排序方式: 共有4条查询结果,搜索用时 33 毫秒
1
1.
2.
Neural-mechanism-driven image block encryption algorithm incorporating a hyperchaotic system and cloud model 下载免费PDF全文
Peng-Fei Fang 《中国物理 B》2022,31(4):40501-040501
An image encryption algorithm is proposed in this paper based on a new four-dimensional hyperchaotic system, a neural mechanism, a Galois field and an improved Feistel block structure, which improves the efficiency and enhances the security of the encryption algorithm. Firstly, a four-dimensional hyperchaotic system with a large key space and chaotic dynamics performance is proposed and combined with a cloud model, in which a more complex and random sequence is constructed as the key stream, and the problem of chaotic periodicity is solved. Then, the key stream is combined with the neural mechanism, Galois field and improved Feistel block structure to scramble and diffuse the image encryption. Finally, the experimental results and security analysis show that the encryption algorithm has a good encryption effect and high encryption efficiency, is secure, and can meet the requirements of practical applications. 相似文献
3.
上市公司财务危机预警分析——基于数据挖掘的研究 总被引:3,自引:0,他引:3
本文以我国上市公司为研究对象,选取了1999-2001年被ST的公司和正常公司各73家作为训练样本,2002年被ST的公司和正常公司各43家作为检验样本,分析了财务危机出现前2年内各年两类公司15个财务指标。在进行数据挖掘中,我们运用了三种独立的方法,分别为判别分析、Logistic回归和神经网络,结果发现神经网络预测的效果要优于其它两种方法。最后,结合了这些方法的优点,建立了一种混合模型,研究表明预测的正确性要高于每种单独方法,从而提高了模型的预警效果。 相似文献
4.
1