、准确性高和速度快的要求,提出了一种基于融合多种特征点信息的最小生成树医学图像配准算法.该算法首先提取3种特征点,Harris-Laplace,Laplacian of Gaussian和网格点;然后使用遗传算法去除特征点集的冗余,并...针对医学图像配准鲁棒性强、准确性高和速度快的要求,提出了一种基于融合多种特征点信息的最小生成树医学图像配准算法.该算法首先提取3种特征点,Harris-Laplace,Laplacian of Gaussian和网格点;然后使用遗传算法去除特征点集的冗余,并通过对位映射构建无向完全图顶点集合;进而使用改进的Kruskal算法来构造最小生成树;最后使用得到的最小生成树估计Rényi熵.该算法较好地解决了在噪声数据中使用最小生成树估计Rényi熵面临的特征点不稳定导致鲁棒性低和构造最小生成树遇到的速度瓶颈.实验结果表明:在图像含有噪声、灰度不均匀以及初始误配范围较大的情况下,该算法在达到良好配准精度的同时,具有较强的鲁棒性和较快的速度.展开更多
文摘Molecular programming is applied to minimum spanning problem whose solution requires encoding of real values in DNA strands. A new encoding scheme is proposed for real values that is biologically plausible and has a fixed code length. According to the characteristics of the problem, a DNA algorithm solving the minimum spanning tree problem is given. The effectiveness of the proposed method is verified by simulation. The advantages and disadvantages of this algorithm are discussed.
文摘Based on the graphic theory and improved genetic algorithm,an improved genetic algorithm to search the minimum spanning trees is given . The algorithm uses binary code to represent the problem of minimum spanning trees. It designs the corresponding fitness function,operator and few controlling strategies to improve its speed and evolutionary efficiency.Only one solution can be gotten with running traditional al-gorithem atone time.The new algorithm can get a set of the solutions with higher probability in a shorter time.The experiment shows that it has a better performance than traditional methods.
文摘针对医学图像配准鲁棒性强、准确性高和速度快的要求,提出了一种基于融合多种特征点信息的最小生成树医学图像配准算法.该算法首先提取3种特征点,Harris-Laplace,Laplacian of Gaussian和网格点;然后使用遗传算法去除特征点集的冗余,并通过对位映射构建无向完全图顶点集合;进而使用改进的Kruskal算法来构造最小生成树;最后使用得到的最小生成树估计Rényi熵.该算法较好地解决了在噪声数据中使用最小生成树估计Rényi熵面临的特征点不稳定导致鲁棒性低和构造最小生成树遇到的速度瓶颈.实验结果表明:在图像含有噪声、灰度不均匀以及初始误配范围较大的情况下,该算法在达到良好配准精度的同时,具有较强的鲁棒性和较快的速度.