A query chemical with leverage higher than the threshold is considered outside the AD and can be associated with unreliable prediction.
Thresholds have a great influence in characterising the AD for reliable predictions; a test sample that exceeds the threshold condition is associated with an unreliable prediction.
However, considerable heterogeneity exists within the Child-Pugh categories, resulting in an unreliable prediction of liver failure after hepatectomy [19, 20].
New input patterns that imply extrapolations and thus unreliable prediction by an artificial neural network model can be recognized from a significant decrease in the regional-knowledge index.
However, the lack in understanding of the influence of salinity interactions on MEOR processes had led to unreliable prediction of MEOR performance, and non-development of efficient strategies to improve the MEOR performance.
Conventional compositional simulators are usually difficult to interpret the different gas oil ratio (GOR) from tight oil reservoirs, and this also indicates an unreliable prediction of ultimate hydrocarbon recovery.
A stochastic-ranking selection scheme based on the prediction accuracy is designed to improve EA + predictor under unreliable prediction, where the prediction accuracy is based on the rank of the individuals but not the fitness.
If there is a test sample that seems to be quite in the vicinity of this potential outlier within the descriptor space, the test sample will be associated with an unreliable prediction since its distance from sample 49 will likely exceed the small threshold.
