Sentence examples for heterogeneous prediction from inspiring English sources

We considered the AODE and BayesNet classification algorithms as the best candidates to address our problem, the prediction of protein functional interactions by combining results of five heterogeneous prediction methods, protein size and number of orthologues of each one of the two proteins.

While some methods can be considered as generally good choices over all data sets and scenarios, other methods show heterogeneous prediction quality on the different data sets.

While some methods, such as ARH, can be considered as generally good choices over all data sets and scenarios, other methods show heterogeneous prediction quality on the different data sets.

Summing up the above literature survey, it is obvious that various theory and empirical results produce heterogeneous predictions on the underlying determinants of current account imbalance which opens the avenue for further investigation.

Nam and Kim [80] proposed an HTL method called Heterogeneous Defect Prediction (HDP) for software defect prediction, though it can also be applied for other tasks.

While heterogeneous cooperative prediction refers to the general case of non-identical secondary user detection performance.

The proposed solution, referred to as the heterogeneous defect prediction (HDP) approach, is to first select the important features from the source domain using a feature selection method to eliminate redundant and irrelevant features.

These benefits include integration of heterogeneous databases, prediction of disease genes and increased quality of modules of cellular machinery.

The comparison with the heterogeneous model predictions for a random packing and with industrial values pointed out that the choice of parameters is fundamental to the performance of the catalyst.

More generally, while epiphyte response to global climate change on tropical mountains is discussed in the literature, tropical mountains and their climates are highly heterogeneous, and predictions may defy all but the broadest generalizations.

But for a complex, heterogeneous landscape, the prediction accuracy of ESTARFM is improved even more compared with STARFM (AAD 0.0135 vs. 0.0194).