The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance.
Even though Random Forest does not need an internal test set for training, as do other methods such as an artificial neural network, we use an internal test set to adjust a threshold to optimise the classification in terms of the Matthews Correlation Coefficient, see below.
The identification of PTMs for each sequence segment of the query protein is done using the set of feed-forward artificial neural networks (ANN), which are trained with Back-Propagation (BP) learning algorithm (Rumelhart et al. 1986) to optimise the classification accuracy between the positive and the negative samples in the randomly chosen training subset of sequence segments.
The MCS could optimise the correct classification rate, reaching an accuracy of 91.7%.
However, our results proved that, although a single classifier trained separately with dynamic and morphological features achieves a low overall accuracy, the MCS could optimise the correct classification rate: dynamic features with the decision tree gave 60% accuracy, morphological features with the Bayes classifier gave 80% accuracy, and the MCS gave 91.7% accuracy.
The microarray design strategy was optimised for the classification of clinically relevant enterobacteria.
Given a perspective matrix M, object classification is performed for each blob b from the current frame as shown in Figure 4. Figure 4 Classification algorithm for optimising the parallelepiped model instance associated to a blob.
They are doing everything from making spoons lighter, to optimising the amount of water in toilets.
The Alexander technique, which is all about optimising the body's use, was incredibly helpful.
"The measures for optimising the portfolio and reducing costs are largely on track," it added.
