The phrase "accuracy curve" is correct and usable in written English.
It can be used in contexts related to statistics, data analysis, or machine learning to describe a graphical representation of the accuracy of a model or system over a range of thresholds or conditions.
Example: "The accuracy curve demonstrated a significant improvement in model performance as the training dataset increased in size."
Alternatives: "performance curve" or "precision curve".
To improve the accuracy, curve reconstruction under the minimum curvature constraint instead of point-based reconstruction was employed.
In a cumulative accuracy curve, the accuracy for predictions up to the (nu) th quantile of the AD measure is plotted against the quantile (nu) (or the percentage of data, respectively).
A closer look at the per-class accuracies (data not shown) reveals that it is mainly the second texture class, see Figure 1, with large homogeneous intensity patches in the pattern that causes this dip in the mean accuracy curve for MBP.
Based on the preceding analysis of the judge accuracy curve, we return to the cost analysis.
The Condorcet Jury Theorem shows that for equally accurate judges the judge accuracy curve monotonically increases as the number of judges increase.
Ultimately, the cost analysis relies on the calculation of the probability of an error as a function of the number of judges (the judge accuracy curve).
Figure 4, comparing the accuracy curves of different aggregation strategies, shows that separable aggregation closely follows the original implementation in most cases.
By varying the radius value, we can repeat the segmentation for different seed sets and trace accuracy curves using the dice coefficient of similarity and error curves of false positive (normalized by the object size).
The mean accuracy curves (dice coefficient of similarity) and the normalized false positive curves, using non-equally eroded-dilated seeds, for segmenting: (a,b) calcaneus, (c,d) talus, and (e,f) liver.
The results show stable performance of established classifiers and efficient (low number of samples requested) as well as fast integration (steeply rising accuracy curves) of new event types (classes).
Thus, judge accuracy curves need not be monotonic.
