The Modified DNA Identification Classification on Fuzzy Relation
We proposed a categorized method of DNA sequences matrix by FCM (fuzzy cluster means). FCM avoided the errors caused by the reduction of dimensions. It further reached comprehensive machine learning. In our experiment, there are 40 training data which are artificial samples, and we verify the proposed method with 182 natural DNA sequences. The result showed the proposed method enhanced the accuracy of the classification of genes from 76% to 93%.
Y. J. Hu et al., "The Modified DNA Identification Classification on Fuzzy Relation", Applied Mechanics and Materials, Vols. 48-49, pp. 1275-1281, 2011