Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Using the information embedded in the testing sample to break the limits caused by the small sample size in microarray-based classification

Figure 4

Experimental results with synthetic data. Shown here are the successful recognition rates obtained with a variety of classification approaches defined in the literature for increasing values of the dimensionality p – ranging from a low of 50 to a maximum of 400. Recognition rates shown in the scale of 0 to 1. (a) Results generated with a single Gaussian distribution per class. (b) Results obtained with samples randomly drawn from a mixture of four randomly generated Gaussian distribution per class.

Back to article page