Similar to other algorithm, K-mean clustering has many weaknesses:

?

1 When the numbers of data are not so many, initial grouping will determine the cluster significantly.? 當(dāng)數(shù)據(jù)數(shù)量不是足夠大時(shí)，初始化分組很大程度上決定了聚類，影響聚類結(jié)果。
2 The number of cluster, K, must be determined before hand.? 要事先指定K的值。
3 We never know the real cluster, using the same data, if it is inputted in a different order may produce different cluster if the number of data is a few. 數(shù)據(jù)數(shù)量不多時(shí)，輸入的數(shù)據(jù)的順序不同會(huì)導(dǎo)致結(jié)果不同。
4 Sensitive to initial condition. Different initial condition may produce different result of cluster. The algorithm may be trapped in the local optimum. 對(duì)初始化條件敏感。
5 We never know which attribute contributes more to the grouping process since we assume that each attribute has the same weight. 無法確定哪個(gè)屬性對(duì)聚類的貢獻(xiàn)更大。
6 weakness of arithmetic mean is not robust to outliers. Very far data from the centroid may pull the centroid away from the real one. 使用算術(shù)平均值對(duì)outlier不魯棒。
7 The result is circular cluster shape because based on distance.? 因?yàn)榛诰嚯x，故結(jié)果是圓形的聚類形狀。

?

One way to overcome those weaknesses is to use K-mean clustering only if there are available many data. To overcome outliers problem, we can use median instead of mean.? 克服缺點(diǎn)的方法： 使用盡量多的數(shù)據(jù)；使用中位數(shù)代替均值來克服outlier的問題。

Some people pointed out that K means clustering cannot be used for other type of data rather than quantitative data. This is not true! See how you can use multivariate data up to n dimensions (even mixed data type) here. The key to use other type of dissimilarity is in the distance matrix.

?

http://people.revoledu.com/kardi/tutorial/kMean/Weakness.htm

轉(zhuǎn)載于:https://www.cnblogs.com/emanlee/archive/2012/03/06/2381617.html

總結(jié)

以上是生活随笔為你收集整理的k-means k均值聚类的弱点/缺点的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。