Moreover, the methods performance is preserved in different conditions.
However, existing methods' performance is not unconditionally convincing.
The charts in Fig. 13 show the methods performance when σ=20.
Their aim is to compare the accuracy and convergence rate of these methods' performance.
Figure 9 Flow chart summarising methods' performance for each parameter setting on NEMA IQ data.
Relationship between earthquake methods performance at pre-test and earthquake methods performance at post-test as a function of embedding condition (dashed line, embedded; solid line, non-embedded) in the right panel.
Steganography methods' performance can be measured by the three valuable specifications: security, capacity, and visual imperceptibility [15, 16].
Open image in new window Fig. 10 Hybrid ANFIS methods' performance in the training and testing datasets.
Bar charts are used in Fig. 12 to represent the methods performance when the noise level is low σ=10.
It appeared that the process of inactive set formation had a substantial impact on the machine learning methods performance.
Steganographic methods' performance can be observed by the three valuable specifications: secrecy, volume/capacity, and visual imperceptibility [4].
