摘要
部分岭估计在许多实际的数据处理中是非常有效的,但其岭参数的确定始终是个难点问题。针对这个问题展开了分析,推导了广义交叉检核法、L-曲线法等几种常用的岭参数确定方法在部分岭估计模型下的具体形式。通过对其算例进行计算分析并比较了各自的优缺点。结果证明,L-曲线法虽然无法定义最优,但是适用性好,稳定性佳,与前两种方法相比有一定优势。
Partial Ridge Estimation was very effective in many data processing, but the determination of ridge parameters was a issue. Partial Ridge Estimation shared the difficulty of the determination of ridge parameters. Several methods of ridge parameters determination, such as Ridge trace, general cross-validation and L-curve method were formulated under the Partial Ridge Estimation Model, their performance was also analyzed and got some conclusions.
出处
《测绘科学技术学报》
北大核心
2007年第6期413-414,418,共3页
Journal of Geomatics Science and Technology