带噪声奇偶学习问题(learning parity with noise,LPN)是密码学中的一类重要困难问题,它可以视作随机线性码译码问题的一般形式,是抗量子假设中的有力候选.在求解LPN问题前,通常需要执行约简操作,将待求实例转化为秘密长度更短的实例....带噪声奇偶学习问题(learning parity with noise,LPN)是密码学中的一类重要困难问题,它可以视作随机线性码译码问题的一般形式,是抗量子假设中的有力候选.在求解LPN问题前,通常需要执行约简操作,将待求实例转化为秘密长度更短的实例.本文提出了一种新的混合约简算法Hybrid,它将经典的丢弃约简算法和覆盖码约简算法相结合,在约简过程中丢弃与码字距离超过给定界限的LPN样本,而非将所有样本直接近似到码字.这种新的约简方法可以到达权衡样本复杂度和时间复杂度的目的.从算法层面讲,丢弃约简与覆盖码约简可以视作混合约简的特例.最后,使用池化高斯算法求解经过混合约简后的LPN样本,给出了其完整的理论复杂度.数值估计的结果表明混合约简可以进一步缩减良好池化高斯算法(Well-Pooled Gauss)的样本复杂度,但需要以时间开销上升为代价.展开更多
The objective of this paper is to improve the monitoring speed and precision of fractional vegetation cover (fc). It mainly focuses on fc estimation when fcmax and fcmin are not approximately equal to 100% and 0%, res...The objective of this paper is to improve the monitoring speed and precision of fractional vegetation cover (fc). It mainly focuses on fc estimation when fcmax and fcmin are not approximately equal to 100% and 0%, respectively due to using remote sensing image with medium or low spatial resolution. Meanwhile, we present a new method of fc estimation based on a random set of fc maximum and minimum values from digital camera (DC) survey data and a di- midiate pixel model. The results show that this is a convenient, efficient and accurate method for fc monitoring, with the maximum error -0.172 and correlation coefficient of 0.974 between DC survey data and the estimated value of the remote sensing model. The remaining DC survey data can be used as verification data for the precision of the fc estimation. In general, the estimation of fc based on DC survey data and a remote sensing model is a brand-new development trend and deserves further extensive utilization.展开更多
文摘带噪声奇偶学习问题(learning parity with noise,LPN)是密码学中的一类重要困难问题,它可以视作随机线性码译码问题的一般形式,是抗量子假设中的有力候选.在求解LPN问题前,通常需要执行约简操作,将待求实例转化为秘密长度更短的实例.本文提出了一种新的混合约简算法Hybrid,它将经典的丢弃约简算法和覆盖码约简算法相结合,在约简过程中丢弃与码字距离超过给定界限的LPN样本,而非将所有样本直接近似到码字.这种新的约简方法可以到达权衡样本复杂度和时间复杂度的目的.从算法层面讲,丢弃约简与覆盖码约简可以视作混合约简的特例.最后,使用池化高斯算法求解经过混合约简后的LPN样本,给出了其完整的理论复杂度.数值估计的结果表明混合约简可以进一步缩减良好池化高斯算法(Well-Pooled Gauss)的样本复杂度,但需要以时间开销上升为代价.
基金Projects NCET-04-0484 supported by the New-Century Outstanding Young Scientist Program from the Ministry of Education and D0605046040191-101Beijing Science and Technology Program
文摘The objective of this paper is to improve the monitoring speed and precision of fractional vegetation cover (fc). It mainly focuses on fc estimation when fcmax and fcmin are not approximately equal to 100% and 0%, respectively due to using remote sensing image with medium or low spatial resolution. Meanwhile, we present a new method of fc estimation based on a random set of fc maximum and minimum values from digital camera (DC) survey data and a di- midiate pixel model. The results show that this is a convenient, efficient and accurate method for fc monitoring, with the maximum error -0.172 and correlation coefficient of 0.974 between DC survey data and the estimated value of the remote sensing model. The remaining DC survey data can be used as verification data for the precision of the fc estimation. In general, the estimation of fc based on DC survey data and a remote sensing model is a brand-new development trend and deserves further extensive utilization.
