Based on the generalized Fisher linear discriminant criterion, this problem is solved by combining projection transform, isomorphic mapping and compressed transform. 该文基于广义的Fisher线性判别准则,将投影变换、同构变换和压缩变换相结合,解决了这个问题,完善了小样本情况下线性鉴别分析理论。
Lastly, we construct the category of I-fuzzy remote neighborhood spaces and its continuous mapping, then prove that it is isomorphic to the category of I-fuzzy topological spaces and I-fuzzy continuous mapping. 最后,从范畴角度研究I-fuzzy拓扑。我们构造了一种新的邻域空间&I-fuzzy远域空间,并进一步证明了I-fuzzy远域空间范畴与I-fuzzy拓扑空间范畴同构。
Based on the idea of isomorphic mapping, We proposed an optimal kernel Fisher discriminant analysis ( OKFDA), from which we acquire a general algorithm for the computation of the optimal discriminant vectors in the singular cases. 基于同构映射的思想,我们提出了一种最优的核Fisher鉴别分析(OKFDA)方法,从理论上巧妙的解决了奇异情况下最优鉴别矢量集的求解问题。
An isomorphic mapping is built between Hibert space L2 [ 0,1 j and reproducing kernel space H1 [ 0,1] using integral operator while wavelet approximation expressions and sampling expressions in the H1 [ 0,1 j are discussed as well. 本文利用积分算子建立了Hibert空间L2[0,1]与再生核空间H1[0.1]之间的同构映射,给出再生核空间H1[0,1]中的多尺度分析方法、小波逼近公式和采样公式。
We also point out that Bessel's mapping is not an isomorphic mapping, it is impossible to fit to arbitrary distance of inverse solution of geodetic problem. 同时指出贝塞尔投影不是同胚映射,不适用于距离太远的大地问题反解。