The developed models are validated through randomly generated examples and a real case study in retailing.
Conversely, under-sampling randomly picks examples from the majority class until the number of examples matches the size of the minority class.
Unlike random (or passive) learning, in which a classifier randomly selects examples from which to learn, the ML based classifier actively indicates the specific examples which are commonly the most informative examples for the training task and should be labeled.
The proposed algorithm is performed for several randomly generated examples and compared with the optimum solutions.
Next, we apply the three algorithms ([19, 21] and our own) to randomly generated examples as follows.
Note that six applications have a "DP" suffix and consist of randomly selected examples of design patterns implemented by Hannemann and Kiczales [67].
Through randomly generated examples with different sizes; the computational performance of the proposed algorithm is also compared with former genetic algorithms in the literature employing the weight-sum technique as a fitness evaluation strategy.
We will now compare all the five basis reduction methods, namely, LLL, DEEP, SLLL, VLLL, and PLLL, based on the 10, 000 randomly simulated examples and in terms of the six quality measures of reduction discussed in Section 3.
Having applied LLL, DEEP, SLLL, VLLL, and PLLL to the 10, 000 randomly simulated examples, we have obtained the 10, 000 condition numbers for each of these methods, which are denoted by κ B LLL, κ B DEEP, κ B SLLL, κ B VLLL, and κ B PLLL, respectively.
