The image signal is represented by using the atomic of image signal to train an over complete dictionary and is described as sparse linear combinations of these atoms. Recently, the dictionary algorithm for image sign...The image signal is represented by using the atomic of image signal to train an over complete dictionary and is described as sparse linear combinations of these atoms. Recently, the dictionary algorithm for image signal tracking and decomposition is mainly adopted as the focus of research. An alternate iterative algorithm of sparse encoding, sample dictionary and dictionary based on atomic update process is K-SVD decomposition. A new segmentation algorithm of brain MRI image, which uses the noise reduction method with adaptive dictionary based on genetic algorithm, is presented in this paper, and the experimental results show that the algorithm in brain MRI image segmentation has fast calculation speed and the advantage of accurate segmentation. In a very complicated situation, the results show that the segmentation of brain MRI images can be accomplished successfully by using this algorithm, and it achieves the ideal effect and has good accuracy.展开更多
本研究将双种群遗传算法引入测试用例排序中以解决单一种群中过早收敛和最终解质量不稳定等问题,通过设置多样性较高的初始解,并在两个进化种群中使用不同的控制参数来协同进化,达到扩大解搜索空间的目的,以降低算法陷入局部最优的风险...本研究将双种群遗传算法引入测试用例排序中以解决单一种群中过早收敛和最终解质量不稳定等问题,通过设置多样性较高的初始解,并在两个进化种群中使用不同的控制参数来协同进化,达到扩大解搜索空间的目的,以降低算法陷入局部最优的风险;同时使用引入权重因子的平均方法覆盖率作为适应度函数,利用Boltzmann选择法实现不同进化阶段选择压力的自适应变化,期望加快算法后期收敛速度。最后在具有真实故障的数据集Defects4J上进行对比验证,结果表明:本文算法在平均故障检测率(average percentage of fault detection,APFD)方面优于单一种群遗传算法,且这种性能的提升在统计学上是显著的。展开更多
三维片上网络(3D No C)中IP核的测试问题日趋突出,测试规划是提高测试效率的有效方法。基于重用No C作为测试存取机制的并行测试方法,针对IP核测试数据传输带宽与TAM带宽不匹配的问题,提出带分复用方法,对有限带宽的TAM进行动态细分,将...三维片上网络(3D No C)中IP核的测试问题日趋突出,测试规划是提高测试效率的有效方法。基于重用No C作为测试存取机制的并行测试方法,针对IP核测试数据传输带宽与TAM带宽不匹配的问题,提出带分复用方法,对有限带宽的TAM进行动态细分,将多核的测试数据共享同一物理TAM实施并行传输,并结合3D No C结构设计二维编码,建立带宽分配和测试顺序模型,采用多种群遗传模拟退火算法,在总功耗、层功耗双重约束下对IP核的带宽分配和测试顺序进行双重优化,提高并行测试效率以获得最短测试时间。算法中针对测试顺序优化设计移位互换杂交策略,并运用精英配对方法加快种群寻优速度,设计求精操作进一步优化测试时间,通过比较、淘汰、替换机制加强种群间交流,增加种群多样性,避免算法陷入局部最优。以ITC'02标准电路作为测试对象,实验结果表明,该方法通过提高带宽利用率,提升了并行测试效率,降低了资源占用,有效地缩短了测试时间。展开更多
文摘The image signal is represented by using the atomic of image signal to train an over complete dictionary and is described as sparse linear combinations of these atoms. Recently, the dictionary algorithm for image signal tracking and decomposition is mainly adopted as the focus of research. An alternate iterative algorithm of sparse encoding, sample dictionary and dictionary based on atomic update process is K-SVD decomposition. A new segmentation algorithm of brain MRI image, which uses the noise reduction method with adaptive dictionary based on genetic algorithm, is presented in this paper, and the experimental results show that the algorithm in brain MRI image segmentation has fast calculation speed and the advantage of accurate segmentation. In a very complicated situation, the results show that the segmentation of brain MRI images can be accomplished successfully by using this algorithm, and it achieves the ideal effect and has good accuracy.
文摘本研究将双种群遗传算法引入测试用例排序中以解决单一种群中过早收敛和最终解质量不稳定等问题,通过设置多样性较高的初始解,并在两个进化种群中使用不同的控制参数来协同进化,达到扩大解搜索空间的目的,以降低算法陷入局部最优的风险;同时使用引入权重因子的平均方法覆盖率作为适应度函数,利用Boltzmann选择法实现不同进化阶段选择压力的自适应变化,期望加快算法后期收敛速度。最后在具有真实故障的数据集Defects4J上进行对比验证,结果表明:本文算法在平均故障检测率(average percentage of fault detection,APFD)方面优于单一种群遗传算法,且这种性能的提升在统计学上是显著的。
文摘三维片上网络(3D No C)中IP核的测试问题日趋突出,测试规划是提高测试效率的有效方法。基于重用No C作为测试存取机制的并行测试方法,针对IP核测试数据传输带宽与TAM带宽不匹配的问题,提出带分复用方法,对有限带宽的TAM进行动态细分,将多核的测试数据共享同一物理TAM实施并行传输,并结合3D No C结构设计二维编码,建立带宽分配和测试顺序模型,采用多种群遗传模拟退火算法,在总功耗、层功耗双重约束下对IP核的带宽分配和测试顺序进行双重优化,提高并行测试效率以获得最短测试时间。算法中针对测试顺序优化设计移位互换杂交策略,并运用精英配对方法加快种群寻优速度,设计求精操作进一步优化测试时间,通过比较、淘汰、替换机制加强种群间交流,增加种群多样性,避免算法陷入局部最优。以ITC'02标准电路作为测试对象,实验结果表明,该方法通过提高带宽利用率,提升了并行测试效率,降低了资源占用,有效地缩短了测试时间。