I. Dalezios et Kj. Siebert, Comparison of pattern recognition techniques for the identification of lactic acid bacteria, J APPL MICR, 91(2), 2001, pp. 225-236
Aims: The goal of this study was to evaluate three pattern recognition meth
ods for use in the identification of lactic acid bacteria.
Methods and Results: Lactic acid bacteria (21 unknown isolates and 30 well-
characterized strains), including the Lactobacillus, Lactococcus, Streptoco
ccus, Pediococcus and Oenococcus genera, were tested for 49 phenotypic resp
onses (acid production on carbon sources). The results were scored in sever
al ways. Three procedures, k-nearest neighbour analysis (KNN), k-means clus
tering and fuzzy c-means clustering (FCM), were applied to the data.
Conclusions: k-Nearest neighbour analysis performed better with five-point-
scaled than with binary data, indicating that intermediate values are helpf
ul to classification. k-Means clustering performed slightly better than KNN
and was best with fuzzified data. The best overall results were obtained w
ith FCM. Genus level classification was best with FCM using an exponent of
1.25.
Significance and Impact of the Study: The three pattern recognition methods
offer some advantages over other approaches to organism classification.