Reduction number basic data

Funds available for hardware for one year were about 11,000. This limited the size of our basic system and made the requirement for modularity especially important. We plan to expand our system to increase the number of detectors that may be sampled simultaneously and increase the complexity of data reduction calculations. The expansion of core size to permit the use of Fortran or Algol would also be desirable at some future date. 

Spectroscopic methods are increasingly employed for quantitative applications in many different fields, including chemistry [1]. The dimensionality of spectral data sets is basically limited by the number of the objects studied, whereas the number of variables can easily reach a few thousands. Highdimensional spectral data are very correlated and usually somewhat noisy, so that, the conventional multiple linear regression (MLR) cannot be applied to this type of data directly the feature selection or reduction procedures are needed [2],... 

In the future, electricity production at large NPPs is likely to remain the main application of nuclear energy. This factor and the reduction of unit costs with increase in the power and number of nuclear units were the reasons for conceptual study of a 1,200 MWe lead-cooled fast reactor as a candidate basic component of a large-scale nuclear power mix. The BREST-OD-300 being developed as a prototype of the BREST-1200 reactor, their design and engineering features are largely similar, as may be seen from the data of Table 58.6 (ISTC 2001 Adamov et al. 1997). 

However, probabilistic methods can be applied only to discrete ordered monotonous characters. Continuous or unordered, non-monotonous characters can only be analysed after transformation or reduction. This can lead to many additional problems that are beyond the scope of the present chapter (but see (jrzymala-Busse, 2002, for an overview on data reduction and discretization problems). The method used to create probabilistic profiles for species is another major issue since the number and the diversity of strains taken into account can have a profound impact on the basic probabilities and, therefore, on the resulting identifications. 

---