Skip to main content

Table 3 Relationship between different training set sizes, different thresholds and the quantity of the entities that can be geolocated and geolocation error

From: Geolocation of covert communication entity on the Internet for post-steganalysis

Landmark setsUQCG/QCNGMGE
Training set size§ > 100
(a total of 40 training sets and 41,231 landmarks)
0.99321/13652.80 km
0.810109/5774.62 km
0.710549/1376.16 km
Training set size > 300
(a total of 14 training sets and 37,134 landmarks)
0.98203/24832.26 km
0.88748/19382.97 km
0.79108/15784.05 km
Training set size > 500
(a total of 10 training sets and 32,241 landmarks)
0.97296/33902.18 km
0.88052/26342.51 km
0.78724/19622.96 km
  1. §“Training set size > N” represents a landmark set composed of all training sets with a landmark quantity greater than N in the training set
  2. U is short for “geolocation threshold”
  3. QCG is short for “quantity of the entities that can be geolocated”
  4. QCNG is short for “quantity of the entities that cannot be geolocated”
  5. MGE is short for “median geolocation error of the entities that can be geolocated”