Instead, we suggest using the features that are generated by discretization to extend the dataset by using both the discretized and non-discretized versions of the data.
To extend the dataset, additional stations from other projects and permanent networks were used (TIPAGE, CAIAG, IRIS, PMP, CAREMON; blue triangles in Figure 1; Sippl et al. (2013)).
It would be useful to extend the dataset presented in this paper in order to analyze the sensitivity of other aquatic or terrestrial organism groups used for pesticide homologation or ecotoxicology tests.
One possibility could have been to extend the dataset with SF data, however all of our patients requiring SF aspiration had active disease.
To extend the dataset, we carried out an alternative approach, pattern matching.
Data from our study support previous findings and extend the dataset for Europe.
For all the studies reported below, we extended the datasets with pure compounds.
Furlan's (2010) dataset is similar but not identical to ours, as she uses all large eruptions, not just those for stratovolcanoes, and we have extended the dataset to include recent eruptions.
Second, we have extended the dataset by including 62 tumors not included in the first dataset.
In another case (PGK), we extended the dataset with protein sequences from Oryzias latipes, Lepisosteus osseus, Rana sylvatica, Equus caballus, Sus scrofa, Bos taurus and Macropus eugenii.
