Table 3.
Comparison of closed set RFF identification mechanisms
Mechanisms | Classifier | Against non-idealenvironment | Against large-scaleidentification | Classification accuracy |
---|---|---|---|---|
TML-based | Simplea | Most rely on preprocessing | Applicable to tens of devices | Lowb |
DL-based | Complexc | Most rely on neural network design | Applicable to more than 10 000 devices | High |
Note: (a)Most are TML-based classifiers. (b)Well-designed RFF features may perform better than some of the DL-based methods. (c)Both TML and DL algorithms are applicable as classifiers.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.