Skip to main content
Figure 9 | Proteome Science

Figure 9

From: A guide through the computational analysis of isotope-labeled mass spectrometry-based quantitative proteomics data: an application study

Figure 9

Davies and Bouldin. Instead of simply proposing a cluster index, Davies and Bouldin formulated a general framework for the evaluation of the outcomes of cluster algorithms. In contrast to other indexes, an optimal cluster solution is indicated by the minimal calculated index value. For instance, for the two cluster algorithms K-means and Neuralgas a local minimum can be located around the 30-cluster solution. A general interpretation of this index, however, seems to be difficult due to a strong tendency towards constantly decreasing index values with regard to large cluster numbers.

Back to article page