發(fā)布時間：2018-04-22 06:33

  本文選題：總體最小二乘 + 相關觀測�。� 參考：《測繪學報》2017年08期

【摘要】：Partial errors-in-variables(Partial-EIV)模型作為EIV模型的擴展形式,其構造方式更有規(guī)律,解算方法更為簡便,能有效應用于實際情況。針對已有Partial EIV模型方法未考慮觀測向量和系數(shù)矩陣存在相關性這一情況,通過提取觀測向量和系數(shù)矩陣組成的增廣矩陣中非重復出現(xiàn)的隨機元素,構建更具一般適用性的Partial EIV模型,在該模型的基礎上,將特殊假定條件擴展到不限定觀測數(shù)據(jù)相關性的一般情況,詳細推導了觀測向量和系數(shù)矩陣元素相關且不等精度情況下的加權總體最小二乘方法,通過算例試驗,并與目前已有的解決EIV模型相關觀測情況下的方法進行了比較分析,研究表明本文方法可以提高計算效率,更具一般性,特別是對于觀測向量和系數(shù)矩陣中存在常數(shù)元素和重復元素的情況。
[Abstract]:As an extended form of EIV model, the Partial errors-in-variables-Partial-Eve) model is constructed in a more regular manner, and its solution method is simpler and can be effectively applied to the actual situation. In view of the fact that the existing Partial EIV model methods do not consider the correlation between the observation vector and the coefficient matrix, the augmented matrix composed of the observation vector and the coefficient matrix is extracted. A more general applicable Partial EIV model is constructed. Based on the model, the special assumptions are extended to the general case of unqualified correlation of observed data. In this paper, the weighted population least square method with variable precision and correlation between the observation vector and coefficient matrix elements is derived in detail. The method is compared with the existing methods for solving the related observation of EIV model through an example. The results show that the proposed method can improve the computational efficiency and be more general, especially in the case of constant elements and repeated elements in the observation vector and coefficient matrix.
【作者單位】： 東華理工大學測繪工程學院;流域生態(tài)與地理環(huán)境監(jiān)測國家測繪地理信息局重點實驗室;江西省數(shù)字國土重點實驗室;武漢大學測繪學院;
【基金】：國家自然科學基金(41664001;41204003) 江西省杰出青年人才資助計劃項目(20162BCB23050) 國家重點研發(fā)計劃(2016YFB0501405) 江西省教育廳科技項目(GJJ150595)~~
【分類號】：P207

【相似文獻】

相關期刊論文 前1條

1 歐吉坤;相關觀測情況的可靠性研究[J];測繪學報;1999年03期

，

本文編號：1786042