Evaluating the confidence level of prognostic predictions

Classification and prediction are effective tools in anomaly and fault detection. They can be used in development of a continuous learning prediction method. Inaccurate classification will result in either too many or too few anomalies or under- and over-diagnosis. The confidence of prediction relies on the accurate determination of class centers and borders based on the adequate training data. This paper will present methods to evaluate the confidence level of class prediction from various points of view. It includes practical examples of experimental data collected from machines at various locations.