admin 管理员组

文章数量: 1086019


2024年4月14日发(作者:instrument是集合名词吗)

模式识别中 距离方法名称及算法流程

1.最常见的距离方法是欧氏距离,它是通过两个点之间的直线距

离来计算它们之间的相似性。

The most common distance method is Euclidean distance,

which calculates the similarity between two points by the

straight-line distance between them.

2.切比雪夫距离是通过两个点之间的最大差值来表示它们之间的

不相似度。

Chebyshev distance represents the dissimilarity between

two points by the maximum difference between them.

3.曼哈顿距离是通过两个点在各个维度上的差值的绝对值之和来

计算它们之间的距离。

Manhattan distance calculates the distance between two

points by the sum of the absolute differences in each

dimension.

4.闵可夫斯基距离是欧氏距离和曼哈顿距离的一般化表示形式,

具有一个参数p用于调节计算过程。

Minkowski distance is a generalization of Euclidean

distance and Manhattan distance with a parameter p to adjust

the calculation process.

5.马氏距离考虑了各个维度之间的相关性,通过协方差矩阵的逆

来调整欧氏距离的计算结果。

Mahalanobis distance takes into account the correlation

between dimensions and adjusts the calculation of Euclidean

distance using the inverse of the covariance matrix.

6.汉明距离是用来衡量两个等长字符串之间的不同之处的度量,

即它们在相应位置上的不同字符的个数。

Hamming distance is a measure used to measure the

differences between two equally long strings, i.e., the

number of different characters at corresponding positions.


本文标签: 距离 计算 方法 集合 用于