Namely, since the optical inverse model for a single subject's data is ill-posed, a solution needs to be selected that is consistent with both that single data set and with the images from other members of the group.
If a decision is made in favor of a big data project or of a general adoption of big data technology, relevant data sources need to be selected, which in an enterprise could be a variety of in-house source, e.g., databases, but could also be a variety of external sources, e.g., from the Web, which may provide relevant data for free or for a cost (as in the case of a data marketplace, see Sect. 5).
In addition to making the sampling data represent the original data effectively [76], how many instances need to be selected for data mining method is another research issue [77] because it will affect the performance of the sampling method in most cases.
Some general guidelines for processing the results of quality assessment experiments are detailed in [11] but, when dealing with subjective data, the statistical tools to be used need to be selected according to the properties of the data under analysis.
In standard methods, the alignment algorithm, evolutionary model and numerous parameters are needed to be selected and set case-by-case according to the heterogeneity of input data.
