CTC works by resampling the training sample and building a tree from each subsample, in a similar manner to ensemble classifiers, but applying the ensemble process during the tree construction phase, resulting in a unique final tree.
To cope with this issue, existing research suggests several different approaches, such as altering the training sample by up-sampling or down-sampling, i.e., balancing.
Two layer HMMs will be trained by the training samples, and save as the model parameters λ = (A, B, Π) for testing.
Along the borders of two cover types, it may suggest that those two classes were not represented to the full extent by the training samples.
MaxEnt is a probability-based algorithm that estimates the posterior likelihood distribution of a variable by maximizing the entropy of said probability distribution while maintaining the constraints provided by the training samples [23].
However, it is not possible to guarantee the optimal solution and instead we replace it by the approximate solution provided in Equation (5): (5) T ≈ ER A, ω As the new case can be sufficiently represented by the training samples from the same class, we obtain the prediction by ω.
To gauge the dependency of system performance on the size of the training set, we progressively reduced the training data by iteratively discarding subsets from the training sample and refitting predictive models.
The second one is screening out outliers from the training sample set by assigning a special value to the penalty factor, and training out the optimal penalty factor from the remained training sample set without outliers.
In this article, the optimal initial centers are determined by analyzing the knowledge rule of the training sample set based on rough set theory, instead of iteration.
