Compared with the MLPNN model, the proposed RBFNN model provides superior performance, when the error efficiency and positional accuracy are considered.
Afterwards, the predictive results of the proposed RBFNN model are compared with the MLPNN model, considering the error efficiency and positional accuracy.
In this section, we show that under appropriate assumptions, the ZZ-type error estimators proposed provide an upper bound for the error (reliability) and, up to some higher-order terms, also a lower bound for the error (efficiency).
This dataset also contains five dimension usability scores: learnability, satisfaction, errors, efficiency and memorability [24].
Figure 6 shows the performance comparison of our NPCS algorithm with different K p and K g on three scan pairs G a, G e and G i. First, we fixed K g = 50 and tested the effects of different K p on the registration accuracy (median estimation errors), efficiency (median estimation times) and robustness (successful estimation rates), as shown in Figure 6a, b, c, respectively.
Error and efficiency values for each mRNA standard curve were <0.009 and >1.8, respectively, except for ACTG1, where the efficiency was 1.789.
Based on these relationships, the error in efficiency for the experimental setup is ±0.5%%.
Quantitative indices to estimate perceptive quality, such as relative errors and efficiencies, were defined and applied to particular cases.
The experiments focused on three main aspects: robustness (successful estimation rate), accuracy (median estimation error), and efficiency (median estimation time), respectively.
For E91, the overall limit (E_{mathit {E}91}^{mathit {max}}) is 11.0% [28], assuming optimal classical PP with error correction efficiency (f=1).
We have also measured different parameters like fault recovery time, power consumption, resource overhead and error correction efficiency to estimate the performance of our proposed methods.
